Agent skill

Skill Inventory Stocktake

by zereight in zereight/gitlab-mcp

Audits a project's skill directories for broken frontmatter, missing template sync and quality gaps, then produces a health report of what needs fixing.

MITAuto-check passedAgent Workflows

Install Skill Inventory Stocktake

skills CLI
$ npx skills add zereight/gitlab-mcp --skill skill-stocktake -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zereight/gitlab-mcp skill-stocktake --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zereight/gitlab-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/skill-stocktake .claude/skills/skill-stocktake && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
skill-stocktake
GitHub stars
2k
Used in
1 other repo
Token cost
~1k tokens
SKILL.md length
192 words
Files
1
Skills in repo
24
Repo updated
First seen
Licence
MIT

At a glance

Audits a project's skill directories for broken frontmatter, missing template sync and quality gaps, then produces a health report of what needs fixing.

  • Works in 5 steps: Inventory → Frontmatter Validation (v1.0.5+) → Template Sync Check → …
  • Checking whether a new skill would duplicate an existing one
  • SKILL.md covers When to Use, Audit Protocol, Output Format and See Also
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill walks through five steps over the .github/skills and a templates folder: listing every skill directory, validating that each SKILL.md's frontmatter is current, for example that a removed hint field was renamed to argument-hint and that allowed-tools was dropped, diffing the two directories to catch skills missing from one side, checking each skill for required sections such as When to Use and Output Format plus a minimum length so empty stubs are caught, and comparing the skill catalog named in the project's copilot instructions against what actually exists on disk.

It is meant to run before adding a new skill to avoid duplicating one that already exists, after a large batch of changes to confirm templates stayed in sync, and periodically to prune stale or incomplete skills. The result is a dated stocktake report, and the skill points to sibling tools for orchestration, task verification, status and saving quality insights to memory.

When your agent uses it

  • Checking whether a new skill would duplicate an existing one
  • Verifying skill frontmatter after a tooling version bump
  • Finding skills that are stale, incomplete or out of sync with templates

Example prompts

  • “Run a stocktake on the skills folder before I add a new deployment skill.”
  • “Check whether any skill still uses the old hint frontmatter field.”
  • “Find skills mentioned in the copilot instructions that are missing from disk.”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Inventory
  2. Frontmatter Validation (v1.0.5+)
  3. Template Sync Check
  4. Quality Checks
  5. Coverage Analysis

What it can do on your machine

Read from SKILL.md and the folder at commit 035e9d1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and yaml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Skill Inventory Stocktake loads about 1k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 192 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zereight/gitlab-mcp at commit 035e9d1, republished under its MIT licence (© zereight). 192 words, ~1,008 tokens.

Download SKILL.mdSave it as .claude/skills/skill-stocktake/SKILL.md (or your agent's skills folder).
name
skill-stocktake
description
Audit the skill inventory for quality, coverage, and staleness. Detect overlapping, incomplete, or outdated skills and produce a health report. Activate when: skill audit, stocktake, skill inventory, check skills, which skills exist, audit skills, skill quality, skill coverage.
argument-hint
[optional: focus area — coverage | quality | staleness | all]

Skill Stocktake

Audit the .github/skills/ and vscode-omg/resources/templates/skills/ directories to produce a quality and coverage report.

When to Use

  • Before adding new skills (to avoid duplication)
  • After a large change batch (to verify templates are in sync)
  • Periodically to prune stale or incomplete skills

Audit Protocol

Step 1: Inventory
bash
# List all skill directories
ls -1d .github/skills/*/

# Count total
ls -1d .github/skills/*/ | wc -l

# Check each has a SKILL.md
for dir in .github/skills/*/; do
  [ -f "${dir}SKILL.md" ] || echo "MISSING SKILL.md: $dir"
done
Step 2: Frontmatter Validation (v1.0.5+)

Each SKILL.md MUST have valid frontmatter:

yaml
---
name: skill-name           # required, kebab-case, matches directory name
description: >             # required, multi-line description with trigger keywords
  ...
argument-hint: "..."       # optional, describes argument
---

v1.0.5 breaking changes to check:

  • ❌ hint: field → ✅ argument-hint:
  • ❌ allowed-tools: field → ✅ remove (not supported)
  • Skill name autopilot → must be omg-autopilot (naming collision)

