Hire an AI skill release package builder

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• 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

How it does the job well

• 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.

Mistakes it avoids

• 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.

What a good result looks like

An example, not your task: You repeat a job and want your AI to do it your way each time.

• Step 1: The skill. A skill folder with test prompts, and a note on what it does and when it fires.
• Step 2: Quality score. A score, what is missing, and fixes in order of value.
• Step 3: Trigger grade. A grade for the description, prompts that should and should not fire it, and skills that block it.
• Step 4: Risk report. Risky code, data leaks and hidden code found in the fixed files, ranked, with what to remove or keep.
• Step 5: Portability. Problems that stop the skill loading in each named tool, with a fix for each.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• 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.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• 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.
• 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.
• 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.
• 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.
• Scan it for risk. Reads every file without running it and lists risky commands, data leaks and hidden code, ranked.
• 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.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id write-a-skill-and-check-it-is-safe-to-share only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/write-a-skill-and-check-it-is-safe-to-share/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• 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)

Functions and deliverables

• AI skill release package builder: Share a repeated job and target AI tools. Get skill files, trigger feedback, quality checks, security findings and a scoped portability review.
  • 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
• Skill writer: Describe a job. Get draft skill instructions, test prompts and a trigger description to review.
  • A drafted skill with clear instructions
  • A set of test prompts
  • Side by side results with pass rates
  • A sharper trigger description
  Source: Anthropic.
• Skill quality tester: Give it a skill folder. Get structure and script checks, a quality score and a ranked fix list.
  • A structure check result
  • Script test results
  • A quality score and grade
  • An improvement road map
  • A security score
  Source: Alireza Rezvani.
• Skill trigger auditor: Share your skills. Get a grade for each on when it fires, and which skills block each other.
  • 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
  Source: sickn33.
• Skill safety checker: Share a skill or bundle before you add it. Get risky code, data leaks and hidden payloads.
  • Risky patterns found, grouped by threat
  • What each finding could do
  • Platform-specific notes
  • A summary of what to remove or ask about
  Source: sickn33.
• Skill portability checker: Share your skill folder. Get mistakes that stop it loading in other AI tools, with fixes.
  • Errors and warnings by skill
  • A plain explanation of each
  • Fixes to apply
  • Machine-readable output if you ask
  Source: Pro Skill Packs.
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • 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
  Source: Addy Osmani.

Tasks you can use it for

• 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 to check before starting

• 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.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• 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.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/write-a-skill-and-check-it-is-safe-to-share for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.