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。

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./cat-cafe-skills/thread-orchestration/SKILL.md

Quality

Content

73%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 body is a well-structured, highly actionable orchestration playbook with explicit validation checkpoints and gating for destructive/batch operations. Its main weakness is redundancy across sections and a monolithic layout with no progressive disclosure into reference files.

Suggestions

De-duplicate the reportingMode semantics and the 'first message must include ## 主 Thread' rule so each is stated once and cross-referenced elsewhere.

Extract the detailed reportingMode contract table and community-PR special case into a reference file linked from the main flow to improve progressive disclosure.

Tighten the Step 2/Step 5/Quick Reference overlap into a single canonical definition with short pointers.

Dimension	Reasoning	Score
Conciseness	Mostly operational and assumes domain knowledge, but the reportingMode rules and '第一条消息必须含 ## 主 Thread' are restated across Step 2, Quick Reference, Common Mistakes, and the Step 5 preface, adding noticeable redundancy.	3 / 5
Actionability	Provides concrete tool-call templates with named parameters and return-value semantics, plus task→cat and reportingMode decision tables, with only minor placeholder gaps like <main_thread_id>.	4 / 5
Workflow Clarity	A clear five-step sequence with explicit gating (user approval before thread creation, commit confirmation), reportingMode-based branching, 5a/5b/5c checkpoints, and a Common Mistakes checklist acting as validation feedback loops.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and a self-contained structure, but it is a ~245-line monolith with no external reference files; dense sections like the reportingMode table could be split out.	4 / 5
	Total	16 / 20 Passed

Description

76%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 strong: it explicitly covers what, when, and not-for boundaries with concrete actions and a distinct niche. Its main weakness is jargon-heavy trigger language that underuses natural user phrasing, and meta lines (GOTCHA, tips_exempt) that slightly dilute capability specificity.

Suggestions

Lead the description with natural trigger phrases users would actually say (e.g., '拆任务', '开多个 thread', '并行推进多个子任务') before internal jargon to raise trigger_term_quality.

Trim or relocate the GOTCHA and tips_exempt meta lines out of the user-facing description so the capability list stays clean and specific.

Add a couple of plain-language synonyms for the core actions (e.g., 'break a big task into parallel subtasks') to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('主动拆解', '多 thread 并行编排', '子 thread 创建 + 选猫 + 各 thread 交付 + 主 thread 汇聚报告'), but GOTCHA/tips_exempt meta lines dilute pure action coverage, leaving minor gaps.	4 / 5
Completeness	Explicitly answers both what ('Output: 子 thread 创建 + 选猫 + 各 thread 交付 + 主 thread 汇聚报告') and when ('Use when: 任务涉及 2+ 个独立可交付子任务') with concrete trigger phrases and a Not-for boundary.	5 / 5
Trigger Term Quality	Includes some natural terms ('并行推进', '拆任务' via triggers) but leans heavily on internal jargon ('独立可交付子任务', 'cross-thread-sync', 'cross_post_message') and misses common synonyms.	3 / 5
Distinctiveness Conflict Risk	Explicit 'Not for' clause distinguishes from cross-thread-sync and CLI subagent parallelism, giving a clear niche with only minor overlap risk against the closely related cross-thread-sync skill.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
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/thread-orchestration/SKILL.md
Commit: 090626a

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.