agentleFS
Sign inStart free
ntaffziintaffzii/Skill-Agents/skills/misc/skill-management/SKILL.md

skill-management

Skill4 starsChanged 2 months agoMITView on GitHub

Manage a skill repository: create, classify, improve, deprecate, or reorganize agent skills with clean buckets, clear SKILL.md metadata, progressive disclosure, and installable structure. Use when the user asks to make skills, organize skills, compare skill quality, or maintain a skills repo.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 9 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to keep a skills repository clean and usable.

    line 8
  2. Distinctive:

    Create a workflow when a job needs multiple skills in a repeatable order.

    line 30
  3. Distinctive:

    Prefer workflow steps and rules.

    line 63
  4. Distinctive:

    Add output format only when consistency matters.

    line 64
  5. Distinctive:

    Add references only when needed

    line 66
  6. Very specific:

    Put long syntax tables, examples, or domain docs in references/.

    line 67
  7. Very specific:

    Keep references one level deep from SKILL.md.

    line 68
  8. Distinctive:

    Keep stable skills in domain buckets, not status buckets.

    line 85
  9. Distinctive:

    Do not promote draft skills until trigger behavior and workflow are clear.

    line 86
  10. Distinctive:

    Do not mix personal setup details into public skills.

    line 87
  11. Distinctive:

    Update workflow and tool registries when skill relationships change.

    line 88

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill Management

Use this skill to keep a skills repository clean and usable.

Repository Model

  • skills/ contains individual capabilities.
  • workflows/ contains ordered playbooks that combine skills.
  • mcp-tools/ contains executable actions exposed through MCP.
  • data/workflows.json indexes workflows for browsing and automation.
  • data/tools.json indexes tool groups and their skill/workflow relationships.

Bucket Model

  • engineering/ - daily code work
  • productivity/ - non-code workflows
  • obsidian/ - Obsidian-specific work
  • misc/ - useful but infrequent
  • personal/ - tied to one user's setup
  • in-progress/ - drafts
  • deprecated/ - retired skills

Workflow Creation

Create a workflow when a job needs multiple skills in a repeatable order.

Each workflow should include:

  • Goal
  • When to use
  • Skills
  • Steps
  • Verification
  • Output

Also add or update the matching entry in data/workflows.json with:

  • id
  • title
  • description
  • path
  • recommendedSkills
  • steps

Skill Creation Workflow

  1. Define the job
    • What task does this skill make repeatable?
    • What trigger should load it?
    • What should the agent do differently after loading it?
  2. Write metadata
    • name must be lowercase and hyphenated.
    • description must include task, trigger, and use cases.
  3. Write the body
    • Keep it procedural.
    • Prefer workflow steps and rules.
    • Add output format only when consistency matters.
  4. Add references only when needed
    • Put long syntax tables, examples, or domain docs in references/.
    • Keep references one level deep from SKILL.md.
  5. Classify status
    • Shippable skills go into a domain bucket.
    • Drafts go into in-progress/.
    • Old skills go into deprecated/ with a short reason in the file.

Bucket Status Skills

The status buckets also contain their own operating skills:

  • in-progress - prototype and promote draft skills.
  • personal - keep user-specific instructions private and scoped.
  • deprecated - retire stale skills with replacement guidance.

Rules

  • Keep stable skills in domain buckets, not status buckets.
  • Do not promote draft skills until trigger behavior and workflow are clear.
  • Do not mix personal setup details into public skills.
  • Update workflow and tool registries when skill relationships change.

Quality Checklist

  • The skill has exactly one main job.
  • The description makes triggering obvious.
  • The workflow has a verification step.
  • The instructions are not generic advice.
  • The skill is small enough to read quickly.
  • Related files are discoverable from SKILL.md.

Output Format

End with:

  • Skills created or changed
  • Bucket classification
  • Workflow or registry updates
  • Validation result
  • Remaining cleanup

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free