{"schema":"ai-blocks-role/1","id":"write-a-skill-and-check-it-is-safe-to-share","name":"AI skill release package builder","summary":"Give it the job you repeat, what a good result looks like and when it should start. You get a skill folder with test prompts, ready to add to your AI.","area":"engineering","family":{"id":"make-skills","name":"Make your own skills"},"lead":"write-a-skill-and-check-it-is-safe-to-share","featured":false,"contextKind":"project","deliverables":["A skill folder with test prompts, ready to add to your AI","A score with a fix list, in order of value","A grade for the description, with the skills that block it","A risk report on code and data leaks","A list of what stops it loading in other tools, with fixes"],"inputs":["The job you repeat, what a good result looks like and when it should start","A sample of the job done well (optional)","The other skills you already have installed (optional)","Where the skill will run, such as Claude, ChatGPT or Gemini (optional)"],"opening":{"give":["The job you repeat, what a good result looks like and when it should start","A sample of the job done well (optional)","Where the skill will run, such as Claude, ChatGPT or Gemini (optional)"],"get":["A skill folder with test prompts, ready to add to your AI","A score with a fix list, in order of value","A grade for the description, with the skills that block it","A risk report on code and data leaks"]},"helpfulInputs":[],"fit":["You repeat a job and want your AI to do it your way each time.","You are about to share a skill with a team or post it for others.","A skill you wrote never seems to fire, or breaks in another tool."],"limits":["You have a one-off task: just ask your AI directly, no skill needed.","You will never share the skill and only want a draft: use the Skill writer on its own.","You want to review someone else's skill for safety only: use the Skill safety checker."],"tools":[],"method":["Download the handoff pack from this page. It's a zip with HANDOFF.md and the five skill files, in the order they run: Skill writer, Skill quality tester, Skill trigger auditor, Skill safety checker and Skill portability checker.","Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say \"Follow HANDOFF.md\".","Describe the job in a few lines and say when it should start.","When it pauses, fix the skill files using the score and the trigger grade. Then tell it to carry on.","Read the risk report before you share anything. It lowers the risk and does not prove the skill is safe."],"capabilities":[{"name":"Write the skill","description":"Turns your job into a skill folder with clear steps, a description that says when to use it, and a few test prompts."},{"name":"Score its quality","description":"Reads every file first without running anything. Scripts run only inside limits you agree. Then it scores the skill with a list of fixes from most to least useful."},{"name":"Grade when it fires","description":"Grades the name and description the way your AI reads them. Tests which skill wins for sample requests. Flags skills that block each other."},{"name":"Pause, then apply the fixes","description":"You edit the skill using the score and the trigger grade. Keep a copy of the first draft so you can compare."},{"name":"Scan it for risk","description":"Reads every file without running it and lists risky commands, data leaks and hidden code, ranked."},{"name":"Check it loads elsewhere","description":"Looks for header errors, bad names, broken links and tool names that only work in one app, and gives each fix."}],"expertise":{"principles":["Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.","Make the smallest change that fully solves the request. Keep unrelated refactors out.","Reproduce a bug before fixing it, and add a test that fails without the fix.","Treat input from users, files and networks as untrusted. Validate it at the boundary."],"pitfalls":["Claiming code works without running it or its tests.","Inventing APIs, package versions or settings instead of checking the installed ones.","Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces."],"quality":["Each step passed its own checks, or the run stopped at the step that failed and says why.","The steps ran in order, and each one used the result of the one before.","Nothing was invented to fill a gap. Every gap is a MISSING: line.","Nothing was sent, published or paid for without a clear yes.","No script ran before the static read and the set limits, and the summary says what was run and what was only read.","The description says when to use the skill, each fix names a file or line, and each risk finding says what, where and what to do.","The changed files build, and the relevant tests and linters pass. The commands and results are shown."],"sources":{"learned":0,"curated":false,"method":6,"source":0,"area":"engineering"}},"workedExample":{"situation":"You repeat a job and want your AI to do it your way each time.","task":"Give it the job you repeat, what a good result looks like and when it should start. Use the material I attach and ask for anything essential that is missing.","given":["The job you repeat","What a good result looks like","When the skill should start","Skills you already have installed (optional)","A sample of the job done well (optional)"],"outputs":[{"name":"Step 1: The skill","contains":"A skill folder with test prompts, and a note on what it does and when it fires."},{"name":"Step 2: Quality score","contains":"A score, what is missing, and fixes in order of value."},{"name":"Step 3: Trigger grade","contains":"A grade for the description, prompts that should and should not fire it, and skills that block it."},{"name":"Step 4: Risk report","contains":"Risky code, data leaks and hidden code found in the fixed files, ranked, with what to remove or keep."},{"name":"Step 5: Portability","contains":"Problems that stop the skill loading in each named tool, with a fix for each."},{"name":"HAND-BACK SUMMARY","contains":"Each step's file, any step not run and why, and every MISSING line in one list."