CtrlK
BlogDocsLog inGet started
Tessl Logo

cross-thread-sync

跨 thread 协同:发现平行 session → 通知(3+2 件套)→ 争用协调 → 确认。 Use when: 平行 session 之间需要协同、收到跨线程消息、通知改动影响、共享文件争用。 Not for: 跨猫工作交接(用 cross-cat-handoff)、需要新建 thread 时(用 propose_thread / thread-orchestration)。 GOTCHA: 收到跨线程 ACTION 不等于接活;先做 thread/feat ownership gate,不属于当前 thread 就 cross-post 退回。 Boundary with F128: 发现跨 scope 问题 → 先 list_threads 查有没有已有 thread → 有 = 本 skill(cross_post)→ 没有 = propose_thread。 Output: cross-post 通知 + 争用协调完成。

74

Quality

92%

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

85%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 highly actionable, well-sequenced coordination protocol with concrete tool calls, claim/release templates, and explicit gating checkpoints. Its main weakness is redundancy: the routing铁律 and ownership-gate rules are repeated across the top matter, Step 2, and the 常见误区 table.

Suggestions

State the "必须触发目标猫" routing rule once (top matter) and reference it from Step 2 and 常见误区 instead of re-explaining it each time.

Collapse the duplicated ownership-gate guidance between 入站门禁 and 常见误区 into a single canonical statement with a back-reference.

Consider moving the 常见误区 and 场景速查 tables into a references file to shorten the SKILL.md body if it grows further.

DimensionReasoningScore

Conciseness

The routing rule ("必须触发目标猫" / targetCats + @句柄) is stated at the top, restated in Step 2, and again in 常见误区; the ownership-gate idea is likewise repeated, so it is mostly efficient but could be tightened.

2 / 3

Actionability

It gives copy-paste-ready tool calls ("cat_cafe_cross_post_message(threadId:..., targetCats:..., content:...)") and concrete Claim/Release message templates, fully executable rather than pseudocode.

3 / 3

Workflow Clarity

A clear 4-step sequence (发现→通知→争用协调→确认) with explicit validation checkpoints (入站门禁三问) and feedback loops (ack→timeout→升级operator, claim→release→超时失效).

3 / 3

Progressive Disclosure

No bundle files exist, so it is scored as a single-file skill; sections are well-organized with clear headers and inline quick-reference tables appropriate to a coordination protocol.

3 / 3

Total

11

/

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 dense, well-structured description that covers what, when, not-for, a gotcha, a boundary rule, and output in third-person voice. It is thorough without devolving into fluff, though it sits at the verbose end of the acceptable range.

DimensionReasoningScore

Specificity

"发现平行 session → 通知(3+2 件套)→ 争用协调 → 确认" names multiple concrete sequential actions rather than vague abstractions, matching the level-3 anchor.

3 / 3

Completeness

It explicitly answers what ("跨 thread 协同:发现...确认") and when ("Use when: ..."), satisfying both halves with an explicit trigger clause; not capped at 2.

3 / 3

Trigger Term Quality

"Use when: 平行 session 之间需要协同、收到跨线程消息、通知改动影响、共享文件争用" plus the triggers list ("通知另一个 session", "cross-thread", "另一只Ragdoll") give natural phrasing a user would say.

3 / 3

Distinctiveness Conflict Risk

"Not for: 跨猫工作交接(用 cross-cat-handoff)" and "Boundary with F128" carve a clear niche, making conflict with adjacent skills unlikely.

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.