# Skill Lint

> Repository-wide lint workflow for skill frontmatter, description routing quality, and high-risk body inconsistencies. Use when the user wants to lint a shared skills repository, enforce skill metadata conventions, or review skills after a bulk refactor or cleanup.

- **Type:** Skill
- **Install:** `agentstack add skill-cloud99277-kitclaw-skill-lint`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [cloud99277](https://agentstack.voostack.com/s/cloud99277)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [cloud99277](https://github.com/cloud99277)
- **Source:** https://github.com/cloud99277/KitClaw/tree/main/core-skills/skill-lint

## Install

```sh
agentstack add skill-cloud99277-kitclaw-skill-lint
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Skill Lint

Run deterministic lint checks across a centralized skills repository.

This skill wraps the repository-wide `lint_skills.py` checker and gives agents a stable entry point for validating skill frontmatter, routing metadata, and a small set of high-risk body inconsistencies.

## When to Use

- After editing many skills in one pass
- Before committing or reviewing changes in a shared skills repo
- When checking whether `SKILL.md` frontmatter follows repository conventions
- When checking whether `description` lines still match the routing template
- When you want a machine-readable lint report for CI or batch cleanup

## Script Directory

Use the wrapper script in this skill:

```bash
python3 "${SKILL_DIR}/scripts/run_lint.py" [path] [options]
```

The wrapper delegates to the repository-level checker at:

```bash
.system/skill-creator/scripts/lint_skills.py
```

## Common Commands

Run across the whole centralized repository:

```bash
python3 "${SKILL_DIR}/scripts/run_lint.py"
```

Run in strict mode:

```bash
python3 "${SKILL_DIR}/scripts/run_lint.py" --strict
```

Get JSON output:

```bash
python3 "${SKILL_DIR}/scripts/run_lint.py" --format json
```

Fail on warnings:

```bash
python3 "${SKILL_DIR}/scripts/run_lint.py" --fail-on-warnings
```

Only show structural errors:

```bash
python3 "${SKILL_DIR}/scripts/run_lint.py" --errors-only
```

Lint a specific root:

```bash
python3 "${SKILL_DIR}/scripts/run_lint.py" "/path/to/skills/root"
```

## What It Checks

- Frontmatter structure and required keys
- `name` format and length
- `description` shape, old phrases, and routing-template drift
- Known high-risk body inconsistencies such as legacy commands or outdated trigger wording

## Output Interpretation

- `OK`: no issues found for that skill
- `WARN`: semantic or routing-quality issues
- `ERROR`: structural issues that should block acceptance

## Default Behavior

- Default mode is compatibility mode
- Body checks are enabled by default
- `--strict` is best for newly-created or fully normalized skill repos
- `--format json` is best for CI or batch post-processing

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [cloud99277](https://github.com/cloud99277)
- **Source:** [cloud99277/KitClaw](https://github.com/cloud99277/KitClaw)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-cloud99277-kitclaw-skill-lint
- Seller: https://agentstack.voostack.com/s/cloud99277
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.