
Agents Md
This enforces research-backed best practices for keeping agent documentation minimal and high-signal. It creates or updates AGENTS.md files following strict length limits (under 60 lines, never over 100) because instruction-following degrades with document bloat. The approach is opinionated: analyze the project's actual toolchain first, use headers and bullets only, reference existing docs instead of duplicating them, and prioritize file-scoped commands over expensive full builds. It includes required sections for package manager, commit attribution, and file-scoped commands, while explicitly banning filler like "Welcome to" intros or duplicating linter configs. Useful if your agent docs have become sprawling novels or you want to start with proven conventions instead of reinventing them.
- skills.sh installs
- 151
- GitHub stars
- 39.4K
- last updated
- Jun 3, 2026
Install
$ npx -y skills add sickn33/antigravity-awesome-skills --skill agents-md --agent claude-codeInstalls into .claude/skills of the current project.
Files
Maintain AGENTS.md from repository evidence
Overview
Create or improve agent instructions that help a coding agent change the repository correctly without rediscovering its workflow. Base every repository-specific command, path, and rule on evidence in the current checkout.
Prefer a focused diff over a wholesale rewrite. There is no universal line limit, required section list, symlink layout, or commit-attribution policy; follow the repository's own needs and maintainer intent.
When to Use
- The user asks to create, update, shorten, or audit
AGENTS.md. - A monorepo needs root instructions plus narrower package-level overrides.
- Existing agent instructions contain stale commands, duplicated policy, or unsupported claims.
- The user wants to reconcile
AGENTS.mdwithCLAUDE.md,.github/copilot-instructions.md, or other repository instruction files.
Use @agents-generator instead when the task specifically calls for its
packaged generation modes, assets, or backup workflow. Use this skill when a
maintainer-readable, evidence-first edit is the primary goal.
How It Works
1. Preserve existing intent
Sponsors
Details
- Repository
- github.com/sickn33/antigravity-awesome-skills
- First seen
- Jun 3, 2026
More from sickn33/antigravity-awesome-skills
All 708- Api Endpoint Builder150
- Privilege Escalation Methods146
- Agent Framework Azure Ai Py145
- Canva Automation144
- Ddd Tactical Patterns143
- Bevy Ecs Expert142
- Agents V2 Py141
- Ai Studio Image139
- Gitlab Automation139
- Ai Seo137
- Amplitude Automation137
- Linkedin Automation137
- X Twitter Scraper137
- 20 Andruia Niche Intelligence136
- Development136
- Idor Testing135
- Advogado Especialista134
- Burp Suite Testing132
- Claude Code Expert132
- Shadcn132
- Aws Cost Optimizer130
- Chrome Extension Developer130
- Shodan Reconnaissance130
- Ai Engineering Toolkit129