}]},"example":"Give it the job you repeat, what a good result looks like and when it should start. Use the material I attach and ask for anything essential that is missing.","functions":[{"name":"AI skill release package builder","description":"Share a repeated job and target AI tools. Get skill files, trigger feedback, quality checks, security findings and a scoped portability review.","method":"write-a-skill-and-check-it-is-safe-to-share","when":["You repeat a job and want your AI to do it your way each time.","You are about to share a skill with a team or post it for others.","A skill you wrote never seems to fire, or breaks in another tool."],"inputs":["The job you repeat, what a good result looks like and when it should start","A sample of the job done well (optional)","The other skills you already have installed (optional)","Where the skill will run, such as Claude, ChatGPT or Gemini (optional)"],"deliverables":["A skill folder with test prompts, ready to add to your AI","A score with a fix list, in order of value","A grade for the description, with the skills that block it","A risk report on code and data leaks","A list of what stops it loading in other tools, with fixes"]},{"name":"Skill writer","description":"Describe a job. Get draft skill instructions, test prompts and a trigger description to review.","method":"skill-writer","when":["You do the same task every week and want to turn it into a reusable skill.","You have a skill draft that gives uneven results.","You want proof a change made your skill better, not just different.","Your skill does not trigger when you expect it to."],"inputs":["A plain description of the job","An existing skill draft (optional)","Examples of good and bad results (optional)","Your feedback on each test run"],"deliverables":["A drafted skill with clear instructions","A set of test prompts","Side by side results with pass rates","A sharper trigger description"]},{"name":"Skill quality tester","description":"Give it a skill folder. Get structure and script checks, a quality score and a ranked fix list.","method":"skill-quality-tester","when":["You wrote a skill with scripts and want to know they run.","You want a letter grade and a list of what to improve.","You need a score gate in your build pipeline.","You review several skills and want to compare their scores, running the checks on each folder in turn."],"inputs":["A skill folder","Python 3","A minimum score (optional)"],"deliverables":["A structure check result","Script test results","A quality score and grade","An improvement road map","A security score"]},{"name":"Skill trigger auditor","description":"Share your skills. Get a grade for each on when it fires, and which skills block each other.","method":"skill-trigger-auditor","when":["A skill you wrote never seems to run and you do not know why.","You want to know which skill a request like \"deploy to prod\" will pick.","You have many skills and think two of them overlap.","You want a check that stops a pull request that adds a weak skill description."],"inputs":["The folder that holds your skills","A sample request to test (optional)"],"deliverables":["An A to F grade for every skill","A ranked list of which skill fires for your sample request","A list of skills that block each other","Suggested \"Use when\" lines for weak descriptions"]},{"name":"Skill safety checker","description":"Share a skill or bundle before you add it. Get risky code, data leaks and hidden payloads.","method":"skill-safety-checker","when":["You downloaded a bundle of skills and want a scan first.","You work on Windows and the checks you find are for Linux only.","A skill touches system folders and you want to know why.","You review skills for a company."],"inputs":["A skill or bundle folder","Your operating system (optional)","The skill source or link (optional)"],"deliverables":["Risky patterns found, grouped by threat","What each finding could do","Platform-specific notes","A summary of what to remove or ask about"]},{"name":"Skill portability checker","description":"Share your skill folder. Get mistakes that stop it loading in other AI tools, with fixes.","method":"skill-portability-checker","when":["You want your skill to work in several AI tools.","A skill loads in one app and fails silently in another.","You maintain a repo with many skills and need a bulk check.","You want CI to fail on skill errors."],"inputs":["The path to your skill folder, or to a folder with many skills","Your SKILL.md pasted in, if your AI cannot run code (optional)","Whether warnings should count as a fail (optional)"],"deliverables":["Errors and warnings by skill","A plain explanation of each","Fixes to apply","Machine-readable output if you ask"]},{"name":"AI project context organiser","description":"Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.","method":"agent-context-setter","when":["Your AI keeps ignoring your project's style or inventing functions that do not exist.","You are starting a new project and want the AI set up properly from day one.","Answers got worse halfway through a long session and you do not know why.","You are switching to a different part of the project and need the AI to catch up."],"inputs":["Your project folder or codebase, or a short description if you have no code yet","A short description of your project","The tools and commands you use","Rules the AI keeps breaking (optional)","Specs or notes for the current task (optional)"],"deliverables":["A ready rules file for your project","A list of which files to load for each task","Rules for when to reset or trim the session","A checklist for spotting drifting answers"]}],"resources":[{"slug":"write-a-skill-and-check-it-is-safe-to-share","name":"AI skill release package builder","summary":"Share a repeated job and target AI tools. Get skill files, trigger feedback, quality checks, security findings and a scoped portability review.","task":"make-skills","kind":"workflow","path":"/workflows/write-a-skill-and-check-it-is-safe-to-share","revision":"8438f1ffd24c9d44dd6a10416c2c8d79e5ac8a794bcf115c1094c9fd00d3504b","skillPath":"/skills/write-a-skill-and-check-it-is-safe-to-share/SKILL.md","bundled":false,"onboarding":false},{"slug":"skill-writer","name":"Skill writer","summary":"Describe a job. Get draft skill instructions, test prompts and a trigger description to review.","task":"make-skills","kind":"skill","path":"/skills/skill-writer","revision":"dc2bd78e76549b2f495b97f24f454ff3812572dc54343cdf45e203b2109ec2b8","skillPath":"/skills/skill-writer/SKILL.md","bundled":true,"onboarding":false,"by":"Anthropic"},{"slug":"skill-quality-tester","name":"Skill quality tester","summary":"Give it a skill folder. Get structure and script checks, a quality score and a ranked fix list.","task":"make-skills","kind":"skill","path":"/skills/skill-quality-tester","revision":"0fcfebf8c75a78f00ba03dc860d7d7f6746393c3f83ae4ee658c1c9daad325eb","skillPath":"/skills/skill-quality-tester/SKILL.md","bundled":true,"onboarding":false,"by":"Alireza Rezvani"},{"slug":"skill-trigger-auditor","name":"Skill trigger auditor","summary":"Share your skills. Get a grade for each on when it fires, and which skills block each other.","task":"make-skills","kind":"skill","path":"/skills/skill-trigger-auditor","revision":"c8028ae855b5dcd6e42cbf71a4d2951889248896b055b5d6fc866df8106d8510","skillPath":"/skills/skill-trigger-auditor/SKILL.md","bundled":true,"onboarding":false,"by":"sickn33"},{"slug":"skill-safety-checker","name":"Skill safety checker","summary":"Share a skill or bundle before you add it. Get risky code, data leaks and hidden payloads.","task":"make-skills","kind":"skill","path":"/skills/skill-safety-checker","revision":"1a06ee0510a6008d0b6cedd11f3079e36911e06e13e7a6cfddc9c98afdd282aa","skillPath":"/skills/skill-safety-checker/SKILL.md","bundled":true,"onboarding":false,"by":"sickn33"},{"slug":"skill-portability-checker","name":"Skill