refactor-agents-mdRefactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure. Use when cleaning up, splitting, or revie...
Install via ClawdBot CLI:
clawdbot install clarezoe/refactor-agents-mdGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/Fei2-Labs/skill-genieAudited Jun 5, 2026 · audit v1.0
Generated Oct 5, 2026
A solo builder maintains a 1,200-line CLAUDE.md that has accumulated contradictory build commands, stale framework notes, and vague style rules. They use the skill in review mode to classify each instruction and get a proposed minimal root file plus topic docs.
An internal developer platform team needs every service repo to follow the same AGENTS.md structure so coding agents behave consistently. They run the skill in apply-refactor mode across repos, splitting root routers from topic docs and deleting outdated guidance.
A popular OSS project receives PRs that grow AGENTS.md into a ball of mud with conflicting contributor instructions. The maintainer uses review mode to flag contradictions, mark redundant rules for deletion, and request a cleaner progressive-disclosure split before merging.
A consultancy that deploys coding agents for clients audits each client's AGENTS.md and CLAUDE.md as part of onboarding. They use the skill to surface conflicts between human docs and agent instructions and deliver a proposed file structure with rationale.
A large monorepo has a single AGENTS.md trying to cover frontend, backend, infra, and data tooling at once. The team applies the refactor to keep only universal rules in root and move per-package guidance into scoped follow-up docs that agents load on demand.
The skill is distributed freely (MIT-0) to drive adoption, with paid tiers offering bulk multi-repo refactoring, policy templates, and migration support. Teams pay for guaranteed consistency and review of agent configs across large codebases.
A hosted service ingests repo AGENTS.md/CLAUDE.md files, runs automated audits, detects drift and contradictions, and enforces a standard structure with CI checks. Customers subscribe per seat or per repo for continuous monitoring and rollout.
Independent developers and agencies offer one-off AGENTS.md refactors, audits, and agent-readiness assessments for teams new to AI coding assistants. The skill serves as the repeatable methodology behind fixed-price engagements.
💬 Integration Tip
Start in review-only mode on a copy of the file so the user can see the classification and conflict report before any edits are applied. Keep the root file as a short router and only move guidance into topic docs when it truly applies to a subset of tasks.
Scored Sep 3, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.