CtrlK
BlogDocsLog inGet started
Tessl Logo

thread-orchestration

大任务的主动拆解与多 thread 并行编排。 Use when: 任务涉及 2+ 个独立可交付子任务,需要不同猫参与、不同 thread 并行推进。 Not for: 单一任务(直接做)、已有 thread 之间的被动协调(用 cross-thread-sync)、单 session 内 subagent 并行(CLI 内置能力)、发现跨 scope 问题但已有归属 thread(用 cross_post_message,不要新建 thread)。 Output: 子 thread 创建 + 选猫 + 各 thread 交付 + 主 thread 汇聚报告。 GOTCHA: projectPath 是子 thread 的工作区/真相源归属,不是外部目标仓;社区 PR review 目标可以是 clowder-ai,但工作区仍可能应继承 cat-cafe。

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.

Highly actionable with a clear gated workflow and concrete tool-call templates, but it is a monolithic single file with notable redundancy around reportingMode and inline time-sensitive notes that hurt token efficiency.

Suggestions

Collapse the repeated reportingMode explanations into one canonical table and have Step 5, Quick Reference, and Common Mistakes reference it instead of restating the modes each time.

Move the 'Phase AA 更新 (2026-06-07)' change note into a dedicated 'Deprecated/old patterns' section so time-sensitive content does not penalize the live conciseness.

Extract the reportingMode contract detail and/or Common Mistakes into a reference file (e.g. references/reporting-modes.md) and link to it one level deep to improve progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly efficient and accurate, but reportingMode is re-explained across the Step 2 table, scenario guide, constraints, Step 5 preface, Quick Reference, and Common Mistakes, and a time-sensitive 'Phase AA 更新 (2026-06-07)' note sits inline rather than in a deprecated section.

2 / 3

Actionability

Provides fully executable tool calls — cat_cafe_propose_thread and cat_cafe_cross_post_message with complete parameter blocks and copy-paste-ready message templates including the required '## 主 Thread' header.

3 / 3

Workflow Clarity

A clear five-step sequence (拆解→提议→选猫→并行执行→汇聚) with explicit validation gates ('等用户批准 proposal 后', '不要直接 commit…等主 thread 确认') and a serial-dependency feedback loop in 5b.

3 / 3

Progressive Disclosure

No bundle files exist, so the ~240-line body is a single monolithic file; it is well-sectioned but keeps the full reportingMode deep-dive and Common Mistakes inline where a one-level reference could offload detail.

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 when/not-for triggers, natural trigger terms, and clear disambiguation from sibling skills. Voice is appropriately third-person.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in the Output line — '子 thread 创建 + 选猫 + 各 thread 交付 + 主 thread 汇聚报告' — alongside the core '主动拆解与多 thread 并行编排', matching the multiple-specific-actions anchor.

3 / 3

Completeness

Clearly answers both what (decomposition + the Output deliverables) and when (explicit 'Use when:' trigger), with a 'Not for' clause clarifying scope; voice is third-person throughout.

3 / 3

Trigger Term Quality

Combines an explicit 'Use when:'/'Not for:' clause with a triggers list of natural user phrases ('拆任务', '分 thread', '并行推进', '任务分解'), giving good coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The 'Not for' clause explicitly disambiguates cross-thread-sync, CLI subagent parallelism, and cross_post_message, giving it a clear niche unlikely to trigger 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.