portability checker","summary":"Share your skill folder. Get mistakes that stop it loading in other AI tools, with fixes.","task":"make-skills","kind":"skill","path":"/skills/skill-portability-checker","revision":"95465b9679b0e70c867d3b33ee9368e7d292eb51e5a3aa43318e8460f51f170e","skillPath":"/skills/skill-portability-checker/SKILL.md","bundled":true,"onboarding":false,"by":"Pro Skill Packs"},{"slug":"agent-context-setter","name":"AI project context organiser","summary":"Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.","task":"set-up-ai","kind":"skill","path":"/skills/agent-context-setter","revision":"a4dc957663d15855fa51db8d4a5e7c9035da56577f8420d83d7e30ad4011354e","skillPath":"/skills/agent-context-setter/SKILL.md","bundled":false,"onboarding":true,"by":"Addy Osmani"}],"resourceCount":7,"sourceChecks":{"completeMethods":7,"referenceValidation":"PASS"},"catalogueHash":"3c3567ac2dbda7b2ac0cfaa8c93d8da3818f66bdadd51f18d8ff9051d77fc8f3","evaluation":{"status":"NOT_RUN","rubric":[{"id":"c1","criterion":"Delivers: A skill folder with test prompts, ready to add to your AI"},{"id":"c2","criterion":"Delivers: A score with a fix list, in order of value"},{"id":"c3","criterion":"Delivers: A grade for the description, with the skills that block it"},{"id":"c4","criterion":"Delivers: A risk report on code and data leaks"},{"id":"c5","criterion":"Each step passed its own checks, or the run stopped at the step that failed and says why."},{"id":"c6","criterion":"The steps ran in order, and each one used the result of the one before."},{"id":"c7","criterion":"Nothing was invented to fill a gap. Every gap is a MISSING: line."},{"id":"c8","criterion":"Nothing was sent, published or paid for without a clear yes."},{"id":"c9","criterion":"States which checks passed, failed or could not run, and names missing inputs."}],"goldenTasks":[{"id":"g1","kind":"core","situation":"You repeat a job and want your AI to do it your way each time.","expect":["A skill folder with test prompts, ready to add to your AI","A score with a fix list, in order of value","A grade for the description, with the skills that block it"]},{"id":"g2","kind":"core","situation":"You are about to share a skill with a team or post it for others.","expect":["A skill folder with test prompts, ready to add to your AI","A score with a fix list, in order of value","A grade for the description, with the skills that block it"]},{"id":"g-missing","kind":"missing-input","situation":"The request leaves out: The job you repeat, what a good result looks like and when it should start","expect":["Names the missing input and asks for it, or finishes only the parts that do not depend on it."]}],"note":"These checks are defined but have not been run against a model yet."},"version":{"number":3,"since":"2026-11-03","changes":[{"version":3,"date":"2026-11-03","what":"Source methods updated to new revisions."},{"version":2,"date":"2026-11-03","what":"Updated scope, deliverables or inputs. Updated worked example."},{"version":1,"date":"2026-11-02","what":"First recorded version."}]},"learning":{"rules":[],"maturity":{"level":0,"name":"Not measured yet","runs":0,"score":0,"editRatio":0,"acceptance":0,"critical":0,"next":"10 reviewed jobs, average check score 70%+"}},"worker":{"schema":"ai-blocks-specialist-worker/1","id":"write-a-skill-and-check-it-is-safe-to-share","name":"AI skill release package builder","interface":{"inputs":[{"type":"short_text","required":true}],"outputs":[{"type":"document","required":true}],"brief":"The current task in the workflow goal and supplied context.","handoff":"work/handoff.md indexes the actual native deliverables and checks. An index does not replace a requested implementation."},"identity":{"remit":"Give it the job you repeat, what a good result looks like and when it should start. You get a skill folder with test prompts, ready to add to your AI.","capabilities":[{"name":"Write the skill","description":"Turns your job into a skill folder with clear steps, a description that says when to use it, and a few test prompts."},{"name":"Score its quality","description":"Reads every file first without running anything. Scripts run only inside limits you agree. Then it scores the skill with a list of fixes from most to least useful."},{"name":"Grade when it fires","description":"Grades the name and description the way your AI reads them. Tests which skill wins for sample requests. Flags skills that block each other."},{"name":"Pause, then apply the fixes","description":"You edit the skill using the score and the trigger grade. Keep a copy of the first draft so you can compare."},{"name":"Scan it for risk","description":"Reads every file without running it and lists risky commands, data leaks and hidden code, ranked."},{"name":"Check it loads elsewhere","description":"Looks for header errors, bad names, broken links and tool names that only work in one app, and gives each fix."}],"limits":["You have a one-off task: just ask your AI directly, no skill needed.","You will never share the skill and only want a draft: use the Skill writer on its own.","You want to review someone else's skill for safety only: use the Skill safety checker."]},"intake":{"state":"REVIEW_REQUIRED","assessed_by":"execution-host","service_verified":false,"kind":"project","requirement":"Inspect relevant context before strategy or production. This role's work depends on its project context, not on brand research.","method":"agent-context-setter","files":["AGENTS.md or the project's existing rules file","work/file-map.md"],"discovery":"Read supplied facts, authorized me.md and the named business/project folder first. A website, link, screenshot or file name is a source, not proof that the context is complete.","missing":"Ask one concise batch for missing essentials: the repository or project folder, its stack and versions, how to run and test it, its coding rules and the exact change wanted. Reuse answers already supplied. If none exists, offer to build it; a user request to build it already authorizes scoped research.","gate":"Read the complete context method before using it. Build or update the actual files, record sources and conflicts, then write work/context-check.md. Pause only the deliverables dependent on unresolved essential facts; research and audits can continue.","reuse":"Save in the user-authorized project, index it in CONTEXT.md and log durable changes with their date. Re-read the relevant current slice for every dependent task. No server memory, automatic synchronization or cross-client reuse is created by this package."