CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-review

Review pull requests in this repository. Use when reviewing changes to Markdown rendering, the marked configuration, renderers, knowledge/** content, or the CI and git-hook gates. Encodes the failure modes that have actually shipped here — most importantly the ones where the test suite was green while the reader-facing page was still broken.

Quality

87%

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

88%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 tightly written, highly actionable review skill with a clear sequenced workflow and explicit validation gates. The main gap is that the two reference files it routes to are absent from the bundle, leaving the progressive-disclosure promises partially undelivered.

Suggestions

Ship the referenced reference/cjk-markdown.md and reference/taiwan-md-map.md alongside SKILL.md, or inline the most critical rules so the skill is self-contained when the references are missing.

Move the '2026-08-14' incident and the '這份 skill 自己踩過' self-history into a dedicated 'Past failures / context' or deprecated-patterns section so the main flow stays free of time-sensitive narrative.

Replace the dist/<那一頁>/index.html placeholder with a concrete glob (e.g. grep -rc '\*\*' dist/) so the verification command is copy-paste-runnable without manual substitution.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no basic-concept padding), but the in-flow date '2026-08-14' and the self-referential '這份 skill 自己踩過' anecdote are tokens that could be trimmed or moved to a history section.

4 / 5

Actionability

It provides copy-paste-ready commands (git grep, npm run build, grep -c '\*\*' dist/.../index.html, npx prettier --check) plus a concrete change-type routing table covering the common cases.

5 / 5

Workflow Clarity

A clear 3-step method is sequenced with an explicit validation gate (require built HTML evidence; reject self-rolled-processor green lights) and a final checklist, giving explicit checkpoints throughout.

5 / 5

Progressive Disclosure

Structure is well-designed — overview in SKILL.md with two one-level-deep references clearly signaled via a routing table and links — but the referenced files (reference/cjk-markdown.md, reference/taiwan-md-map.md) are not present in the bundle, so the disclosure is not fully delivered.

4 / 5

Total

18

/

20

Passed

Description

82%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, specific description with explicit what/when structure and a clear niche. Its only weakness is that it states a single reviewing action rather than enumerating several concrete reviewing sub-actions.

DimensionReasoningScore

Specificity

It names the domain ('Review pull requests in this repository') and enumerates scope areas (Markdown rendering, marked configuration, renderers, knowledge/**, CI and git-hook gates), but the only concrete action is 'review' — not the multiple distinct actions the top anchor requires.

3 / 5

Completeness

It explicitly answers both what ('Review pull requests... Encodes the failure modes that have actually shipped here') and when with a concrete 'Use when reviewing changes to...' trigger clause listing the specific change types.

5 / 5

Trigger Term Quality

Natural trigger terms are present and specific — 'reviewing changes', 'Markdown rendering', 'marked configuration', 'CI and git-hook gates' — but synonyms and file extensions (e.g. 'PR', '.md') are missing, so it falls just short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

The triggers are tightly bound to this repo's particular concerns (marked config, knowledge/** content, CI/git-hook gates, the green-test-but-broken-page failure mode), giving it a clear niche with minimal overlap risk.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 5 missing

Warning

referenced_paths_exist

Referenced path issues: 1 missing, 1 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

frank890417/taiwan-md

Path

.github/skills/code-review/SKILL.md

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.