contributing-to-superpowers
Skill80 starsChanged 11 days agoMITView on GitHub
Use when editing skills/, agents/, rules/ or .github/ in the superpowers-antigravity repository
In this repository16 other files it gives its agents.
- brainstormingSkill
- browser-testingSkill
- diagnosing-superpowersSkill
- dispatching-parallel-agentsSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- using-git-worktreesSkill
- using-superpowersSkill
- verification-before-completionSkill
- writing-plansSkill
- writing-skillsSkill
The file
We split this skill 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
- Very specific: line 16
Before you report an edit done, run bash tests/run-tests.sh from the repository root (Git Bash on Windows) and fix every FAIL.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Contributing to superpowers-antigravity
This repository is a native Antigravity port of upstream superpowers. Three rules govern every edit under skills/, agents/, rules/ and .github/.
The purity law. Skill, agent and rule text names only Antigravity's own tools and features: no other agent product, no other product's tool names, no tool-mapping file. .github/ names no other agent product either. The banned vocabulary is tests/antigravity/purity-patterns.txt; the tool names skill text may use are the baseline class in tests/antigravity/known-tools.txt.
R3: verbatim port or recorded divergence. Text ported from upstream stays word for word. Any change to it is a divergence, recorded in the spec and the release notes of the change that makes it.
R6: shell neutrality. Skill text works under any shell Antigravity's command tool runs: prefer native tools, give commands that behave the same in every shell, and invoke a bundled script through its interpreter, never by its bare path.
Before you report an edit done, run bash tests/run-tests.sh from the repository root (Git Bash on Windows) and fix every FAIL. A SKIP is not a pass.
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
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.