/improve-lint
Run the AI-augmented lint self-improvement loop on the current project. Scans `.lint-history/` for recurring violation patterns (≥3 hits in 30d window), drafts a Claude-ready prompt to author a new semgrep rule for the top candidate, and surfaces the proposal under
$ npx -y skills add heymegabyte/claude-skills --agent claude-codeShips with claude-skills. Installing the plugin gets this command.
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/improve-lint
Context preview
What this command does when you run it.
Run the AI-augmented lint self-improvement loop on the current project. Scans `.lint-history/` for recurring violation patterns (≥3 hits in 30d window), drafts a Claude-ready prompt to author a new semgrep rule for the top candidate, and surfaces the proposal under
14-category autonomous product-building OS for 32+ AI coding tools. One-line prompts → deployed products.
Repo: heymegabyte/claude-skills
Other commands on claude-skills.
- /agent-audit
Audit agents spawned in the current/last run against the agent-selection taxonomy
Open command - /agent-diversity-review
Run the Agent Diversity Review gate and emit the result table
Open command - /audit-cron-arc
Meta-analyze the effectiveness of a /loop arc — per-iteration metrics, LOC delta trend, saturation detection, and a keep/lengthen/delete recommendation.
Open command - /audit-doctrine
Audit the rules/ directory for missing foundational principles; output gap list with priority and justification
Open command - /audit-hook-wiring
Validate ~/.claude/settings.json hooks block — event names, file existence, executability, matcher syntax; --fix repairs common issues
Open command - /audit-mcp-error-semantics
Catch Resend-class bug (isError: false on HTTP 4xx/5xx) across all MCP server tool handlers
Open command