agentleFS
Sign inStart free
Tamircohen28Tamircohen28/tamirs-superpowers/.cursor/rules/skills-guide.mdc

tamirs-superpowers / rules

Cursor rule2 starsChanged 3 months agoMITView on GitHub

How to create, modify, or invoke skills in this plugin — use when working with SKILL.md files or adding new skills

The file

We split this skills-guide.mdc into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Create skills/<domain>/<skill-name>/SKILL.md with skill-creator — never hand-write one

    line 15
  2. Distinctive:

    Update the skill table and any documented count in README.md

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule 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
skills-guide.mdc
---
description: "How to create, modify, or invoke skills in this plugin — use when working with SKILL.md files or adding new skills"
alwaysApply: false
globs: "skills/**/*"
---

# Skills guide

Skills are `SKILL.md` files with YAML frontmatter, loaded as slash commands. The **directory name** under `skills/<domain>/` is the command name.

Canonical authoring rules: `rules/dev/skill-quality-standards.md`. Canonical frontmatter schema: `core/schemas/skill-frontmatter.json`. Do not restate the field list here — read the schema; a copied list drifts.

## Adding a skill

1. Create `skills/<domain>/<skill-name>/SKILL.md` with `skill-creator` — never hand-write one
2. `python3 scripts/validate-skill-frontmatter.py skills/<domain>/<skill-name>/SKILL.md`
3. Update the skill table and any documented count in `README.md`
4. `make validate` (`check-doc-claims` fails on a stale count)

## Portability

One `skills/` tree ships to every target. Keep skill bodies provider-neutral: check `core/capabilities/platforms.json` before relying on subagents, hooks, a statusline, or background tasks, and degrade explicitly when a capability is absent — a stated fallback, or a plain "unsupported here". Never silently pretend it worked.

**User guide:** [docs/user/agent-kit.md](../../docs/user/agent-kit.md) — agent-kit distribution repos (`repo-scaffold --type plugin`).

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