Skip to content

jnMetaCode/superpowers-zh / skills/subagent-driven-development

subagent-driven-development

Verified

当在当前会话中执行包含独立任务的实现计划时使用

FileKindSize
SKILL.mdskill md17.7 KB
implementer-prompt.mdmarkdown6.0 KB
re-review-prompt.mdmarkdown5.0 KB
references/example-workflow.mdmarkdown2.5 KB
references/final-review.mdmarkdown1.6 KB
references/finishing.mdmarkdown868 B
references/fix-loop.mdmarkdown4.3 KB
references/preflight-and-resuming.mdmarkdown3.8 KB
references/report-handling.mdmarkdown1.6 KB
scripts/review-packageexecutablescript2.4 KB
scripts/sdd-repoexecutablescript2.3 KB
scripts/sdd-workspaceexecutablescript4.7 KB
scripts/task-briefexecutablescript4.6 KB
task-reviewer-prompt.mdmarkdown9.0 KB

references/report-handling.md

View on GitHub
### 2. 处理报告

实现子智能体会回传四种状态之一。分别处理:

**DONE:** 生成审查包(保持项目工作树为当前目录,用本技能脚本的绝对路径运行 `bash "<本技能目录>/scripts/review-package" PLAN_FILE BASE HEAD`——它会打印出自己写入的那个唯一文件路径;BASE 是你在分派实现者之前记录下来的那个提交——**绝不用** `HEAD~1`,那会悄悄丢掉多提交任务里除最后一个之外的所有提交),然后把打印出的路径交给任务审查者去分派。

**DONE_WITH_CONCERNS:** 实现者完成了工作但提出了疑虑。继续之前先读这些疑虑。如果疑虑关乎正确性或范围,在审查之前先处理掉。如果只是观察(比如"这个文件变大了"),记下来,继续走审查。

**NEEDS_CONTEXT:** 实现者需要没被提供的信息。补上缺失的上下文并重新分派。

**BLOCKED:** 实现者无法完成任务。评估这个阻塞:
1. 如果是上下文问题,补充上下文并用同一个模型重新分派
2. 如果任务需要更多推理,用更强的模型重新分派
3. 如果任务太大,拆成更小的块
4. 如果是计划本身错了,对这个更正作出裁决,记进账本,并把裁决带进重新分派的提示词里

**绝不**忽视一次上报,也**绝不**在什么都没改的情况下强迫同一个模型重试。如果实现者说它卡住了,那就一定有东西需要改变。

如果实现者提问——不论是开始前还是任务中途——清楚完整地回答,需要时补充上下文,不要催着它进入实现。

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: 463kUpdated Claude CodeCodexVerifiedInstall
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: 463kUpdated Claude CodeCodexVerifiedInstall
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: 195kUpdated Claude CodeCodexVerifiedInstall
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: 195kUpdated Claude CodeCodexVerifiedInstall