agent-skills
AGENTS.md27 starsChanged 8 months agoApache-2.0View on GitHub
This file provides guidance to AI coding agents (Codex, Claude Code, Cursor, Copilot, etc.) when working with this repository. This repository contains reusable AI agent skills for Eigent workflows. Each skill is defined in a SKILL.md file and may include helper scripts, references, and assets. Packaged ZIP artifacts for one-click download are stored in packages/. Use YAML frontmatter with only: Then define concise workflow instructions in markdown. After creating or updating a skill, regenerate its ZIP package: For this repo,…
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 31,439 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 repository40 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- webapp-testingSkill
- env-hubSkill
- mcp-builderSkill
- mintlify-docs-updaterSkill
- reviewSkill
- shipSkill
- skill-creatorSkill
- specSkill
- internal-commsSkill
- ml-failure-auditSkill
- changelog-generatorSkill
- algorithmic-artSkill
- canvas-designSkill
- instagram-reel-editorSkill
- remotionSkill
- slack-gif-creatorSkill
- ab-test-setupSkill
- copywritingSkill
- humanizerSkill
- instagram-postingSkill
- marketing-ideasSkill
- seo-auditSkill
- claude-for-legalSkill
- contract-review-risk-scoringSkill
- doc-coauthoringSkill
- docxSkill
- legal-work-pluginSkill
- pdfSkill
- pptxSkill
- xlsxSkill
- pm-skillsSkill
- resume-tailoringSkill
- last30daysSkill
- brand-guidelinesSkill
- excalidrawSkill
- frontend-designSkill
- open-designSkill
- theme-factorySkill
- web-artifacts-builderSkill
The file
We split this AGENTS.md into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 66
Use YAML frontmatter with only:
- Very specific: line 79
Keep SKILL.md concise; put detailed docs in references/.
- Distinctive: line 81
Prefer scripts for repeated deterministic operations.
- Very specific: line 86
Prefer deterministic scripts with explicit arguments (argparse for Python scripts).
- Distinctive: line 88
Keep script output actionable for agents and humans.
- Distinctive: line 92
After creating or updating a skill, regenerate its ZIP package:
- Distinctive: line 107
When skill behavior changes, update README.md accordingly:
≈ “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
AGENTS.md
This file provides guidance to AI coding agents (Codex, Claude Code, Cursor, Copilot, etc.) when working with this repository.
Repository Overview
This repository contains reusable AI agent skills for Eigent workflows.
Each skill is defined in a SKILL.md file and may include helper scripts, references, and assets.
Packaged ZIP artifacts for one-click download are stored in packages/.
Current Skill Layout
skills/
coding-agents-and-ides/
mintlify-docs-updater/
SKILL.md
scripts/
references/
skill-creator/
SKILL.md
scripts/
references/
mcp-builder/
SKILL.md
scripts/
references/
LICENSE.txt
web-and-frontend-development/
excalidraw/
SKILL.md
references/
packages/
coding-agents-and-ides/mintlify-docs-updater.zip
coding-agents-and-ides/skill-creator.zip
coding-agents-and-ides/mcp-builder.zip
web-and-frontend-development/excalidraw.zipCreating or Updating a Skill
Directory Structure
skills/
{category}/
{skill-name}/
SKILL.md # Required: skill definition
scripts/ # Optional: helper automation scripts
references/ # Optional: supporting docs
assets/ # Optional: templates/static resources
packages/
{category}/{skill-name}.zip # Distribution artifact for one-click downloadNaming Conventions
- Skill directory:
kebab-case(for example:mintlify-docs-updater) - Skill file: always
SKILL.md(uppercase) - Scripts: use clear task-oriented names (existing scripts use
snake_case.py) - Category directory:
kebab-case(for example:coding-agents-and-ides) - Package file:
packages/{category}/{skill-name}.zip
SKILL.md Format
Use YAML frontmatter with only:
---
name: {skill-name}
description: {when to use this skill, including trigger phrases}
---Then define concise workflow instructions in markdown.
Best Practices for Context Efficiency
- Keep
SKILL.mdconcise; put detailed docs inreferences/. - Make descriptions explicit so agents can trigger the correct skill reliably.
- Prefer scripts for repeated deterministic operations.
- Load only the references needed for the current task.
Script Guidelines
- Prefer deterministic scripts with explicit arguments (
argparsefor Python scripts). - Fail fast on invalid input and return clear error messages.
- Keep script output actionable for agents and humans.
Packaging Skills (ZIP)
After creating or updating a skill, regenerate its ZIP package:
zip -rq packages/{category}/{skill-name}.zip skills/{category}/{skill-name} -x "*.DS_Store"For this repo, keep these package artifacts updated:
packages/coding-agents-and-ides/mintlify-docs-updater.zippackages/coding-agents-and-ides/skill-creator.zippackages/coding-agents-and-ides/mcp-builder.zippackages/web-and-frontend-development/excalidraw.zip
README Sync Requirements
When skill behavior changes, update README.md accordingly:
Available Skillsdescriptions (capabilities and outcomes)Installation,Usage,Skill Structure, andLicensesections when relevant
Installation (End Users)
Primary install method:
npx skills add eigent-ai/agent-skillsLicense
This repository is licensed under Apache License 2.0.
See LICENSE for full terms.
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.

