← ClaudeAtlas

skillsaw-onboardlisted

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.
stbenjam/skillsaw · ★ 73 · AI & Automation · score 90
Install: claude install-skill stbenjam/skillsaw
# skillsaw Onboard Onboard this repository to **skillsaw**, a linter for agentic contextual building blocks (CLAUDE.md, skills, plugins, agents, hooks, etc.). ## Workflow Ask one routing question at a time and wait for the answer. An explicit choice in the user's request already counts as an answer. Read a reference only after its condition or a yes answer routes to it; do not read the reference to formulate the question. After completing it, return here. If the answer is no, continue to the next checkpoint without reading it. Carry forward the command prefix, counts, choices, and changed-file list. Resolve every `references/...` path relative to the directory containing this `SKILL.md`, never relative to the target repository or the process's current working directory. If this file was fetched from the web, resolve each reference against the parent URL of this file and fetch it from that sibling location. Replace brace-delimited fields below with facts from the repository or scan; never show placeholders to the user, and render singular or plural wording naturally. ### 1. Establish the current state If no working skillsaw command is known, read [install](references/01-install.md). Then read [initial scan](references/02-initial-scan.md) and report its violations before offering changes. ### 2. Triage findings by rule Run `skillsaw lint --format json -v` to see all violations, including the info-level ones the first scan hid. Group the results by `rule_id` and sort th