CtrlK
BlogDocsLog inGet started
Tessl Logo

qa

交互式 QA 会话,用户以对话方式报告缺陷或问题,代理创建 GitHub issues。后台探索代码库以获取上下文和领域语言。适用于用户想报告缺陷、执行 QA、以对话方式提交 issues,或提到 “QA session” 时。

76

Quality

93%

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

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable instruction skill with concrete templates and a clear five-step workflow. Its main weakness is the absence of an explicit verification/feedback loop after filing issues, particularly for batch breakdowns.

Suggestions

Add a verification checkpoint after filing — e.g., confirm each 'gh issue create' succeeded and record the returned URL/number before cross-referencing blockers, so a failed creation cannot produce dangling 'Blocked by #N' references.

Add an error-recovery loop for the batch breakdown case: if issue creation fails or a blocking relationship is mis-ordered, re-file in dependency order and correct the 'Blocked by' links.

Tighten the repeated domain-language emphasis (stated in step 2, the template 'Additional context', and 'Rules for all issue bodies') into a single canonical statement to reduce redundancy.

DimensionReasoningScore

Conciseness

Lean and procedural throughout — it provides templates, rules, and a numbered workflow without explaining what GitHub issues or QA are, assuming Claude's competence; every section earns its place despite minor repetition of the domain-language guidance.

3 / 3

Actionability

Gives the concrete command 'gh issue create' plus two complete, copy-paste-ready issue-body templates with labeled sections and explicit rules (e.g., 'No file paths or line numbers', 'Reproduction steps are mandatory'), matching the fully-executable anchor.

3 / 3

Workflow Clarity

The five-step sequence (Listen → Explore → Assess scope → File → Continue) is clearly ordered with an assess-scope checkpoint, but creating multiple issues in a breakdown is a batch operation with no explicit post-creation verification or error-recovery loop, which caps the score per the batch-operations guideline.

2 / 3

Progressive Disclosure

A single self-contained SKILL.md with no bundle files, well-organized into numbered sections and templates; the only external mention (UBIQUITOUS_LANGUAGE.md) is a conditional project-file check rather than a nested reference, so there is no inappropriate deep nesting or content that should be split out.

3 / 3

Total

11

/

12

Passed

Description

100%

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 tight, third-person description that states concrete capabilities and provides an explicit 'use when' trigger clause with natural keywords. It answers both what the skill does and when to invoke it without fluff or over-claims.

DimensionReasoningScore

Specificity

Names multiple concrete actions — '代理创建 GitHub issues', '后台探索代码库以获取上下文和领域语言', '交互式 QA 会话...报告缺陷或问题' — matching the anchor that lists several specific actions rather than vague verbs.

3 / 3

Completeness

Clearly answers what (interactive QA session that creates GitHub issues with background codebase exploration) AND when via an explicit '适用于...时' trigger clause, satisfying both halves of the highest anchor.

3 / 3

Trigger Term Quality

Covers natural phrasings a user would actually say — '报告缺陷', '执行 QA', '以对话方式提交 issues', and the explicit literal trigger '提到 "QA session" 时', giving good keyword coverage with common variations.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (conversational QA → durable GitHub issues) with distinct triggers unlikely to fire for unrelated skills; would not overlap meaningfully with general git or doc skills.

3 / 3

Total

12

/

12

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
vinvcn/mattpocock-skills-zh-CN
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.