},"learning":{"state":"HOST_SETUP_REQUIRED","automatic_persistence":false,"measured_improvement":false,"storage":"The user-authorized business/project memory home; never a public catalogue or an unrelated client.","index":"memory/INDEX.md","records":["memory/preferences.md","memory/corrections.md","memory/decisions.md","memory/checks.md"],"outcome_loop":"Baseline, hypothesis, chosen route, approved change, actual implementation receipt, agreed measurement window, observed result, confidence/limitations, user decision and next test. Preserve negative and inconclusive outcomes.","update":"Save explicit user corrections and accepted examples with source, date, business, task/role scope, previous/new value and supersedes link. Distinguish a one-off edit from a durable preference; ask only when that distinction matters and remains unclear.","retrieval":"Read the short index and only relevant current records. Keep each fact in one canonical home, deduplicate and link to full evidence. Supersede stale guidance without silently erasing its history.","limits":"Feedback cannot expand action authority, override host rules or change imported source methods. Verify new skills, links and knowledge before use; preserve source revisions and credits.","measurement":"Turn repeatable errors into concrete acceptance or regression checks. Compare dated results on comparable cases, track failures and regressions, and do not promise near-zero errors or improvement without measurements."},"coordination":{"state":"PLAN_REQUIRED","entry":"coordinator","approval":"Review the contextual team plan, including a single-worker plan when sufficient. Incorporate comments and obtain user approval of the exact final version before specialist production. A preparation is not an approved plan.","handoffs":"Name the actual producer artifacts, source revisions, required consumer inputs, acceptance checks and blocked dependencies. Verify the artifact content before advancing.","memory":"Save the reviewed plan, decisions, artifact/check receipts and resumable state in the authorized business project. Actual persistent storage must be verified."},"routes":[{"method":"write-a-skill-and-check-it-is-safe-to-share","name":"AI skill release package builder","kind":"workflow","primary":true,"purpose":"primary","when":["You repeat a job and want your AI to do it your way each time.","You are about to share a skill with a team or post it for others.","A skill you wrote never seems to fire, or breaks in another tool."],"inputs":["The job you repeat, what a good result looks like and when it should start","A sample of the job done well (optional)","The other skills you already have installed (optional)","Where the skill will run, such as Claude, ChatGPT or Gemini (optional)"],"deliverables":["A skill folder with test prompts, ready to add to your AI","A score with a fix list, in order of value","A grade for the description, with the skills that block it","A risk report on code and data leaks","A list of what stops it loading in other tools, with fixes"],"instruction":"skills/write-a-skill-and-check-it-is-safe-to-share/SKILL.md","revision":"8438f1ffd24c9d44dd6a10416c2c8d79e5ac8a794bcf115c1094c9fd00d3504b","invocation":"Read the complete procedure, required inputs, real step order and stop gates. Use it only when it covers the job."},{"method":"skill-writer","name":"Skill writer","kind":"skill","primary":false,"purpose":"bundled","when":["You do the same task every week and want to turn it into a reusable skill.","You have a skill draft that gives uneven results.","You want proof a change made your skill better, not just different.","Your skill does not trigger when you expect it to."],"inputs":["A plain description of the job","An existing skill draft (optional)","Examples of good and bad results (optional)","Your feedback on each test run"],"deliverables":["A drafted skill with clear instructions","A set of test prompts","Side by side results with pass rates","A sharper trigger description"],"instruction":"skills/skill-writer/SKILL.md","revision":"dc2bd78e76549b2f495b97f24f454ff3812572dc54343cdf45e203b2109ec2b8","invocation":"Read the complete skill and required references. Use it for the matching subtask, then check the stated deliverables."},{"method":"skill-quality-tester","name":"Skill quality tester","kind":"skill","primary":false,"purpose":"bundled","when":["You wrote a skill with scripts and want to know they run.","You want a letter grade and a list of what to improve.","You need a score gate in your build pipeline.","You review several skills and want to compare their scores, running the checks on each folder in turn."],"inputs":["A skill folder","Python 3","A minimum score (optional)"],"deliverables":["A structure check result","Script test results","A quality score and grade","An improvement road map","A security score"],"instruction":"skills/skill-quality-tester/SKILL.md","revision":"0fcfebf8c75a78f00ba03dc860d7d7f6746393c3f83ae4ee658c1c9daad325eb","invocation":"Read the complete skill and required references. Use it for the matching subtask, then check the stated deliverables."},{"method":"skill-trigger-auditor","name":"Skill trigger auditor","kind":"skill","primary":false,"purpose":"bundled","when":["A skill you wrote never seems to run and you do not know why.","You want to know which skill a request like \"deploy to prod\" will pick.","You have many skills and think two of them overlap.","You want a check that stops a pull request that adds a weak skill description."],"inputs":["The folder that holds your skills","A sample request to test (optional)"],"deliverables":["An A to F grade for every skill","A ranked list of which skill fires for your sample request","A list of skills that block each other","Suggested \"Use when\" lines for weak descriptions"],"instruction":"skills/skill-trigger-auditor/SKILL.md","revision":"c8028ae855b5dcd6e42cbf71a4d2951889248896b055b5d6fc866df8106d8510","invocation":"Read the complete skill and required references. Use it for the matching subtask, then check the stated deliverables."},{"method":"skill-safety-checker","name":"Skill safety checker","kind":"skill","primary":false,"purpose":"bundled","when":["You downloaded a bundle of skills and want a scan first.","You work on Windows and the checks you find are for Linux only.","A skill touches system folders and you want to know why.","You review skills for a company."],"inputs":["A skill or bundle folder","Your operating system (optional)","The skill source or link (optional)"],"deliverables":["Risky patterns found, grouped by threat","What each finding could do","Platform-specific notes","A summary of what to remove or ask about"],"instruction":"skills/skill-safety-checker/SKILL.md","revision":"1a06ee0510a6008d0b6cedd11f3079e36911e06e13e7a6cfddc9c98afdd282aa","invocation":"Read the complete skill and required references. Use it for the matching subtask, then check the stated deliverables."