Improve Lint — AI skill for Claude Code
Run the AI-augmented lint self-improvement loop on the current project.
How to install Improve Lint
Installs to ~/.claude/skills/heymegabyte-agent-skills-improve-lint/SKILL.md
mkdir -p ~/.claude/skills/heymegabyte-agent-skills-improve-lint && curl -fsSL https://raw.githubusercontent.com/heymegabyte/agent-skills/HEAD/commands/improve-lint.md -o ~/.claude/skills/heymegabyte-agent-skills-improve-lint/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Improve Lint does
name: improve-lint description: 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 `.lint-history/proposals/.md`. Non-blocking analysis. See rules/lint-doctrine.md § Self-improving. argument-hint: "[project-dir]" user-invocable: true
/improve-lint
Closes the self-impro
Alternatives in AI
- Sentrux — Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improveme 2.9k ★
- PRD: Agent Builder — Create Your Own Sub-Agent — Your ecosystem, your rules 1.9k ★
- Claude Hub — by Claude Did This - A webhook service that connects Claude Code to GitHub repositories, enabling AI-powered c 393 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Repo Intel
Unified static analysis - git history, AST symbols, project metadata, doc-code sync, plus LLM-augmented file d
OpenAIReview
AI reviewing paper drafts for improvement.
Skill Evolution
Self-improvement feedback loop for AI agent skills — analyzes past sessions, drafts structured improvement pro
AI Outreach Automation
Claude Code skill that drafts governed, CASL-compliant cold outreach at scale: reusable prompt library, guardr
Analyze Prompts
AI-powered analysis of your prompt history to identify improvement opportunities
Review Slop
Review the current branch diff against main for AI-generated code slop — unnecessary or stylistically inconsis
Related Agents
Moody Blues
Use this agent when you need code reviews, quality audits, or local quality checks (typecheck, lint, test) on
Swe Dev Loop Systems Architect
Designs and audits coding-agent loops, debugging and migration workflows, CI/release loops, autonomous-science
Self Improve Agent
After each OneCommand run, extracts successful patterns, recurring errors, and proven stack combinations into