agentleFS
codacycodacy/codacy-skills/CLAUDE.md

codacy-skills

CLAUDE.md13 starsChanged 5 months agoMITView on GitHub

This is a collection of Claude skills for working with the Codacy CLI. When making changes: 1. Update README.md if skills are added, removed, or renamed 2. Bump version in the skill's YAML frontmatter metadata when its instructions change 3. If the Codacy CLI adds new commands, update skills/codacy-cloud-cli/SKILL.md and any affected skills

  • Installs packages

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:

    Keep SKILL.md under 500 lines.

    line 29
  2. Very specific:

    Do not use reserved names: anthropic-*, claude-*

    line 39
  3. Distinctive:

    Use numbered steps for ordered workflows

    line 58
  4. Distinctive:

    Update README.md if skills are added, removed, or renamed

    line 78
  5. Very specific:

    If the Codacy CLI adds new commands, update skills/codacy-cloud-cli/SKILL.md and any affected skills

    line 80

≈ “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

CLAUDE.md — Project instructions for Claude

This is a collection of Claude skills for working with the Codacy CLI.

Project structure

/
├── CLAUDE.md               # This file
├── README.md               # Project overview and installation
├── CONTRIBUTING.md         # How to contribute
├── LICENSE                 # MIT
├── CODE_OF_CONDUCT.md      # Community standards
├── .claude-plugin/         # Plugin manifest
│   ├── plugin.json         # Plugin metadata
│   └── marketplace.json    # Marketplace catalog
└── skills/                 # All Agent Skills
    └── <skill-name>/       # One folder per skill
        ├── SKILL.md        # Required — YAML frontmatter + instructions
        └── references/     # Optional — detailed docs

Skill authoring rules

Structure

  • Folder name and name field: kebab-case only (lowercase, hyphens, no spaces or capitals)
  • File must be exactly SKILL.md (case-sensitive)
  • No README.md inside skill folders
  • Keep SKILL.md under 500 lines; move verbose content to references/ files

YAML frontmatter (required fields)

---
name: skill-name-in-kebab-case
description: Third-person description of what it does and when to use it. Include trigger phrases.
---
  • description: under 1024 characters, no XML tags (< >), written in third person
  • Do not use reserved names: anthropic-*, claude-*

Writing good descriptions

Include: what the skill does + when to trigger it + key trigger phrases.

Good:

Queries Codacy issues, findings, and pull request data using the Codacy CLI.
Use when the user asks about code issues, security findings, pull request analysis,
or wants to run Codacy commands.

Bad:

Helps with Codacy.

Writing good instructions

  • Be specific and actionable — avoid vague directives
  • Use numbered steps for ordered workflows
  • Set appropriate freedom: exact commands for fragile operations, flexible guidance for context-dependent ones
  • Include error handling for common failures
  • Reference detailed content via links to references/ files rather than inlining everything
  • Provide concrete examples

Skills in this project

SkillPurpose
codacy-cloud-cliUse the Codacy Cloud CLI: authentication, commands, help system
codacy-code-reviewEnrich code reviews with Codacy data
configure-codacyTailor Codacy config to the project, reduce noise
configure-codacy-cloudTune Codacy config directly on the cloud (repo already on Codacy), reduce noise
setup-coverageSet up test coverage reporting and upload to Codacy
codacy-analysis-cliRun local static analysis using the Codacy Analysis CLI

Keeping this project up to date

When making changes:

  1. Update README.md if skills are added, removed, or renamed
  2. Bump version in the skill's YAML frontmatter metadata when its instructions change
  3. If the Codacy CLI adds new commands, update skills/codacy-cloud-cli/SKILL.md and any affected skills

Codacy CLI basics

  • Install: npm install -g @codacy/codacy-cloud-cli
  • Auth: export CODACY_API_TOKEN=<token> (from Codacy > My Account > Access Management)
  • Help: codacy --help, codacy <command> --help
  • Output formats: --output table (default) or --output json
  • Provider values: gh (GitHub), gl (GitLab), bb (Bitbucket)

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.