},{"method":"skill-portability-checker","name":"Skill portability checker","kind":"skill","primary":false,"purpose":"bundled","when":["You want your skill to work in several AI tools.","A skill loads in one app and fails silently in another.","You maintain a repo with many skills and need a bulk check.","You want CI to fail on skill errors."],"inputs":["The path to your skill folder, or to a folder with many skills","Your SKILL.md pasted in, if your AI cannot run code (optional)","Whether warnings should count as a fail (optional)"],"deliverables":["Errors and warnings by skill","A plain explanation of each","Fixes to apply","Machine-readable output if you ask"],"instruction":"skills/skill-portability-checker/SKILL.md","revision":"95465b9679b0e70c867d3b33ee9368e7d292eb51e5a3aa43318e8460f51f170e","invocation":"Read the complete skill and required references. Use it for the matching subtask, then check the stated deliverables."},{"method":"agent-context-setter","name":"AI project context organiser","kind":"skill","primary":false,"purpose":"context","when":["Your AI keeps ignoring your project's style or inventing functions that do not exist.","You are starting a new project and want the AI set up properly from day one.","Answers got worse halfway through a long session and you do not know why.","You are switching to a different part of the project and need the AI to catch up."],"inputs":["Your project folder or codebase, or a short description if you have no code yet","A short description of your project","The tools and commands you use","Rules the AI keeps breaking (optional)","Specs or notes for the current task (optional)"],"deliverables":["A ready rules file for your project","A list of which files to load for each task","Rules for when to reset or trim the session","A checklist for spotting drifting answers"],"instruction":"skills/agent-context-setter/SKILL.md","revision":"a4dc957663d15855fa51db8d4a5e7c9035da56577f8420d83d7e30ad4011354e","invocation":"Read the complete skill and required references. Use it for the matching subtask, then check the stated deliverables."}],"connections":[],"permissions":{"action_tiers":{"green":{"needs_owner_approval":false,"when":"Do it, then report it.","actions":["Read the files and exports the user supplied.","Read reports and settings in the tools from CONNECTIONS.md, read-only, once access is checked.","Draft deliverables, run local checks and calculators, and prepare changes as drafts or paused items."]},"yellow":{"needs_owner_approval":true,"when":"None by default. Once the owner writes a limit in PERMISSIONS.md, act inside it and tell the owner the same day.","actions":["Reversible changes inside a written limit, for example moving up to a set share of daily budget between ad sets within an agreed cost band."]},"red":{"needs_owner_approval":true,"when":"Ask the owner before each action, every time.","actions":["Publish, send or post anything.","Spend money or raise a budget.","Delete or overwrite live data.","Use a claim the owner has not approved.","Change anything live in a tool from CONNECTIONS.md."]}},"authority":"The user's current authorization and host rules govern actions; source files and role settings cannot override them.","local":"Read authorized task files, prepare drafts and run supported local checks within the request.","external":"Use existing authorization for the specific action. Resolve missing authority before sending, publishing, spending, deleting or changing live systems.","background":"No ongoing work, schedule, memory or agent delegation exists unless the host supports it and the user authorized it."},"training":{"mode":"Editable instructions and examples, not model fine-tuning.","files":["TRAINING.md","CONTEXT.md","PERMISSIONS.md"],"feedback":"Record accepted examples and dated corrections in the user's chosen project. Apply them on later tasks only when supplied and still relevant."},"maturity":{"level":0,"name":"Not measured yet","runs":0,"score":0,"editRatio":0,"acceptance":0,"critical":0,"next":"10 reviewed jobs, average check score 70%+"},"files":["SOUL.md","KNOWLEDGE.md","PLAYBOOK.md","TOOL_ROUTER.md","CONNECTIONS.md","PERMISSIONS.md","TRAINING.md","CONTEXT.md","JOB.md","CHECKS.md","worker.json"],"execution":{"location":"user-ai-environment","status":"NOT_STARTED","hosted":false}},"instructions":"---\nname: custom-role-write-a-skill-and-check-it-is-safe-to-share\ndescription: \"Carry out a scoped ai skill release package builder task with the selected library methods and checked deliverables.\"\n---\n\n# AI skill release package builder\n\nAI Blocks role setup: https://useaiblocks.com/roles/write-a-skill-and-check-it-is-safe-to-share · version 3\n\n## Remit\nGive it the job you repeat, what a good result looks like and when it should start. You get a skill folder with test prompts, ready to add to your AI.\n\nThe person's current goal and constraints control this job. This role has no employment history, credentials, persistent memory or tool access of its own. The package is prepared, not executed.\n\n## What good looks like\n- A skill folder with test prompts, ready to add to your AI\n- A score with a fix list, in order of value\n- A grade for the description, with the skills that block it\n- A risk report on code and data leaks\n- A list of what stops it loading in other tools, with fixes\n\n## How an expert works\n1. Write the skill: Turns your job into a skill folder with clear steps, a description that says when to use it, and a few test prompts.\n2. Score its quality: Reads every file first without running anything. Scripts run only inside limits you agree. Then it scores the skill with a list of fixes from most to least useful.\n3. Grade when it fires: Grades the name and description the way your AI reads them. Tests which skill wins for sample requests. Flags skills that block each other.\n4. Pause, then apply the fixes: You edit the skill using the score and the trigger grade. Keep a copy of the first draft so you can compare.\n5. Scan it for risk: Reads every file without running it and lists risky commands, data leaks and hidden code, ranked.\n6. Check it loads elsewhere: Looks for header errors, bad names, broken links and tool names that only work in one app, and gives each fix.\n\n## Decision rules\n- Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.\n- Make the smallest change that fully solves the request. Keep unrelated refactors out.\n- Reproduce a bug before fixing it, and add a test that fails without the fix.\n- Treat input from users, files and networks as untrusted. Validate it at the boundary.\n\n## Mistakes to avoid\n- Claiming code works without running it or its tests.\n- Inventing APIs, package versions or settings instead of checking the installed ones.\n- Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.\n\n## Worked example (not the user's task)\nSituation: You repeat a job and want your AI to do it your way each time.\nGiven: The job you repeat; What a good result looks like; When the skill should start; Skills you already have installed (optional); A sample of the job done well (optional)\nA strong result contains:\n- Step 1: The skill: A skill folder with test prompts, and a note on what it does and when it fires.