agentleFS
Sign inStart free
rade-nugrohorade-nugroho/Agentic-Enteprises-Skill/ai-skill-manager/SKILL.md

ai-skill-manager

Skill9 starsChanged 6 months agoMITView on GitHub

Guides management of an enterprise Agent Skills portfolio—inventory and catalog hygiene, naming and structure standards, overlap and routing deduplication, cross-linking between skills, validation and packaging at scale, lifecycle (split, merge, deprecate), and quality/security review before distribution. Use when curating a skills repo, auditing skill quality, fixing trigger overlap, maintaining a skill catalog, batch-validating or packaging skills, or governing who may publish skills—not for authoring a single new skill from scratch (follow skill-creator), implementing agents or RAG (ai-engineer), production LLM ops (ai-lead-ops), or writing prompts inside one skill (prompt-engineer).

  • Pipes a download into a shell

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Add or fix When NOT to Use and Related skills cross-links

    line 20
  2. Very specific:

    Run batch validation or package .skill bundles for distribution

    line 21
  3. Distinctive:

    Before merge or publish:

    line 66
  4. Distinctive:

    No README/CHANGELOG inside skill folder

    line 71
  5. Distinctive:

    When two skills trigger on the same user phrase:

    line 78
  6. Distinctive:

    Add reciprocal Related skills rows

    line 82
  7. Distinctive:

    If overlap >30% of workflows, plan split or merge

    line 83
  8. Distinctive:

    No secrets, API keys, or customer data in skills

    line 119

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “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

AI Skill Manager

When to Use

  • Inventory skills in a repo or org catalog; find gaps and duplicates
  • Audit description frontmatter for clear triggers and routing
  • Add or fix When NOT to Use and Related skills cross-links
  • Run batch validation or package .skill bundles for distribution
  • Split an overloaded skill or merge overlapping ones
  • Deprecate or rename a skill without breaking consumers
  • Define governance: review checklist, owners, publish cadence
  • Triage security concerns in skill content (secrets, dangerous scripts)

When NOT to Use

  • Step-by-step creation of one new skill → use skill-creator (init_skill.py, package_skill.py)
  • Design RAG, agents, eval harnesses → ai-engineer
  • Model/prompt release ops and cost rituals → ai-lead-ops
  • AI regulatory policy registers → ai-risk-governance
  • Rewrite prompts inside a domain skill → prompt-engineer

Related skills

NeedSkill
Build and ship AI featuresai-engineer
Prompt and tool-schema craftprompt-engineer
AI risk tiering and policiesai-risk-governance
AI production ops cadenceai-lead-ops
Token cost programsai-token-improvement-plan-engineer
Comms for rolling out new capabilitiescommunication-lead

Core Workflows

1. Portfolio inventory

For each skill directory with SKILL.md, record:

FieldSource
nameYAML frontmatter
One-line purposeFirst sentence of description
Primary triggersdescription (not body)
References countreferences/*.md
Has scripts/assetsoptional dirs

Flag: same trigger keywords in multiple description fields.

See references/catalog_inventory.md.

2. Quality gate (per skill)

Before merge or publish:

  1. name matches folder name (hyphen-case, ≤64 chars)
  2. description includes what + when to use + when NOT (peer skill names)
  3. Body ≤ ~500 lines; deep detail in references/
  4. No README/CHANGELOG inside skill folder
  5. Run validator (below)

See references/quality_standards.md.

3. Routing and overlap

When two skills trigger on the same user phrase:

  1. Pick primary owner of the workflow
  2. Move triggers into primary description; add explicit negation in the other
  3. Add reciprocal Related skills rows
  4. If overlap >30% of workflows, plan split or merge

See references/routing_and_overlap.md.

4. Lifecycle

ActionWhen
CreateNew domain with ≥3 repeatable workflows → skill-creator
SplitSKILL.md or references too large; distinct audiences
MergeTwo skills always loaded together; duplicate triggers
DeprecateSuperseded; keep folder 1 release with redirect text in description

See references/skill_lifecycle.md.

5. Validate and package

Single skill:

python3 ~/.claude/skills/skill-creator/scripts/quick_validate.py <path/to/skill-dir>
python3 ~/.claude/skills/skill-creator/scripts/package_skill.py <path/to/skill-dir> ./dist

Entire repo (this skill bundle):

bash ai-skill-manager/scripts/validate_all_skills.sh /path/to/Agentic-Enteprises-Skill

See references/validation_packaging.md.

6. Security and supply chain

Review before org-wide install:

  • No secrets, API keys, or customer data in skills
  • Scripts: least privilege; no curl | bash patterns
  • description must not instruct bypassing safety or compliance
  • Third-party skills: same checklist + license note

See references/portfolio_governance.md.

Output standards

  • Inventory as table: name, purpose, triggers, overlap risk, last reviewed
  • Change proposals: what moves, which skills get updated cross-links
  • Deprecation notice: replacement skill name and migration sentence for description

When to load references

  • Inventory and catalog → references/catalog_inventory.md
  • Review checklist → references/quality_standards.md
  • Dedup and routing → references/routing_and_overlap.md
  • Split/merge/deprecate → references/skill_lifecycle.md
  • validate/package commands → references/validation_packaging.md
  • RACI and publish policy → references/portfolio_governance.md

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