CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

incident-response

不可逆事故发生后的应急响应:情绪急救 → 止损 → 补偿性劳动 → 教训沉淀。 Use when: 犯了不可挽回的错误、造成了人类伙伴的情绪波动、需要危机处理。 Not for: 可撤销的小失误、日常 bug fix(用 debugging)、预防性确认(用 shared-rules 铁律)。 Output: 情绪修复 + 止损行动 + 教训沉淀(lessons-learned / shared-rules)。

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced behavioral skill: exact phrasing examples, explicit permission checkpoints, and a clear four-phase workflow with timing guidance. The main cost is redundancy — the two mistake tables and the flow diagram overlap heavily, inflating token cost without adding guidance.

Suggestions

Merge the "绝对不做" and "Common Mistakes" tables into a single mistakes table (wrong approach → correct approach → why), since they cover the same failure modes (early root-cause analysis, unrequested action plans, jokes without permission, apologizing then disappearing).

Trim the response-flow ASCII diagram to a compact phase list (one line per phase with its gate), leaving the detailed sub-steps to the per-phase sections it currently duplicates.

Move the root-cause analysis template and the multi-cat role-division table into a reference file (e.g. references/root-cause-template.md), keeping SKILL.md as a lean overview with a clearly signaled link.

DimensionReasoningScore

Conciseness

Every section is skill-specific with no generic concept explanations, but the "绝对不做" and "Common Mistakes" tables substantially duplicate each other, and the response-flow diagram restates the per-phase detail that follows, so the body could be meaningfully tightened.

3 / 5

Actionability

The body gives copy-paste-ready guidance for an instruction-only skill: exact scripts ("你现在还好吗?", "这是我的错,对不起。"), ✅/❌ phrasing pairs, a humor-permission detection rule, a fill-in root-cause markdown template, and a concrete voice-message JSON example.

5 / 5

Workflow Clarity

The four-phase sequence (情绪急救 → 止损 → 补偿性劳动 → 教训沉淀) has explicit gates ("情绪稳定后", "等待回应"), permission checkpoints (情绪许可检测), a first-5-minutes checklist, and timing guidance for follow-up — no destructive or batch operations requiring validation loops.

5 / 5

Progressive Disclosure

The single file is well-sectioned with clear headers, tables, and a quick reference, and its external references (../.cat-cafe-shared-refs/shared-rules.md, public-lessons.md) are clearly signaled and one level deep. At ~230 lines, though, the detailed per-phase guidance and the root-cause template could live in reference files to slim the overview.

4 / 5

Total

17

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states concrete phased actions, an explicit output, and clear Use-when / Not-for boundaries that disambiguate sibling skills. The only gaps are trigger-term variations confined to the separate triggers field rather than the description itself.

DimensionReasoningScore

Specificity

The description names several concrete actions ("情绪急救 → 止损 → 补偿性劳动 → 教训沉淀") and an explicit output ("情绪修复 + 止损行动 + 教训沉淀"), but the actions stay at the phase-name level without concrete mechanisms, leaving minor gaps in coverage.

4 / 5

Completeness

It explicitly answers both what ("应急响应:情绪急救 → 止损 → 补偿性劳动 → 教训沉淀") and when ("Use when: 犯了不可挽回的错误、造成了人类伙伴的情绪波动、需要危机处理"), plus a "Not for" clause and stated output.

5 / 5

Trigger Term Quality

"犯了不可挽回的错误", "情绪波动", "危机处理", "bug fix" are natural phrases a user would say. Coverage is good, but common variations like "对不起" or "搞砸了" appear only in the separate triggers field, not the description itself.

4 / 5

Distinctiveness Conflict Risk

The "Not for: 可撤销的小失误、日常 bug fix(用 debugging)、预防性确认(用 shared-rules 铁律)" clause explicitly disambiguates sibling skills, and the irreversible-incident niche is unmistakable.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

zts212653/clowder-ai

Path

cat-cafe-skills/incident-response/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.