Validate with:

bash
# Find skills using old 'hint:' field
grep -rn "^hint:" .github/skills/

# Find skills using unsupported 'allowed-tools:'
grep -rn "^allowed-tools:" .github/skills/

# Check for old 'autopilot' directory
ls .github/skills/ | grep "^autopilot$"
Step 3: Template Sync Check
bash
# Skills in .github but not in templates
diff <(ls .github/skills/) <(ls vscode-omg/resources/templates/skills/)

# Skills in templates but not in .github (orphan templates)
diff <(ls vscode-omg/resources/templates/skills/) <(ls .github/skills/)
Step 4: Quality Checks

For each skill, check:

  • name: matches directory name exactly
  • description: includes trigger keywords ("Activate when: X, Y, Z")
  • Has a clear "When to Use" or "Steps" section
  • Has an "Output Format" or "See Also" section
  • No broken cross-references to renamed skills (/autopilot → /omg-autopilot)
  • File is not empty stub (< 20 lines = likely incomplete)
Step 5: Coverage Analysis

Check against the skill catalog in copilot-instructions.md:

bash
# Extract skill names from instructions
grep -o '/[a-z-]*' .github/copilot-instructions.md | sort | uniq

# Compare to actual skill directories
ls -1d .github/skills/*/ | xargs -I{} basename {}

Identify gaps: skills mentioned in instructions but missing from disk, or vice versa.


Output Format

## Skill Stocktake Report

**Date:** [timestamp]
**Total Skills:** X

### Inventory
| Skill | Has SKILL.md | Lines | Frontmatter OK | In Instructions |
|-------|-------------|-------|----------------|-----------------|
| omg-autopilot | ✅ | 120 | ✅ | ✅ |
| [skill] | ❌ missing | — | — | ✅ |

### Issues Found
| Type | Skill | Issue | Severity |
|------|-------|-------|----------|
| Frontmatter | old-skill | Uses `hint:` not `argument-hint:` | MEDIUM |
| Sync | new-skill | In .github but missing from templates | LOW |
| Coverage | planning | Mentioned in instructions but no directory | HIGH |
| Stale | autopilot | Old name — should be omg-autopilot | HIGH |

### Summary
- Skills passing all checks: X/Y
- Issues requiring action: Z
  - HIGH: A
  - MEDIUM: B
  - LOW: C

### Recommended Actions
1. [Action with file path]
2. [Action with file path]

See Also

  • @omg-coordinator — orchestrates multi-skill workflows
  • /verify — verifies specific task completion
  • /status — shows current active workflow state
  • /remember — stores quality insights to memory

© zereight, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .github/skills/skill-stocktake of zereight/gitlab-mcp.

Open the folder on GitHubat commit 035e9d1

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in zereight/gitlab-mcp, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Skill Inventory Stocktake next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Skill Inventory Stocktake compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Inventory Stocktake this skillzereight/gitlab-mcp2k1 repos~1kAutomated safety check: PassMIT
Darwin Skill Optimizeralchaincyf/darwin-skill6.2k1 repos~4.7kAutomated safety check: PassMIT
Skill Creatorzhayujie/CowAgent47k—~4.7kAutomated safety check: NotesMIT
Open-Science Skill Creatoraipoch/open-science5.5k—~1.7kAutomated safety check: PassApache-2.0
Skill Quality ReviewerGalaxy-Dawn/claude-scholar5.7k1 repos~3kAutomated safety check: PassMIT
Prismer Skill CreatorPrismer-AI/PrismerCloud1.6k—~2.6kAutomated safety check: NotesMIT

Similar skills

  • Darwin Skill Optimizer

    alchaincyf/darwin-skill

    Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.

    6.2k GitHub starsUsed in 1 repo~4.7k tokens
    Agent WorkflowsAuto-check passed
  • Skill Creator

    zhayujie/CowAgent

    Guides creating, installing and updating agent skills in a workspace: SKILL.md frontmatter, bundled scripts and references, with scripts to scaffold, validate and package.

    47k GitHub stars~4.7k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Open-Science Skill Creator

    aipoch/open-science

    Creates, revises, evaluates and publishes skills in the Open-Science app through its native host.skills composer, with optional test prompts and benchmarks.

    5.5k GitHub stars~1.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Skill Quality Reviewer

    Galaxy-Dawn/claude-scholar

    Scores a skill across description, content organization, writing style and structure, then produces letter grades and a prioritized improvement plan.

    5.7k GitHub starsUsed in 1 repo~3k tokens
    Agent WorkflowsAuto-check passed
  • Prismer Skill Creator

    Prismer-AI/PrismerCloud

    Walks an agent through creating, importing, editing, validating, testing and publishing Prismer Skills with a fixed workflow and bundled scripts.

