agentleFS
Sign inStart free
hevangelhevangel/media-agent-skills/AGENTS.md

media-agent-skills

AGENTS.md4 starsChanged 18 days agoMITView on GitHub

Skills follow the Agent Skills open format: The skills/ directory is the single source of truth. Symlinks/junctions for different AI tools (.github/skills/, .claude/skills, .cursor/skills, .agent/skills) all point back to skills/. This repo supports both Windows and Linux: This repo is a Claude Code plugin marketplace. To use: See .claude-plugin/marketplace.json for available plugin groups.

  • Reads credentials
  • 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 31,700 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 repository15 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Use 4 spaces for indentation (no tabs)

    line 6
  2. Distinctive:

    Use snake_case for function and variable names

    line 7
  3. Very specific:

    Do not call python -c with generated code.

    line 8
  4. Distinctive:

    Always print progress messages when creating Python scripts

    line 9
  5. Very specific:

    Create temporary scripts and test files under temp/

    line 42
  6. Very specific:

    Never commit .env to version control

    line 54
  7. Very specific:

    Use pathlib.Path for all file paths

    line 62
  8. Distinctive:

    Avoid OS-specific path separators in Python code

    line 64

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AI Agents — Coding Guidelines

Basic Standards

  • This repo uses uv for Python package management; always run scripts with uv run python
  • Use 4 spaces for indentation (no tabs)
  • Use snake_case for function and variable names
  • Do not call python -c with generated code; create a Python script then run it
  • Always print progress messages when creating Python scripts

Project Structure

skills/                  # Agent skills (agentskills.io format)
  <skill-name>/
    SKILL.md             # Required: metadata + instructions
    scripts/             # Code snippets and reusable modules
mcp_servers/             # MCP server implementations
anime_organizer/         # Anime library organizer
anime_database/          # Anime metadata (MongoDB)
audiobooks_organizer/    # Legacy audiobook prompts
ebook_organizer/         # Legacy ebook prompts
prompts/                 # Standalone prompt files
temp/                    # Temporary scripts and data (gitignored)

Skills Directory

Skills follow the Agent Skills open format:

  • Each skill lives in skills/<skill-name>/ with a SKILL.md file
  • Directory names: lowercase letters, numbers, and hyphens only
  • The name field in YAML frontmatter must match the directory name
  • Code snippets go in scripts/; assets go in assets/

The skills/ directory is the single source of truth. Symlinks/junctions for different AI tools (.github/skills/, .claude/skills, .cursor/skills, .agent/skills) all point back to skills/.

Temporary Files

  • Create temporary scripts and test files under temp/
  • Store intermediate data (JSON, etc.) under temp/
  • temp/ is gitignored — do not commit temporary files

File Handling

  • Path handling must support both Windows and Linux (use pathlib.Path)
  • Reference library paths via environment variables, not hardcoded paths

Configuration

  • Store all sensitive data (usernames, passwords, API keys, hosts) in .env
  • Never commit .env to version control
  • See .env.example for all available configuration variables
  • Skills reference env vars in their .env code blocks with placeholder values

Cross-Platform Support

This repo supports both Windows and Linux:

  • Use pathlib.Path for all file paths
  • Shell scripts: update_agents.ps1 (Windows) and update_agents.sh (Linux/macOS)
  • Avoid OS-specific path separators in Python code

Claude Code Plugin Marketplace

This repo is a Claude Code plugin marketplace. To use:

/plugin marketplace add <owner>/<repo>

See .claude-plugin/marketplace.json for available plugin groups.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free