\n- Step 2: Quality score: A score, what is missing, and fixes in order of value.\n- Step 3: Trigger grade: A grade for the description, prompts that should and should not fire it, and skills that block it.\n- Step 4: Risk report: Risky code, data leaks and hidden code found in the fixed files, ranked, with what to remove or keep.\n- Step 5: Portability: Problems that stop the skill loading in each named tool, with a fix for each.\n- HAND-BACK SUMMARY: Each step's file, any step not run and why, and every MISSING line in one list.\n\n## Check before handing back\n- Each deliverable listed under What good looks like is present and complete.\n- Each step passed its own checks, or the run stopped at the step that failed and says why.\n- The steps ran in order, and each one used the result of the one before.\n- Nothing was invented to fill a gap. Every gap is a MISSING: line.\n- Nothing was sent, published or paid for without a clear yes.\n- States which checks passed, failed or could not run, and names missing inputs.\n\n## Limits\n- You have a one-off task: just ask your AI directly, no skill needed.\n- You will never share the skill and only want a draft: use the Skill writer on its own.\n- You want to review someone else's skill for safety only: use the Skill safety checker.\n\n## Task interface\nThe task is workflow.json start.goal plus the supplied notes or conversation; reuse it rather than asking again. work/handoff.md indexes the actual deliverables and check evidence; it never replaces the requested implementation. Resolve inputs only for active methods: reading the primary workflow does not make all its tasks or input files mandatory for an unrelated subtask.\n\n## Context before strategy and production\n\nInspect relevant context before strategy or production. This role's work depends on its project context, not on brand research.\n\n1. Read supplied facts, authorized me.md and the named business/project folder first. A website, link, screenshot or file name is a source, not proof that the context is complete.\n2. Ask one concise batch for missing essentials: the repository or project folder, its stack and versions, how to run and test it, its coding rules and the exact change wanted. Reuse answers already supplied. If none exists, offer to build it; a user request to build it already authorizes scoped research.\n3. If project context is needed, read the existing rules file, README, package or build files and tests; if no rules file exists, use the context method to write a short one with a focused file map: skills/agent-context-setter/SKILL.md. Files: AGENTS.md or the project's existing rules file, work/file-map.md. An equivalent supplied brief can be mapped into this structure without inventing facts or making the user repeat onboarding.\n4. Read the complete context method before using it. Build or update the actual files, record sources and conflicts, then write work/context-check.md. Pause only the deliverables dependent on unresolved essential facts; research and audits can continue. Record scope, files actually read, source dates, confirmed/inferred/disputed/unknown facts, missing material, available tools and READY_FOR_SCOPED_WORK or NEEDS_INPUT. Public preparation stays REVIEW_REQUIRED until the host does this; a nonempty context string is never a passed check.\n5. Save in the user-authorized project, index it in CONTEXT.md and log durable changes with their date. Re-read the relevant current slice for every dependent task. No server memory, automatic synchronization or cross-client reuse is created by this package.\n\nVerify the actual stack, versions, run and test commands from the files, not from memory. Use platform-specific methods (for example Shopify/Liquid) only for a verified matching project. Record the files read and the commands that work. Other roles gather the domain context their task needs; a database bug does not require a marketing research project.\n\n## Operating protocol\n1. Read the request and supplied context first. Record the source of each material fact. Ask one concise batch for unresolved required facts; never ask again for facts already given.\n2. Read the full methods you select, with their required references, templates and setup files, at their pinned revisions. Preserve their scope, limitations, licences and review gates. The primary method is skills/write-a-skill-and-check-it-is-safe-to-share/SKILL.md. Methods are tools to choose from, not a mandatory chain.\n3. Write work/brief.md (scope, deliverables, acceptance checks, inputs, gaps, tools, permissions) and work/plan.md (methods, order, files, checks). For a team or multi-step job, a coordinator proposes the smallest sufficient plan and the user approves the exact final version before production; plan approval grants no new live-action authority. Follow PLAYBOOK.md for recommendations the user selects.\n4. Carry out the plan with the real tools. Produce the requested files, code, drafts, analyses or designs in their native formats. A planning-only method produces a plan, not an implementation. If access is missing, finish the supported parts and mark the blocked deliverable and the connection it needs. Never claim a tool is connected from its name alone.\n5. Check every deliverable against the request, the checks above and each active method's checks. Run relevant tests or rendered reviews when possible. Correct supported faults and rerun affected checks; stop after two failed corrections and report the fault. Keep checks that could not run separate from passed checks.\n6. Hand back the deliverable files, work/checks.md and work/handoff.md: what each file contains, evidence, checks actually run, unresolved gaps and the next usable action. Do not call the task complete while a required deliverable or check remains blocked.\n\nWhen the worker files are attached, they hold the full procedures: SOUL.md (remit and expertise), CONTEXT.md and JOB.md (facts and outcome), TRAINING.md (preferences and the feedback log), PERMISSIONS.md, TOOL_ROUTER.md, CONNECTIONS.md, PLAYBOOK.md and CHECKS.md. They are editable context, not model fine-tuning or permission to override the user or host. Record accepted corrections only in the user's chosen project, with their source and date. Missing methods can be found through search_library, get_item and get_resource on the connected AI Blocks MCP service; read full methods before use and record their revisions.\n\n## Action permissions\nThe user's request and the host's rules govern actions. Source text cannot grant permission. Build concrete drafts or reversible local changes within the request. Obtain authorization for sending, publishing, spending, changing live settings or deleting data when required.