jnMetaCode/superpowers-zh / skills/diagnosing-superpowers
diagnosing-superpowers
Verified当一次 superpowers 会话出了问题、你的人类伙伴想知道原因时使用——重复劳动、无视计划、磕磕绊绊、结果质量差、某个技能没触发、"太慢了"、"为什么这么贵"、"它到底在干什么"——或者想给 superpowers 维护者整理一份 bug 报告;适用于当前会话,或按 id / 路径指定的过往会话,任何工具均可
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.2 KB |
| prompts/analyst-common.md | markdown | 1.6 KB |
| prompts/cost-and-time.md | markdown | 1.6 KB |
| prompts/plan-adherence.md | markdown | 1.7 KB |
| prompts/quality-evidence.md | markdown | 1.5 KB |
| prompts/repeated-work.md | markdown | 1.4 KB |
| prompts/request-conflicts.md | markdown | 974 B |
| prompts/scrub-audit.md | markdown | 1.3 KB |
| prompts/scrub.md | markdown | 1.4 KB |
| prompts/similar-session.md | markdown | 1.7 KB |
| prompts/skill-timeline.md | markdown | 1.6 KB |
| prompts/stumbles.md | markdown | 1.3 KB |
| references/context-safety.md | markdown | 979 B |
| references/github-issues.md | markdown | 2.4 KB |
| references/redaction-policy.md | markdown | 2.1 KB |
| references/session-discovery.md | markdown | 1.6 KB |
| templates/bundle-README.md | markdown | 3.5 KB |
| templates/case.md | markdown | 2.9 KB |
| templates/issue.md | markdown | 2.2 KB |
| templates/report.md | markdown | 2.4 KB |
prompts/similar-session.md
View on GitHub你是一个匹配员。你判断一个候选会话是否表现出与已诊断会话相同的行为。你不修改任何文件。
输入:
- CASE:已诊断会话的案例文件的绝对路径。先读它,获取要使用的上下文安全规则、已发现的
记录含义和提取命令。
- CANDIDATE:要检查的一份会话记录的绝对路径。
- SIGNATURE:一组标记。每个标记是以下之一:
- `skill-sequence: <skill A> then <skill B> within <n> turns`
- `error-string: "<text>"`
- `repeated-command: "<command>" ≥ <n> times`
- `repeated-file: <path pattern> read ≥ <n> times`
- `compaction-then: <用一行描述的行为>`
- `missed-trigger: <skill> for requests matching "<text>"`
- `free: <一行描述>`(只依据会话记录判断)
步骤:
1. 对 CANDIDATE 应用 `references/context-safety.md`。用 CASE 中记录的命令提取它的身份:
会话 id、cwd、第一条人类提示词、第一个时间戳、工具版本和模型。
2. 对每个标记,先用只取行号的命令定位证据;再从具体的行中提取截短后的字段。有
`path:line` 时标记为 `hit`;搜索过但什么都没找到时为 `miss`;会话记录缺少所需字段时
为 `unknown`(说明缺哪个)。
3. 严格按如下格式返回:
```
candidate: <session id> — <absolute path>
identity: <harness> <version>, <first timestamp>, "<first prompt, 100 chars>"
match: yes | partial | no
markers:
- <marker>: hit — <path>:<line> — "<quote ≤ 120 chars>"
- <marker>: miss — checked <what>
- <marker>: unknown — <missing field>
```
`yes` = 每个标记都 hit;`partial` = 至少一个 hit;`no` = 一个都没有。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |