agentleFS
sugarforeversugarforever/01coder-agent-skills/CLAUDE.md

01coder-agent-skills

CLAUDE.md139 starsChanged 9 months agoMITView on GitHub

A Claude Code plugin marketplace containing skills grouped by category. This repo is a marketplace — a catalog of plugins that users add to Claude Code. All skills are bundled in a single plugin 01coder-skills. The plugin uses: - "source": "./" — plugin root is the repo root - "skills": [...] — explicit list of all skill directory paths This structure ensures that when the plugin is installed and cached, the skills/ directory hierarchy is preserved and Claude Code can…

The file

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

5 rules. About 0 are common, 2 are distinctive, and 3 are 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All skills are bundled in a single plugin 01coder-skills.

    line 35
  2. Very specific:

    Create skills/{skill-name}/SKILL.md with frontmatter:

    line 67
  3. Distinctive:

    Commit and push. Users get the new skill on their next marketplace update.

    line 83
  4. Very specific:

    Follow personal-chinese-writing-style skill conventions when writing Chinese content

    line 92
  5. Distinctive:

    Use fictional examples in skill files, not real user data

    line 93

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

01coder Agent Skills

A Claude Code plugin marketplace containing skills grouped by category.

Repo Structure

01coder-agent-skills/
├── .claude-plugin/
│   └── marketplace.json       # Marketplace catalog (groups skills into plugins)
├── skills/                    # All skills live here
│   ├── {skill-name}/
│   │   ├── SKILL.md           # Skill definition (frontmatter + instructions)
│   │   ├── references/        # Domain knowledge, patterns (optional)
│   │   ├── scripts/           # Automation scripts (optional)
│   │   ├── assets/            # Templates, resources (optional)
│   │   └── templates/         # Report templates (optional)
│   └── ...
├── CLAUDE.md                  # This file
└── README.md

Plugin & Marketplace Architecture

This repo is a marketplace — a catalog of plugins that users add to Claude Code.

Key Concepts

  • Marketplace = this repo. Users add it with /plugin marketplace add sugarforever/01coder-agent-skills
  • Plugin = a group of related skills. Defined in marketplace.json under plugins[]
  • Skill = a SKILL.md file that Claude auto-invokes based on context

marketplace.json Structure

All skills are bundled in a single plugin 01coder-skills. The plugin uses:

  • "source": "./" — plugin root is the repo root
  • "skills": [...] — explicit list of all skill directory paths
{
    "plugins": [
        {
            "name": "01coder-skills",
            "source": "./",
            "skills": [
                "./skills/video-planner",
                "./skills/share-reading"
            ]
        }
    ]
}

This structure ensures that when the plugin is installed and cached, the skills/ directory hierarchy is preserved and Claude Code can discover the SKILL.md files.

Installation

/plugin marketplace add sugarforever/01coder-agent-skills
/plugin install 01coder-skills@01coder-agent-skills

New skills are picked up automatically on marketplace update — no reinstall needed.

Adding a New Skill

  1. Create skills/{skill-name}/SKILL.md with frontmatter:
    ---
    name: skill-name
    description: When to trigger this skill. Be specific about trigger phrases.
    ---
  2. Sync marketplace.json from the filesystem:
    ./scripts/sync-marketplace-skills.sh
    The script scans skills/*/SKILL.md, respects .gitignore (so personal-only skills excluded via gitignore stay out), and rewrites the skills[] array alphabetically. Never edit skills[] by hand.
  3. Bump the marketplace version in marketplace.json (script does not touch the version field).
  4. Commit and push. Users get the new skill on their next marketplace update.

SKILL.md Conventions

Frontmatter

  • name: kebab-case identifier
  • description: Must clearly describe when to trigger. Include trigger phrases in both Chinese and English if applicable.

Content Guidelines

  • Follow personal-chinese-writing-style skill conventions when writing Chinese content
  • Use fictional examples in skill files, not real user data
  • Include interactive workflows (ask user for input before acting)
  • Reference external tools/scripts with relative paths from the skill directory

Personal Data

  • User-specific data (promo links, API keys) should be stored in auto memory (~/.claude/projects/.../memory/), not in the skill repo
  • On first use, skills should ask for personal data and save to memory for reuse

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.