agentleFS
eugenepyvovaroveugenepyvovarov/mcpbundler-agent-skills-marketplace/skill-boilerplate-skill/SKILL.md

skill-boilerplate

Skill12 starsChanged 9 months agoMITView on GitHub

Define a standard per-skill local data layout at <project_root>/.skills-data/<skill-name> and required SKILL.md guidance for env/config/deps/tools. Use when starting a new skill and you must specify where to store data, env files, local binaries, and dependencies.

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Document the mandatory local data layout and instructions to embed in new skills.

    line 10
  2. Very specific:

    If <skill-root>/.. is skills, guess project_root as two levels above the skills folder (i.e.

    line 15
  3. Distinctive:

    Ask the user to confirm the guess.

    line 17
  4. Very specific:

    If the skill is not under a skills directory, do not guess.

    line 18
  5. Very specific:

    Write these keys into .skills-data/<skill-name>/.env:

    line 41
  6. Very specific:

    If a skill needs setup automation, add helper scripts under that skill's scripts/ directory.

    line 61
  7. Very specific:

    If a skill needs system utilities (rg, jq, git), document manual install commands and reference references/os-install.md.

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill 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
SKILL.md

Skill Boilerplate

Purpose

Document the mandatory local data layout and instructions to embed in new skills. This skill does not create any folders or files.

Determine project_root and data dir

  • Let <skill-root> be the folder containing SKILL.md.
  • If <skill-root>/.. is skills, guess project_root as two levels above the skills folder (i.e. <skill-root>/../../..).
  • This works when skills are stored as <project_root>/<container>/skills/<skill-name>, where <container> can be .codex, .claude, .github, or any other parent.
  • Ask the user to confirm the guess; if it is wrong, request project_root.
  • If the skill is not under a skills directory, do not guess; ask the user for project_root.
  • Data dir: <project_root>/.skills-data/<skill-name>/.

Mandatory SKILL.md section (copy into every new skill)

## Local data and env
- Store all mutable state under <project_root>/.skills-data/<skill-name>/.
- Keep config and registries in .skills-data/<skill-name>/ (for example: config.json, <feature>.json).
- Use .skills-data/<skill-name>/.env for SKILL_ROOT, SKILL_DATA_DIR, and any per-skill env keys.
- Install local tools into .skills-data/<skill-name>/bin and prepend it to PATH when needed.
- Install dependencies under .skills-data/<skill-name>/venv:
  - Python: .skills-data/<skill-name>/venv/python
  - Node: .skills-data/<skill-name>/venv/node_modules
  - Go: .skills-data/<skill-name>/venv/go (modcache, gocache)
  - PHP: .skills-data/<skill-name>/venv/php (cache, vendor)
- Write logs/cache/tmp under .skills-data/<skill-name>/logs, .skills-data/<skill-name>/cache, .skills-data/<skill-name>/tmp.
- Keep automation in <skill-root>/scripts and read SKILL_DATA_DIR (default to <project_root>/.skills-data/<skill-name>/).
- Do not write outside <skill-root> and <project_root>/.skills-data/<skill-name>/ unless the user requests it.

Environment variables

Write these keys into .skills-data/<skill-name>/.env:

  • SKILL_ROOT: absolute path to the skill directory
  • SKILL_NAME: skill name
  • SKILL_DATA_ROOT: absolute path to <project_root>/.skills-data
  • SKILL_DATA_DIR: absolute path to <project_root>/.skills-data/<skill-name>

Optional language-specific keys (use only if the skill needs that runtime):

  • PYTHON_VENV
  • NODE_PATH
  • NPM_CONFIG_CACHE
  • GOMODCACHE
  • GOCACHE
  • COMPOSER_CACHE_DIR
  • COMPOSER_VENDOR_DIR
  • COMPOSER_HOME

Boilerplate helper functions

If a skill needs setup automation, add helper scripts under that skill's scripts/ directory. Keep them opt-in and document them in that skill's SKILL.md. Use references/boilerplate-functions.md for copy-ready snippets.

OS utilities (optional)

If a skill needs system utilities (rg, jq, git), document manual install commands and reference references/os-install.md.

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.