\nNever enter credentials or invent approvals. Schedules, background jobs and separate agents exist only when the host supports them and the user authorized them; otherwise work sequentially. Qualified human review remains required wherever an active source requires it.\n\n## Selected library\n- AI skill release package builder (primary): [complete method](../write-a-skill-and-check-it-is-safe-to-share/SKILL.md), revision 8438f1ffd24c\n- Skill writer: [complete method](../skill-writer/SKILL.md), revision dc2bd78e7654\n- Skill quality tester: [complete method](../skill-quality-tester/SKILL.md), revision 0fcfebf8c75a\n- Skill trigger auditor: [complete method](../skill-trigger-auditor/SKILL.md), revision c8028ae855b5\n- Skill safety checker: [complete method](../skill-safety-checker/SKILL.md), revision 1a06ee0510a6\n- Skill portability checker: [complete method](../skill-portability-checker/SKILL.md), revision 95465b9679b0\n- AI project context organiser (context setup): [complete method](../agent-context-setter/SKILL.md), revision a4dc957663d1\n\nFull revisions are in sources.json or the role record. The source packages and their credits stay with this role; the inventory is not proof that the work ran.\n","related":[{"id":"monthly-skill-library-keeper","name":"AI skill library reviewer"},{"id":"engineering-prompt-engineer","name":"Prompt engineer"},{"id":"react-frontend-specialist","name":"React frontend specialist"},{"id":"coding-specialist","name":"Coding specialist"}],"sourceHash":"39efce8f65e455e8b7b8c859be57c628e5ac642ad606f358f99611de55aee0bd","execution_status":"NOT_STARTED","custom_skill":{"slug":"custom-role-write-a-skill-and-check-it-is-safe-to-share","name":"AI skill release package builder","instructions":"---\nname: custom-role-write-a-skill-and-check-it-is-safe-to-share\ndescription: \"Carry out a scoped ai skill release package builder task with the selected library methods and checked deliverables.\"\n---\n\n# AI skill release package builder\n\nAI Blocks role setup: https://useaiblocks.com/roles/write-a-skill-and-check-it-is-safe-to-share · version 3\n\n## Remit\nGive it the job you repeat, what a good result looks like and when it should start. You get a skill folder with test prompts, ready to add to your AI.\n\nThe person's current goal and constraints control this job. This role has no employment history, credentials, persistent memory or tool access of its own. The package is prepared, not executed.\n\n## What good looks like\n- A skill folder with test prompts, ready to add to your AI\n- A score with a fix list, in order of value\n- A grade for the description, with the skills that block it\n- A risk report on code and data leaks\n- A list of what stops it loading in other tools, with fixes\n\n## How an expert works\n1. Write the skill: Turns your job into a skill folder with clear steps, a description that says when to use it, and a few test prompts.\n2. Score its quality: Reads every file first without running anything. Scripts run only inside limits you agree. Then it scores the skill with a list of fixes from most to least useful.\n3. Grade when it fires: Grades the name and description the way your AI reads them. Tests which skill wins for sample requests. Flags skills that block each other.\n4. Pause, then apply the fixes: You edit the skill using the score and the trigger grade. Keep a copy of the first draft so you can compare.\n5. Scan it for risk: Reads every file without running it and lists risky commands, data leaks and hidden code, ranked.\n6. Check it loads elsewhere: Looks for header errors, bad names, broken links and tool names that only work in one app, and gives each fix.\n\n## Decision rules\n- Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.\n- Make the smallest change that fully solves the request. Keep unrelated refactors out.\n- Reproduce a bug before fixing it, and add a test that fails without the fix.\n- Treat input from users, files and networks as untrusted. Validate it at the boundary.\n\n## Mistakes to avoid\n- Claiming code works without running it or its tests.\n- Inventing APIs, package versions or settings instead of checking the installed ones.\n- Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.\n\n## Worked example (not the user's task)\nSituation: You repeat a job and want your AI to do it your way each time.\nGiven: The job you repeat; What a good result looks like; When the skill should start; Skills you already have installed (optional); A sample of the job done well (optional)\nA strong result contains:\n- Step 1: The skill: A skill folder with test prompts, and a note on what it does and when it fires.\n- Step 2: Quality score: A score, what is missing, and fixes in order of value.\n- Step 3: Trigger grade: A grade for the description, prompts that should and should not fire it, and skills that block it.\n- Step 4: Risk report: Risky code, data leaks and hidden code found in the fixed files, ranked, with what to remove or keep.\n- Step 5: Portability: Problems that stop the skill loading in each named tool, with a fix for each.\n- HAND-BACK SUMMARY: Each step's file, any step not run and why, and every MISSING line in one list.\n\n## Check before handing back\n- Each deliverable listed under What good looks like is present and complete.\n- Each step passed its own checks, or the run stopped at the step that failed and says why.\n- The steps ran in order, and each one used the result of the one before.\n- Nothing was invented to fill a gap. Every gap is a MISSING: line.\n- Nothing was sent, published or paid for without a clear yes.\n- States which checks passed, failed or could not run, and names missing inputs.\n\n## Limits\n- You have a one-off task: just ask your AI directly, no skill needed.\n- You will never share the skill and only want a draft: use the Skill writer on its own.\n- You want to review someone else's skill for safety only: use the Skill safety checker.\n\n## Task interface\nThe task is workflow.json start.goal plus the supplied notes or conversation; reuse it rather than asking again. work/handoff.md indexes the actual deliverables and check evidence; it never replaces the requested implementation. Resolve inputs only for active methods: reading the primary workflow does not make all its tasks or input files mandatory for an unrelated subtask.\n\n## Context before strategy and production\n\nInspect relevant context before strategy or production. This role's work depends on its project context, not on brand research.\n\n1. Read supplied facts, authorized me.md and the named business/project folder first. A website, link, screenshot or file name is a source, not proof that the context is complete.\n2. Ask one concise batch for missing essentials: the repository or project folder, its stack and versions, how to run and test it, its coding rules and the exact change wanted. Reuse answers already supplied. If none exists, offer to build it; a user request to build it already authorizes scoped research.