awesome-ai
AGENTS.md67 starsChanged 59 days agoMITView on GitHub
Collection of custom instructions, prompts, agents, and skills for GitHub Copilot and other AI tools. Skills may include: All artifact files (instructions, prompts, agents, skills) use a status field in YAML frontmatter. Documentation files in docs/ do not require frontmatter. Status definitions: docs/status-badge-lifecycle.md. Emojis in Markdown headers MUST appear after the header text, never before. Reason: screen readers announce emojis first when they lead, disrupting comprehension.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- anchildress1/awesome-github-copilotword for word, first seen Sep 16, 2026
Other versions1 project uses a version of this.
Word for word · 1
- anchildress1/awesome-github-copilot★ 67100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,542 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository7 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- changelog-writerSkill
- eslint-plugin-configuringSkill
- generate-commit-messageSkill
- pr-comment-reviewSkill
- readme-generatorSkill
- test-writerSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
All artifact files (instructions, prompts, agents, skills) use a status field in YAML frontmatter.
- Distinctive: line 35
Must contain a status badge
- Distinctive: line 43
Follow existing file patterns in each directory
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
awesome-ai — Agent Instructions
Repository purpose
Collection of custom instructions, prompts, agents, and skills for GitHub Copilot and other AI tools.
File layout
| Artifact type | Location | File suffix/name |
| Instructions | instructions/ | .instructions.md |
| Prompts | prompts/ | .prompt.md |
| Agents (formerly Chat Modes) | agents/ | .agent.md |
| Skills | skills/<skill-name>/ | SKILL.md |
Skills may include:
skills/<skill-name>/references/— reference docs consumed by the skillskills/<skill-name>/assets/— templates and examples consumed by the skill
Status system
All artifact files (instructions, prompts, agents, skills) use a status field in YAML frontmatter. Documentation files in docs/ do not require frontmatter. Status definitions: docs/status-badge-lifecycle.md.
Content rules
Emojis
Emojis in Markdown headers MUST appear after the header text, never before. Reason: screen readers announce emojis first when they lead, disrupting comprehension.
Documentation (docs/)
- Audience: human readers (contributors, users)
- No frontmatter required
- Must contain a status badge
- Explains purpose, usage, and examples for the corresponding artifact
- Extend existing files; do not create new formats
Artifact files (instructions, prompts, agents, skills)
- Audience: AI agents
- YAML frontmatter required with at minimum a
statusfield - Follow existing file patterns in each directory
Toolchain
- remark: Markdown linting and formatting —
npm run lint/npm run format - commitlint: Conventional Commits enforcement via custom plugin
- lefthook: Runs remark and commitlint as pre-commit and commit-msg hooks
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.