Hire an AI skill library reviewer

Everything it can hand back

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

• Which skills are new, changed or flagged since last month
• Skills that never fire, or clash with each other
• Any skill marked do not run, with what was found
• A ranked fix list to approve
• Skills worth adding, from your projects and history

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

• Running a skill's own scripts to test it before the safety check has passed.
• Merging two skills that look alike without reading both. They may do different jobs.
• Adding a new skill for a task that happens once.
• Scoring a skill on length. Short skills that fire at the right time score well.
• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.

What a good result looks like

An example, not your task: You have more than a handful of skills and are not sure all of them still work.

• This month. One line with the count of skills, and how many are new, changed, flagged and unsafe.
• Do not run. Any skill that failed the safety check, with what was found. Empty if none.
• Fixes to approve. Up to 15 ranked fixes, each with the skill, the problem, the step that found it and the fix.
• Clashes. Pairs of skills that block or copy each other, which one to keep and why.
• Skills worth adding. New skill ideas from your projects and history, each with the job it would do.
• Last month's fixes. Each fix agreed last time, marked fixed or still open.

How the work is checked

• Every skill appears in the inventory, marked new, changed or unchanged.
• No skill flagged unsafe was tested, run or recommended.
• Every finding names the skill and the step that found it.
• Skills not tested this month are listed, with when they will be.
• 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

• Take stock. Lists every skill and marks it new, changed or unchanged since last month.
• Check the triggers. Finds skills too vague to fire, too broad, or clashing with another.
• Check structure. Validates each new and changed skill for structure, wording and naming problems.
• Check safety before any test. Checks outside skills and new scripts. A skill that fails is marked do not run and is not tested or run.
• Test quality and check portability. Tests the skills that passed, meaning new, changed and flagged ones plus a rotating sample, and checks they load in each AI tool you use.
• Look for gaps. If nothing is unsafe, looks in your project and history for skills worth adding.
• Rank and hand back. Puts every finding in one list, unsafe first, and stops for your yes.

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 monthly-skill-library-keeper 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/monthly-skill-library-keeper/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 folder of skills, each with its SKILL.md
• Which ones came from outside (optional)
• A project folder, to find skills the work needs (optional)
• Session or screen history, to find tasks you repeat (optional)
• Last month's folder, after the first run

Helpful context (optional)

• The prompts you use most often, to compare with the skills you have
• A note of which skills fired wrongly last month

Tools and access

• Claude Code: It can read the skills folder, keep the inventory. You start each monthly run. It does not run on a timer.

Functions and deliverables

• AI skill library reviewer: Review skill files for unclear triggers, structure gaps and risks. Get a ranked fix list and ideas for useful additions.
  • Which skills are new, changed or flagged since last month
  • Skills that never fire, or clash with each other
  • Any skill marked do not run, with what was found
  • A ranked fix list to approve
  • Skills worth adding, from your projects and history
• 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 file validator: Share a SKILL.md. Get structure, wording and naming problems to fix before you share it.
  • A list of problems by category
  • Points where the file does well
  • A quality score
  • Fixes for the issues found
  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 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 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.
• Project skill finder: Find the skills your project needs. Give it your project folder and get a ranked list of skills to add or update, based on how you really work.
  • Ranked list of skills to add or update
  • Evidence for each pick
  • Notes on existing skills that nearly fit
  Source: sickn33.
• Repeated work skill finder: Share your screen history. Get tasks you repeat and draft skills to automate them.
  • List of repeated tasks found
  • Match to existing skills
  • Draft skills for new tasks
  • Notes on which are worth automating
  Source: K-Dense.
• 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 have more than a handful of skills and are not sure all of them still work.
• You add skills from other people and want them checked before they run.
• Your AI picks the wrong skill, or no skill, for jobs you do every week.

Limits to check before starting

• You want a one-off check of one new skill: use the Skill file validator, which covers that alone.
• You have no skills yet: write your first skill by hand, then come back once you have a folder.
• You want a failed skill fixed: use the Prompt and skill improvement tester, then run this agent again next month.

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.

• Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to run this month's check.
• Point it at the folder where your skills live. Say which came from outside.
• Say yes to quality tests only for your own skills that passed the safety check. Tests run in a copy of the folder with the network off and made-up data. If your tool cannot do that, the test is skipped and marked blocked.
• Read the hand-back. Anything marked do not run goes first.
• Say yes to the fixes you want, or make them yourself. For a skill that failed its test, use the Prompt and skill tuner.
• Run it next month. It checks whether the fixes worked.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/monthly-skill-library-keeper 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.