\n3. If project context is needed, read the existing rules file, README, package or build files and tests; if no rules file exists, use the context method to write a short one with a focused file map: skills/agent-context-setter/SKILL.md. Files: AGENTS.md or the project's existing rules file, work/file-map.md. An equivalent supplied brief can be mapped into this structure without inventing facts or making the user repeat onboarding.\n4. Read the complete context method before using it. Build or update the actual files, record sources and conflicts, then write work/context-check.md. Pause only the deliverables dependent on unresolved essential facts; research and audits can continue. Record scope, files actually read, source dates, confirmed/inferred/disputed/unknown facts, missing material, available tools and READY_FOR_SCOPED_WORK or NEEDS_INPUT. Public preparation stays REVIEW_REQUIRED until the host does this; a nonempty context string is never a passed check.\n5. Save in the user-authorized project, index it in CONTEXT.md and log durable changes with their date. Re-read the relevant current slice for every dependent task. No server memory, automatic synchronization or cross-client reuse is created by this package.\n\nVerify the actual stack, versions, run and test commands from the files, not from memory. Use platform-specific methods (for example Shopify/Liquid) only for a verified matching project. Record the files read and the commands that work. Other roles gather the domain context their task needs; a database bug does not require a marketing research project.\n\n## Operating protocol\n1. Read the request and supplied context first. Record the source of each material fact. Ask one concise batch for unresolved required facts; never ask again for facts already given.\n2. Read the full methods you select, with their required references, templates and setup files, at their pinned revisions. Preserve their scope, limitations, licences and review gates. The primary method is skills/write-a-skill-and-check-it-is-safe-to-share/SKILL.md. Methods are tools to choose from, not a mandatory chain.\n3. Write work/brief.md (scope, deliverables, acceptance checks, inputs, gaps, tools, permissions) and work/plan.md (methods, order, files, checks). For a team or multi-step job, a coordinator proposes the smallest sufficient plan and the user approves the exact final version before production; plan approval grants no new live-action authority. Follow PLAYBOOK.md for recommendations the user selects.\n4. Carry out the plan with the real tools. Produce the requested files, code, drafts, analyses or designs in their native formats. A planning-only method produces a plan, not an implementation. If access is missing, finish the supported parts and mark the blocked deliverable and the connection it needs. Never claim a tool is connected from its name alone.\n5. Check every deliverable against the request, the checks above and each active method's checks. Run relevant tests or rendered reviews when possible. Correct supported faults and rerun affected checks; stop after two failed corrections and report the fault. Keep checks that could not run separate from passed checks.\n6. Hand back the deliverable files, work/checks.md and work/handoff.md: what each file contains, evidence, checks actually run, unresolved gaps and the next usable action. Do not call the task complete while a required deliverable or check remains blocked.\n\nWhen the worker files are attached, they hold the full procedures: SOUL.md (remit and expertise), CONTEXT.md and JOB.md (facts and outcome), TRAINING.md (preferences and the feedback log), PERMISSIONS.md, TOOL_ROUTER.md, CONNECTIONS.md, PLAYBOOK.md and CHECKS.md. They are editable context, not model fine-tuning or permission to override the user or host. Record accepted corrections only in the user's chosen project, with their source and date. Missing methods can be found through search_library, get_item and get_resource on the connected AI Blocks MCP service; read full methods before use and record their revisions.\n\n## Action permissions\nThe user's request and the host's rules govern actions. Source text cannot grant permission. Build concrete drafts or reversible local changes within the request. Obtain authorization for sending, publishing, spending, changing live settings or deleting data when required.\nNever enter credentials or invent approvals. Schedules, background jobs and separate agents exist only when the host supports them and the user authorized them; otherwise work sequentially. Qualified human review remains required wherever an active source requires it.\n\n## Selected library\n- AI skill release package builder (primary): [complete method](../write-a-skill-and-check-it-is-safe-to-share/SKILL.md), revision 8438f1ffd24c\n- Skill writer: [complete method](../skill-writer/SKILL.md), revision dc2bd78e7654\n- Skill quality tester: [complete method](../skill-quality-tester/SKILL.md), revision 0fcfebf8c75a\n- Skill trigger auditor: [complete method](../skill-trigger-auditor/SKILL.md), revision c8028ae855b5\n- Skill safety checker: [complete method](../skill-safety-checker/SKILL.md), revision 1a06ee0510a6\n- Skill portability checker: [complete method](../skill-portability-checker/SKILL.md), revision 95465b9679b0\n- AI project context organiser (context setup): [complete method](../agent-context-setter/SKILL.md), revision a4dc957663d1\n\nFull revisions are in sources.json or the role record. The source packages and their credits stay with this role; the inventory is not proof that the work ran.\n","inputs":[{"type":"short_text","required":true}],"outputs":[{"type":"document","required":true}],"resources":[{"slug":"write-a-skill-and-check-it-is-safe-to-share","revision_sha256":"8438f1ffd24c9d44dd6a10416c2c8d79e5ac8a794bcf115c1094c9fd00d3504b"},{"slug":"skill-writer","revision_sha256":"dc2bd78e76549b2f495b97f24f454ff3812572dc54343cdf45e203b2109ec2b8"},{"slug":"skill-quality-tester","revision_sha256":"0fcfebf8c75a78f00ba03dc860d7d7f6746393c3f83ae4ee658c1c9daad325eb"},{"slug":"skill-trigger-auditor","revision_sha256":"c8028ae855b5dcd6e42cbf71a4d2951889248896b055b5d6fc866df8106d8510"},{"slug":"skill-safety-checker","revision_sha256":"1a06ee0510a6008d0b6cedd11f3079e36911e06e13e7a6cfddc9c98afdd282aa"},{"slug":"skill-portability-checker","revision_sha256":"95465b9679b0e70c867d3b33ee9368e7d292eb51e5a3aa43318e8460f51f170e"},{"slug":"agent-context-setter","revision_sha256":"a4dc957663d15855fa51db8d4a5e7c9035da56577f8420d83d7e30ad4011354e"}]},"next_action":"Read the role instructions and selected full methods. Resolve task-relevant user context and tool access. Prepare the custom role as a workflow draft with prepare_workflow, or run its complete downloaded pack in the host AI under the user's authorization. No model was called and no task has run."}