CtrlK
BlogDocsLog inGet started
Tessl Logo

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)。

72

Quality

88%

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

77%Weight 40%Scale 1-3

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

A clear, actionable crisis-response workflow with concrete phrasing examples and well-gated phases, weakened mainly by redundancy across sections and a monolithic inline structure with no reference files.

Suggestions

Consolidate the repeated 'don't analyze first / no jokes without permission / apology is ongoing' rules into one canonical section (e.g. 核心原则) and have the 绝对不做 and Common Mistakes tables reference it instead of restating it.

Extract the detailed Phase 1–4 guidance, the root-cause template, and the multi-cat collaboration table into reference files (e.g. references/phase-detail.md, references/root-cause-template.md) and have SKILL.md link to them one level deep.

Trim the 597-star anecdote and any restated principles to a single溯源 line so the body assumes Claude's competence and earns its tokens.

DimensionReasoningScore

Conciseness

Mostly efficient domain-specific guidance, but the same rules (don't analyze root cause first, no jokes without permission, apology isn't one-time) are restated four times across 核心原则, the phase detail, the 绝对不做 table, and Common Mistakes — padding that could be tightened.

2 / 3

Actionability

Provides copy-paste-ready phrases ('你现在还好吗?', '这是我的错,对不起'), ✅/❌ example pairs, a root-cause markdown template, and a concrete voice-message JSON schema — concrete and executable guidance for a behavioral skill.

3 / 3

Workflow Clarity

A clear four-phase flowchart with explicit gating checkpoints (情绪许可检测 before joking, '情绪稳定后' before post-mortem) plus a 'first 5 minutes' checklist and a Common Mistakes recovery table.

3 / 3

Progressive Disclosure

Well-sectioned but ~230 lines all inline with no bundle files present; detailed phase guidance, the root-cause template, and multi-cat collaboration tables could be split into one-level-deep reference files rather than living in SKILL.md.

2 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 well-constructed description: concrete actions, explicit 'Use when'/'Not for' triggers, and clear disambiguation from sibling skills. Uses third-person/noun-phrase voice with no first/second-person padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the response arc — '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' — rather than vague language.

3 / 3

Completeness

Explicitly answers both 'what' (the four-phase emergency response) and 'when' via a clearly labeled 'Use when:' clause, plus a 'Not for:' discriminator and 'Output:' line.

3 / 3

Trigger Term Quality

The triggers list ('闯祸了', '搞砸了', '对不起', '怎么补救', 'incident') covers natural phrases a user would actually say when needing crisis response, with good variation.

3 / 3

Distinctiveness Conflict Risk

The 'Not for:' clause explicitly redirects reversible mistakes to 'debugging' and preventive confirmation to 'shared-rules', carving a clear niche unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

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.

Validation15 / 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
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.