CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-quality-gate

评估 Codex Skill 的触发边界、内部流程、输出契约、验证方式和回归质量。用于审查或优化现有 Skill、发布前做行为质量检查、比较修改前后的 Skill 质量,默认只读,不替代仓库结构校验或跨设备同步。

68

Quality

83%

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

78%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.

A well-structured, mostly lean instruction skill with a clear sequenced workflow, explicit output contract, and one-level-deep references. The main improvements are tightening the minor dimension-list redundancy and making the per-dimension assessment steps more concrete.

Suggestions

Remove the restatement of the six dimensions in 审查流程 step 3 (or replace with a pointer to 适用范围) to eliminate the small redundancy.

Add one concrete checkpoint or example per dimension in 审查流程, or link directly to the relevant section of references/quality-rubric.md, so each assessment step is actionable rather than delegated.

Add an explicit validate→fix→re-run loop in 审查流程 step 4 (e.g. 'if a smoke test fails, record the error, propose a minimal fix, and re-run') to reach the top workflow-clarity anchor.

DimensionReasoningScore

Conciseness

The body is lean with bullets and no padding, but the six-dimension focus list in "适用范围" is lightly restated in "审查流程" step 3, a redundancy that could be trimmed.

4 / 5

Actionability

Concrete file-reading targets, a six-dimension assessment checklist, an exact verification command, and a fixed output contract give mostly executable guidance; the per-dimension assessment method is delegated to the reference, leaving minor gaps.

4 / 5

Workflow Clarity

The five-step "审查流程" is clearly sequenced with a validation checkpoint (step 4: run smoke tests, preserve original errors on failure), but it lacks an explicit validate-fix-retry loop, which is acceptable for a read-only review skill yet keeps it just below the top anchor.

4 / 5

Progressive Disclosure

The body is a concise overview with clearly signaled one-level-deep navigation to the real references/quality-rubric.md for detailed scoring and scripts/quality_report.py for verification; content is appropriately split and easy to navigate.

5 / 5

Total

17

/

20

Passed

Description

87%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.

A strong, third-person description that concretely states what it evaluates and when to use it, with explicit non-goals that reduce conflict risk. Minor gains are possible by varying the action verbs beyond "评估" and adding a few more natural synonyms.

DimensionReasoningScore

Specificity

Lists several concrete evaluation targets ("触发边界、内部流程、输出契约、验证方式和回归质量") and three concrete use cases, but all actions sit under the single verb "评估", leaving minor coverage gaps versus a fully enumerated action set.

4 / 5

Completeness

It explicitly answers both what ("评估 Codex Skill 的触发边界...") and when ("用于审查或优化现有 Skill、发布前做行为质量检查、比较修改前后的 Skill 质量") with concrete trigger scenarios, matching the anchor for explicit what-and-when.

5 / 5

Trigger Term Quality

Natural trigger phrases like "审查或优化现有 Skill", "发布前做行为质量检查", and "比较修改前后的 Skill 质量" match what a user would say, but a few common synonyms (e.g. "评测"/"打分") are absent.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (Codex Skill behavior-quality assessment) and explicitly excludes adjacent duties ("不替代仓库结构校验或跨设备同步"), minimizing overlap with related skills.

5 / 5

Total

18

/

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
ooooooooooooooooooop/agent-tools
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.