# Skillcheck

> Validates and scores SKILL.md files against the agentskills.io specification; use when linting skills for cross-agent compatibility, description quality, or capability graph structure.

- **Type:** Skill
- **Install:** `agentstack add skill-moonrunnerkc-skillcheck-skillcheck`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [moonrunnerkc](https://agentstack.voostack.com/s/moonrunnerkc)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [moonrunnerkc](https://github.com/moonrunnerkc)
- **Source:** https://github.com/moonrunnerkc/skillcheck/tree/main/skills/skillcheck

## Install

```sh
agentstack add skill-moonrunnerkc-skillcheck-skillcheck
```

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

## About

skillcheck is a static analyzer for SKILL.md files. It validates frontmatter structure, scores description discoverability, checks file references, and extracts a capability graph from heading and backtick-reference patterns. Run it before committing a skill, plugging it into CI, or publishing to a skill registry.

## Prerequisites

- path - the SKILL.md file or directory to validate
- prompt.txt - file path for a saved agent prompt (critique or graph extraction)
- response.json - file path for an agent-provided JSON response

## Validate a skill

Pass `path` to `skillcheck` for a full structural check against the agentskills.io specification. Validates name constraints, description quality, body sizing, file references, and cross-agent compatibility. The `validation report` is written to stdout. Exit codes: 0 no errors, 1 errors found, 2 input error (missing file), 3 symbolic passed but semantic critique flagged errors.

```bash
skillcheck 
skillcheck  --format json
```

## Review a skill with an agent

skillcheck generates a structured critique prompt for `path` and ingests `response.json` as the agent's reply. Save the emitted prompt to `prompt.txt`. The merged `validation report` combines symbolic diagnostics and semantic findings from the critique.

```bash
skillcheck  --emit-critique-prompt > prompt.txt
```

Hand `prompt.txt` to your agent. The agent returns JSON. Save the response as `response.json`, then ingest it.

```bash
skillcheck  --ingest-critique response.json
```

Pass `--critique-agent codex` or `--critique-agent cursor` to select a prompt variant tuned for that platform. The critique JSON schema is identical across all agent targets.

## Extract a capability graph

skillcheck extracts the `capability graph` from heading structure and backtick references in the body of `path`. Use `prompt.txt` for emitted graph prompts and ingest `response.json` from your agent for richer extraction.

Run graph analysis using the heuristic extractor (no agent needed):

```bash
skillcheck  --analyze-graph
```

For richer extraction, emit the graph prompt, run it through your agent, and ingest the response:

```bash
skillcheck  --emit-graph-prompt > prompt.txt
skillcheck  --ingest-graph response.json
```

Print the graph to stdout:

```bash
skillcheck  --emit-graph
skillcheck  --emit-graph --format json
```

When both heuristic and agent graphs are available, skillcheck compares them and emits `graph.contradiction.heuristic_disagreement` at error severity for agent-claimed edges that the heuristic does not confirm.

## Check validation history

Append a record to the `validation ledger` for each `--history` run on `path`. The ledger is stored in `.skillcheck-history.json` next to the skill file, is append-only, and is safe to commit.

```bash
skillcheck  --history
skillcheck  --show-history
skillcheck  --show-history --format json
```

Each record stores the timestamp, skillcheck version, a 16-character content hash, which validation modes ran, and diagnostic counts. When the skill content matches a prior passing run but the current run fails, skillcheck emits `history.skill.regressed` to flag rule tightening or a new agent finding.

## Outputs

- validation report - diagnostic output written to stdout
- capability graph - graph of capabilities, inputs, and outputs extracted from the skill body
- validation ledger - written to `.skillcheck-history.json` next to the skill file

## Source & license

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

- **Author:** [moonrunnerkc](https://github.com/moonrunnerkc)
- **Source:** [moonrunnerkc/skillcheck](https://github.com/moonrunnerkc/skillcheck)
- **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-moonrunnerkc-skillcheck-skillcheck
- Seller: https://agentstack.voostack.com/s/moonrunnerkc
- 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%.