CtrlK
BlogDocsLog inGet started
Tessl Logo

cs-refactor

行为等价的重构、拆分、性能优化。会改变外部可观察行为的诉求走 cs-feat 或 cs-issue。

52

Quality

58%

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 ./plugins/codestable/skills/cs-refactor/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 an information-dense, action-oriented policy with strong validation gates, concrete templates and paths, and clear feedback loops. Its main weaknesses are length/density that could be tightened and a total absence of progressive disclosure — no reference files split out the elaborate review and learning protocols.

Suggestions

Move the elaborate 审查协议 (review protocol) and 持续学习 (learning protocol) into separate reference files (e.g. references/review-protocol.md) referenced one level deep from SKILL.md to improve progressive disclosure.

Tighten the 持续学习 section: the bounded read-repair and candidate rules repeat conditions across paragraphs and could be condensed into a short checklist.

Add a short numbered '典型流程' (typical flow) summary near the top so the section-based policy maps to an explicit step sequence for workflow clarity.

DimensionReasoningScore

Conciseness

The body avoids concept padding Claude already knows, but it is a very long, dense policy wall; the 持续学习 and 审查协议 sections in particular could be tightened or trimmed without losing operational value.

3 / 5

Actionability

Highly concrete instruction guidance — exact paths (`.codestable/work/refactor-{slug}.md`), report templates (`经验命中:{path}({status});核验:{fact};影响:{plan_or_check}`), thresholds (max 3 review rounds), and explicit triggers — with only minor gaps from its policy (non-code) form.

4 / 5

Workflow Clarity

A clear section-based workflow (开工 → 硬门槛 → 验证范围 → 收尾) with explicit validation checkpoints ("先有能自证等价的验证,再动代码"), a red→green feedback loop, and a hard-gate checklist; the only gap is policy-style rather than crisp numbered sequencing.

4 / 5

Progressive Disclosure

Section headers are well organized, but the skill is a long monolithic SKILL.md with no bundle files or references, and the elaborate 审查协议 and 持续学习 sections are content that could plausibly live in separate reference files.

3 / 5

Total

14

/

20

Passed

Description

53%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 third-person, concise, and draws a clear boundary against sibling skills, but it lacks an explicit "Use when..." trigger clause and offers only two concrete actions with no keyword synonyms. Adding a concrete trigger phrase and one or two more specific actions would lift specificity and completeness.

Suggestions

Add an explicit 'Use when...' clause (e.g. 'Use when the user asks to refactor, split, or optimize code without changing its observable behavior').

List one or two more concrete actions (e.g. 'extract module', 'inline dead code', 'rename for clarity') to raise specificity from 3 to 4-5.

Include natural trigger synonyms (e.g. '重构 / refactor / 重新组织代码') so the description matches more varied user phrasings.

DimensionReasoningScore

Specificity

Names the refactor domain plus two concrete actions ("拆分" splitting, "性能优化" performance optimization), but stops at 1-2 actions beyond the domain rather than listing several specific operations.

3 / 5

Completeness

The "what" is clear ("行为等价的重构、拆分、性能优化"), but the "when" is only weakly implied via the redirect clause ("会改变外部可观察行为的诉求走 cs-feat 或 cs-issue") rather than an explicit "Use when..." trigger, capping completeness at 3.

3 / 5

Trigger Term Quality

Includes relevant natural keywords ("重构", "拆分", "性能优化") a user would say, but offers no synonyms, file extensions, or variations and no "Use when..." trigger phrase.

3 / 5

Distinctiveness Conflict Risk

The explicit redirect to cs-feat / cs-issue carves out a clear behavior-preserving niche with minimal conflict risk; only minor overlap remains with the closely related cs-* skill family.

4 / 5

Total

13

/

20

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
codestable/CodeStable
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.