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)。

73

Quality

91%

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

82%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.

The content is highly actionable with concrete templates, phrase banks, and a sequenced 4-phase workflow supported by timing checkpoints. It is well-structured for progressive disclosure, with only minor conciseness and validation-checkpoint gaps.

Suggestions

Add an explicit validation/verify step in Phase 2 (e.g., 'confirm the silent repair actually took effect before reporting progress to the partner') to strengthen the workflow's feedback loop.

Trim repeated retellings of the 597-star incident to a single origin note; the principle is already reinforced throughout the body.

Consider extracting the root-cause analysis template and multi-cat role table into a reference file so SKILL.md stays a leaner overview.

DimensionReasoningScore

Conciseness

The body is mostly efficient — concrete tables, ✅/❌ phrase lists, and templates — but the recurring 597-star narrative and some repeated restatements of the core principle add mild padding. Not a 5 because a few narrative passages could be trimmed without losing clarity.

4 / 5

Actionability

Provides copy-paste-ready scripts (root-cause template, voice-message JSON, 5-minute quick reference), do/don't tables, and concrete ✅/❌ phrasing examples that cover the common cases fully.

5 / 5

Workflow Clarity

A clear 4-phase sequence with explicit timing gates (情绪稳定后再复盘, 幽默许可检测) and a quick-reference checklist; not a 5 because the Phase 2 silent-repair backend work lacks an explicit validation/verification checkpoint before presenting results to the partner.

4 / 5

Progressive Disclosure

No bundle files exist; the body is well-organized into clearly headed sections with one-level-deep external references (shared-rules.md, public-lessons.md) that are explicitly signaled. Not a 5 because the ~230-line body is somewhat dense and a couple of sections (root-cause template, multi-cat分工) could arguably live in reference files.

4 / 5

Total

17

/

20

Passed

Description

100%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.

The description is comprehensive, concrete, and well-structured with explicit what/when/not-for/output clauses and a rich trigger list. It is clearly distinguishable from sibling skills and uses the appropriate voice.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 情绪急救, 止损, 补偿性劳动, 教训沉淀 — giving comprehensive coverage of the skill's capabilities rather than vague language.

5 / 5

Completeness

Explicitly answers what (情绪修复+止损+教训沉淀), when ('Use when'), and even what not to use it for ('Not for') plus expected output, far exceeding the both-what-and-when bar.

5 / 5

Trigger Term Quality

The triggers list and 'Use when' clause cover natural phrases users would say (闯祸了, 搞砸了, 对不起, 怎么补救, 人很难过) plus the technical term 'incident', with synonym coverage.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (irreversible-incident emotional repair) and the 'Not for' clause explicitly disambiguates from debugging and shared-rules, minimizing conflict risk.

5 / 5

Total

20

/

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.

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.