---
title: "skillsaw"
description: "A configurable linter for agent skills, plugins, and AI coding assistant context"
canonical: https://agentpluginsdirectory.com/plugins/skillsaw
last-updated: 2026-09-21
---

# skillsaw
A configurable linter for agent skills, plugins, and AI coding assistant context
- Slug: skillsaw
- Publisher: stbenjam
- Repository: https://github.com/stbenjam/skillsaw
- Manifest: plugin.json
- Version: 1.0.0
- Category (editorial): agent-tooling
- Skills: 6 (skillsaw-create-plugin, skillsaw-fix, skillsaw-issue, skillsaw-lint, skillsaw-onboard, skillsaw-update)
- MCP servers: 0
- Stars: 66
- Repository created: 2026-05-07
- Repository last pushed: 2026-09-20
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/skillsaw
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What skillsaw does, in the publisher's words

Keep your skills sharp.

A linter for the files that steer AI coding agents.

Agent instructions behave like code, but most teams still review them like prose. skillsaw gives them a linter. It validates structure across every major AI coding ecosytem, guards against many supply-chain attacks, and applies content and context rules backed by research and frontier lab guidance.

- Multi-ecosystem structure & compatibility: schema, frontmatter, and manifest validation for Agent Skills (SKILL.md), Claude Code, OpenAI Codex (project config, plugins & marketplaces), Grok Build (project config, plugins & marketplaces), Google Antigravity (configuration in any customization root:.agents/,.agent/, _agents/, _agent/: its rules/ and agents/ prose, plugins, hooks, MCP servers and registries), Agent Plugins v1 (plugin.json, mcp.json), GitHub Copilot & VS Code custom agents (.github/agents/), OpenCode configuration, APM packages, MCP server maps, and MCP Registry metadata.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/stbenjam/skillsaw/HEAD/README.md

## Skills

- skillsaw-create-plugin: Create a skillsaw rule plugin: a pip-installable Python package that adds custom lint rules to skillsaw. Walks through scaffolding the package, writing rules against the lint tree, testing, and publishing to PyPI. Use when a user wants to share skillsaw rules across repositories or publish them fo…
- skillsaw-fix: Fix skillsaw lint violations: apply deterministic autofixes, then resolve the remaining violations with targeted edits guided by `skillsaw explain`. Use when skillsaw reports violations, when asked to clean up lint findings, or after `skillsaw fix` leaves violations behind.
- skillsaw-issue: Use when skillsaw reports a likely false positive, misses an edge case, behaves incorrectly, or needs an RFE. Gather a safe report and, only with explicit user permission, create a feedback bundle or open a GitHub issue.
- skillsaw-lint: Use when modifying agentic contextual building blocks like skills (SKILL.md), slash commands, agents, hooks, plugins, marketplaces, and instruction files (CLAUDE.md, AGENTS.md, GEMINI.md, QWEN.md, Cursor, Copilot, Cline, or Kiro rules), tool configuration such as an OpenCode `opencode.json`, Muse C…
- skillsaw-onboard: Onboard a repository to skillsaw: run the linter, triage the findings by rule, apply autofixes, manually fix what remains, set up CI, and create a baseline. Use when adopting skillsaw on a new or existing project.
- skillsaw-update: Update a repository to the newest skillsaw, upgrade the install, report new rules and their findings in your repo, and bump version pins (GitHub Action SHAs, Makefile targets, pre-commit hooks). Use when a new skillsaw release is out and you want its latest checks.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.