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.
The English summary is being prepared. Showing the original description.
Review the instructions the agent will receive before you install.
Use this skill when skillsaw itself needs a GitHub issue: a false positive, a missed violation, a crash, incorrect autofix, an edge case in rule detection, or a request for enhancement (RFE). Do not use it to report a problem in the repository being linted unless that problem demonstrates incorrect skillsaw behavior or a useful feature gap.
Collect the minimum evidence needed to explain the issue without sending anything externally:
Never copy credentials, private repository content, or complete diagnostic output into an issue draft. Prefer a minimal synthetic reproducer.
Ask the user two explicit questions before taking either action:
skillsaw feedback to create a local diagnostic ZIP?"stbenjam/skillsaw?"Do not run skillsaw feedback without permission for the first action. Do
not create a GitHub issue without permission for the second action. Permission
for one action does not authorize the other. If permission is absent, present
a sanitized draft and ask for the missing approval.
Run skillsaw feedback <repository-path> with a concise --message that
describes the observed behavior. The command creates a local ZIP; it does not
submit anything. Do not add --include unless the user explicitly identifies
the file to share.
Review the ZIP before sharing it. skillsaw does not scan file contents for
secrets: anything --include or --config names is copied in verbatim, so
read those files yourself and remove or replace anything sensitive. Keep the
bundle local if the user does not also approve opening an issue.
Search existing issues first to avoid duplicates. Then open an issue in
stbenjam/skillsaw with:
State which sensitive details were omitted. Link the issue back to the user and summarize what was shared. Do not change labels, milestones, assignees, or project state unless the user specifically requests it.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
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 for others.
The English summary is being prepared. Showing the original description.
Survey the AI coding assistant and agentic tool ecosystem, assess skillsaw's competitive position, identify emerging patterns and missing capabilities, and produce a prioritized strategic report as a GitHub issue. Use when evaluating ecosystem trends and product gaps.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Pick up open GitHub issues from collaborators and create PRs to solve them. Use when triaging and resolving reported bugs or feature requests.
The English summary is being prepared. Showing the original description.
Triage a GitHub issue filed against skillsaw — classify it (bug, feature, docs, question, other), verify its claims against the codebase, enrich it with missing details, and post one structured triage comment. Use when triaging and labeling incoming issues, not to fix them.
The English summary is being prepared. Showing the original description.
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 Code hooks (`.muse/hooks.json`), a Grok Build `.grok/` project layer or a Google Antigravity customization root (`.agents/`, `.agent/`, `_agents/`, `_agent/` — hooks, MCP config, rules, registries and plugins), and committed project memory (`.agents/memory/`). Run skillsaw on the files you touched, apply autofixes, resolve remaining violations with `skillsaw explain` guidance, and re-lint until clean before considering the work complete.
The English summary is being prepared. Showing the original description.