jnMetaCode/superpowers-zh / skills/using-superpowers
using-superpowers
Verified在开始任何对话时使用——确立如何查找和使用技能,要求在任何响应(包括澄清性问题)之前调用 Skill 工具
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.0 KB |
| references/antigravity-tools.md | markdown | 1.6 KB |
| references/claude-code-tools.md | markdown | 1.5 KB |
| references/codex-tools.md | markdown | 5.8 KB |
| references/copilot-tools.md | markdown | 3.8 KB |
| references/gemini-tools.md | markdown | 4.5 KB |
| references/hermes-tools.md | markdown | 2.3 KB |
| references/muse-tools.md | markdown | 2.0 KB |
| references/pi-tools.md | markdown | 2.0 KB |
| references/qoder-tools.md | markdown | 3.1 KB |
references/claude-code-tools.md
View on GitHub# Claude Code 工具说明
Claude Code 是基准运行环境:skill 用的就是它的词汇(`Agent` 表示分派子智能体、todos、`Skill`)。这份说明只讲一处:Claude Code 可以用比 skill 默认形态更便宜的方式跑一份计划。它需要你的人类伙伴主动选择,不改变 skill 的任何要求。
## 子智能体驱动开发的更便宜编排方式
在一次 subagent-driven-development 运行里,控制者会话是最贵的那个席位:它要读每一次分派的结果和每一份报告,而且通常跑在会话里最强的模型上。Claude Code 支持嵌套子智能体(默认可在主对话之下嵌套三层;`CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH` 可调整),所以整个循环可以下沉一层来跑。
当你的人类伙伴要求这样做——或者说过会话模型太贵、不值得花在协调上——就分派**一个**跑在中档模型上的编排者子智能体,给它计划路径,并指示它端到端地使用 subagent-driven-development。编排者按那个技能的「模型选择」分派它自己的实现者和审查者;工作区和账本都在磁盘上,所以多出来的这一层不会丢任何东西。它的最后一条消息必须逐字带上「我作出的裁决」(Rulings I made)清单——这份清单是这些决定抵达你人类伙伴的途径,你要原样转达,而不是概括。
只对整份计划这样做。只为单个任务的分派多嵌一层,什么也换不来,只是多了一个席位。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 463k | Updated | Claude CodeCodex | Verified | Install |
| 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: 463k | Updated | Claude CodeCodex | Verified | Install |
| discernment-nudgeanthropics/skillsAfter you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format. | Stars: 195k | Updated | Claude CodeCodex | Verified | Install |
| internal-commsanthropics/skillsA set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.). | Stars: 195k | Updated | Claude CodeCodex | Verified | Install |