    1.6k GitHub stars~2.6k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check: notes
  • Skill Factory

    sangrokjung/claude-forge

    Analyze session work and automatically convert reusable patterns into Claude Code skills.

    852 GitHub stars~2.7k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

More from zereight/gitlab-mcp

All 24 skills in this repo
  • OMG Mode Canceller

    zereight/gitlab-mcp

    Detects which autonomous OMG mode is currently active - Autopilot, Ralph, Ultrawork, UltraQA, Team or Self-Improve - and shuts it down cleanly.

    2k GitHub starsUsed in 1 repo~690 tokens
    Auto-check passed
  • CCG Tri-Model Orchestration

    zereight/gitlab-mcp

    Runs a task through Codex and Gemini CLIs in parallel alongside Claude, then synthesizes the three outputs into one answer with agreements and conflicts called out.

    2k GitHub starsUsed in 1 repo~657 tokens
    Auto-check passed
  • Shared reference for naming, function size, complexity and error handling rules that reviewer agents apply across TypeScript, Python, Go, Rust, Java, C# and Swift.

    2k GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Remember Project Knowledge

    zereight/gitlab-mcp

    Sorts what you learned in a session into the right memory surface, filtering out ephemeral notes and duplicates before anything is stored.

    2k GitHub starsUsed in 1 repo~846 tokens
    Auto-check passed
  • Pre-Commit Security Scan

    zereight/gitlab-mcp

    Runs a fast security sweep of recent code changes before a commit or PR, checking for leaked secrets, vulnerable dependencies, unsafe input handling and auth gaps.

    2k GitHub starsUsed in 1 repo~859 tokens
    Auto-check: notes
  • OMG Mode Status

    zereight/gitlab-mcp

    Reports which OMG modes are active, such as autopilot, ralph, team, ultraqa and self-improve, with phase, story or cycle progress read from their state files.

    2k GitHub starsUsed in 1 repo~441 tokens
    Auto-check passed

Categories

Questions about Skill Inventory Stocktake

What does Skill Inventory Stocktake do?

Audits a project's skill directories for broken frontmatter, missing template sync and quality gaps, then produces a health report of what needs fixing. md's frontmatter is current, for example that a removed hint field was renamed to argument-hint and that allowed-tools was dropped, diffing the two directories to catch skills missing from one side, checking each skill for required sections such as When to Use and Output Format plus a minimum length so empty stubs are caught, and comparing the skill catalog named in the project's copilot instructions against what actually exists on disk.

When should I use Skill Inventory Stocktake?

Skill Inventory Stocktake fits situations like: checking whether a new skill would duplicate an existing one; verifying skill frontmatter after a tooling version bump; finding skills that are stale, incomplete or out of sync with templates.

How do I install Skill Inventory Stocktake in Claude Code?

Run `npx skills add zereight/gitlab-mcp --skill skill-stocktake -a claude-code`. Or copy the skill folder (.github/skills/skill-stocktake in zereight/gitlab-mcp) into .claude/skills/skill-stocktake in your project. Claude Code loads it when a task matches its description.

How do I install Skill Inventory Stocktake in Codex?

Run `npx skills add zereight/gitlab-mcp --skill skill-stocktake -a codex`. Or copy the skill folder (.github/skills/skill-stocktake in zereight/gitlab-mcp) into .agents/skills/skill-stocktake in your project. Codex loads it when a task matches its description.

Can I use Skill Inventory Stocktake in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zereight/gitlab-mcp --skill skill-stocktake -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-stocktake, .gemini/skills/skill-stocktake, .github/skills/skill-stocktake and .opencode/skills/skill-stocktake in your project.

What does Skill Inventory Stocktake need to run?

SKILL.md names no scripts, command-line tools or credentials: Skill Inventory Stocktake is instructions for the agent only.

Does Skill Inventory Stocktake access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Skill Inventory Stocktake safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Skill Inventory Stocktake use?

Skill Inventory Stocktake is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Inventory Stocktake use?

About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Skill Inventory Stocktake?

Skills that share tags, products or a category with Skill Inventory Stocktake: Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars), Skill Creator (zhayujie/CowAgent, 47k stars), Open-Science Skill Creator (aipoch/open-science, 5.5k stars) and Skill Quality Reviewer (Galaxy-Dawn/claude-scholar, 5.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Inventory Stocktake?

zereight (a GitHub user) maintains it in zereight/gitlab-mcp, which has 2,033 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 10, 2026.

Source: zereight/gitlab-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.