agentleFS
Sign inStart free
HeyEddi-comHeyEddi-com/heyeddi-skills/.cursor/rules/skill-authoring.mdc

heyeddi-skills / rules

Cursor rule0 starsChanged 3 months agoMITView on GitHub

Standards for authoring installable skills in skills/. Hub .cursor/ is rules only.

The file

We split this skill-authoring.mdc into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    Do not: put distributable skills under .cursor/skills/.

    line 27

≈ “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
skill-authoring.mdc
---
description: Standards for authoring installable skills in skills/. Hub .cursor/ is rules only.
globs: skills/**/*
alwaysApply: false
---

# Skill authoring (HeyEddi collection)

## Layout — installable triad

Each skill lives under `skills/<skill-name>/` — same structure as its standalone GitHub repo:

```
skills/<skill-name>/
├── SKILL.md
├── manifest.json
├── context/
│   ├── VOCABULARY.md
│   ├── ANTI_PATTERNS.md
│   └── EXAMPLES.md
├── reference/
└── scripts/
    ├── _skill_cli.py
    └── *.py / *.sh
```

**Do not** put distributable skills under `.cursor/skills/`. Consumers install via `npx skills add`.

## Distribution

- Subtree prefix: `skills/<name>/`
- Install locally: `./scripts/install-skills.sh <name> --project <app>`
- Publish: `./scripts/push-skill-subtree.sh <name> <remote>`
- Register remotes in `skills-registry.json`

## `.heyeddi/` in consumer projects

Skills read/write product and design context under `.heyeddi/` in the **app repo** (not this hub). See [docs/heyeddi-folder.md](../../docs/heyeddi-folder.md). `project-engineering` scaffolds `.heyeddi/README.md` via `scaffold_heyeddi`.

## Cloud

- `manifest.json` → `python3 scripts/cloud/register_tools.py .`
- Scripts use `_skill_cli.py`, `--project-root`, return text on failure

## Subagents

Skills that orchestrate multi-step work **delegate by default** via Cursor Task tool. Each skill may ship `reference/subagents.md`. Hub spec: [docs/subagent-delegation.md](../../docs/subagent-delegation.md). Cloud backend: same prompt shape as `delegate_to_skill` (Phase 7 roadmap).

## References

- `skills/README.md` — install instructions
- `docs/distribution.md` — subtrees
- `docs/skills-roadmap.md` — full plan

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