Superpowers Model Card
这是可索引项目报告证据页：它保留 Superpowers Model Card 的源材料入口、机制线索和限制提醒；正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。
Superpowers Model Card
One Sentence
Superpowers is a skills-and-methodology layer for coding agents, turning operating habits into reusable procedures.
Three Sentences
It supports multiple agent clients, including Claude Code, Codex, Cursor, and related coding agents. Its value is that it treats development workflow as a skill library: brainstorming, worktrees, plans, TDD, review, debugging, and finishing branches. The 2026-06-17 morning packet keeps the methodology lane aligned with another substantial public GitHub movement.
Model Card
| Field | Value |
|---|---|
| Repository | obra/superpowers |
| Source | raw-github/obra_superpowers.md |
| Category | Agentic skills methodology |
| Pattern | reusable skills -> disciplined workflow policy -> worktrees/plans/TDD/review -> cross-agent execution |
| Evidence | Authenticated GitHub API snapshot, 2026-06-17 08:29 +0800 |
Teaching Use
Use Superpowers to teach that self-evolution can happen through reusable operating manuals, not only through automated mutation. A skill is a compressed decision policy: when to plan, when to test, when to ask for review, and when to finish.
Evidence And Limits
The raw capture now reflects a GitHub metadata packet observed on 2026-07-05: 246,190 stars, 21,830 forks, 628 commits, 148 open issues, and 174 open pull requests. This packet is fresher than the previous authenticated packet at 2026-07-05 01:38 +0800 where a delta was observed. This run did not execute the repository locally, validate workflows end to end, or independently rerun benchmark claims. Product, memory, benchmark, and automation claims therefore remain repository-scoped unless separately tested.