CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-stream-nesting-logic

万悟平台 SSE 子会话递归嵌套与三明治序列渲染架构指南。涵盖 parentId 领养、order 绝对排序、动静 Chunk 分层及 Vue 2 响应式引用协议。

57

Quality

64%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-stream-nesting-logic/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 lean, well-organized protocol spec that respects Claude's competence and gives concrete structural rules plus a critical code reference. Its main weakness is workflow clarity: it reads as a reference standard rather than a step-by-step, validated procedure, which leaves the sequence and checkpoint anchors unmet.

Suggestions

Add a short ordered 'Implementation/Verification workflow' section with explicit checkpoints (e.g., 1. receive packet -> 2. resolve parentId adoption -> 3. push original reactive ref into messageSequence -> 4. validate status lock) to lift workflow clarity toward the sequenced-with-validation anchors.

Provide one complete, copy-paste-ready code snippet (e.g., the sseMethod.js id-correction interceptor) rather than only the inline single-line push reference, to move actionability from mostly-executable to fully-executable.

Tighten the explanatory '原因' bullets under section 5 to a one-line imperative so the body stays lean at the top of the conciseness scale.

DimensionReasoningScore

Conciseness

The body is compact and assumes Claude's competence (no over-explanation of SSE or Vue 2 basics), with each of the six sections earning its place; only minor phrases like the explanatory '原因' sub-bullets could be trimmed.

4 / 5

Actionability

Provides concrete structural rules (type:'main'/'sub', messageSequence push, order升序) plus a specific code reference (parentSub.messageSequence.push(subConversion)), concrete attribute names (data-sub-id, data-parent-id) and a concrete ID-prefix rule (content_ prefix), but it is mostly architectural rules rather than fully copy-paste-ready code blocks.

4 / 5

Workflow Clarity

Sections are logically numbered (1–6) but this is an architecture/protocol spec rather than a sequenced operational workflow, and there are no explicit validation checkpoints or feedback loops for the lifecycle/ID-correction steps it describes.

3 / 5

Progressive Disclosure

At under 50 lines with no bundle files present (references/, scripts/, assets/ are empty) and well-organized section headers, the simple-skill exception applies and progressive disclosure is fully met by clean internal organization.

5 / 5

Total

16

/

20

Passed

Description

57%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 specific and occupies a clearly distinct niche, but it is written entirely in technical jargon with no natural user trigger phrases and lacks any 'Use when' guidance. Adding an explicit usage-trigger clause and a few natural-language keywords would substantially raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause in plain language stating when Claude should invoke this skill (e.g., '当用户需要渲染万悟平台 SSE 子会话嵌套、调试子会话卡片递归或排查打字效果丢失时使用').

Include a few natural user-facing keywords alongside the technical jargon so a user would naturally trigger this skill (e.g., '子会话渲染', 'SSE 流式嵌套', '打字机闪烁', '孙级会话').

Keep the third-person voice (currently correct) but front-load the 'when' as prominently as the 'what' so completeness reaches the explicit-both anchor.

DimensionReasoningScore

Specificity

Names the domain (SSE sub-session recursive nesting, sandwich-sequence rendering) and lists multiple concrete capabilities — parentId领养, order绝对排序, 动静Chunk分层, Vue 2响应式引用协议 — with strong coverage; sits just below the fully comprehensive anchor.

4.5 / 5

Completeness

The 'what' is clear (an architecture guide covering the listed topics) but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guideline.

3 / 5

Trigger Term Quality

Terms are highly technical jargon ('三明治序列渲染', 'parentId领养', '动静Chunk分层') rather than natural phrases a user would actually say when they need this skill, and there are no natural user-facing synonyms or variations.

2 / 5

Distinctiveness Conflict Risk

The niche is extremely specific (Wanwu platform SSE sub-session nesting) with distinct, jargon-bound triggers and minimal overlap risk with other skills.

5 / 5

Total

14.5

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
UnicomAI/wanwu
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.