Skip to content

gooseworks-ai/goose-skills / docs/skill-template

<slug>

Verified

<What it does and when to use it, in one or two sentences. This is what an agent matches on. At most 1,024 characters.>

FileKindSize
README.mdmarkdown1.3 KB
SKILL.mdskill md529 B
skill.meta.jsonconfig129 B
# Skill template

Copy this folder to start a new skill. It is a sketch to fill in, not a skill: it is not under `skills/`, so nothing publishes it.

1. Copy `SKILL.md` and `skill.meta.json` into `skills/<family>/<slug>/` (see the table in [CONTRIBUTING.md](../../CONTRIBUTING.md#adding-a-skill) for the family).
2. Replace every `<…>`. The folder name, `name` and `slug` are the same slug, and it never changes once published.
3. Set `category` (`capabilities` for one step, `composites` for several, `playbooks` for a marketing playbook). A marketing skill also sets `tier` (`playbook`, `atom` or `foundation`); a shared skill sets `domain`.
4. Name GooseWorks tools only from `scripts/lib/action-names.json` `actions`, in backticks. `npm run check:tools` catches old names and most made-up ones ([CONTRIBUTING.md](../../CONTRIBUTING.md#gooseworks-tool-names) says which).
5. Put the skill's own tests in `tests/` (`test_*.py` or `*.test.js` run in CI on their own).
6. **A skill in `skills/shared/`** also needs an entry in `retired-skills.json` `current_shared` (or `retained`), saying who uses it.
7. **Update the counts** in the README's "What's in the catalog" table (`test/readme-counts.test.js` fails until they match).
8. Run `npm run ci`, and commit the rebuilt `skills-index.json`.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall