CtrlK
BlogDocsLog inGet started
Tessl Logo

cs-feat-design-review

Deprecated 兼容入口:旧 cs-feat-design-review 调用用;转交 cs-feat --stage design-review。新请求不要主动选择。

66

Quality

78%

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-feat-design-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%

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 exemplar of a lean compatibility shim: concise, concrete, well-sequenced, and properly scoped with a clear fail-stop. It makes no unnecessary assumptions and avoids both verbosity and reference indirection.

DimensionReasoningScore

Conciseness

The body is lean (24 lines), assumes Claude's competence, and contains no concept padding or unnecessary context; every line earns its place.

3 / 3

Actionability

For an instruction-only shim it gives concrete, complete guidance — load cs-feat by installed name, carry the requested_stage intent, and fail-stop if the main protocol cannot load — with no vague or pseudocode directions.

3 / 3

Workflow Clarity

The four-step sequence is clearly ordered and includes an explicit error/validation checkpoint (step 4: stop and report if the main entry cannot be loaded), appropriate for this simple single-purpose skill.

3 / 3

Progressive Disclosure

A short, well-sectioned single-purpose skill with no need for external references; sections are clearly organized and no nested reference chains exist.

3 / 3

Total

12

/

12

Passed

Description

57%

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 clearly communicates that this is a deprecated compatibility shim forwarding to cs-feat's design-review stage, and is well-differentiated. It is weakened by the absence of an explicit 'Use when...' trigger clause and by relying on technical identifiers rather than natural user terms.

Suggestions

Add an explicit 'Use when...' clause stating the legacy trigger conditions (e.g., 'Use only when a legacy cs-feat-design-review invocation must be preserved').

Include natural-language trigger terms a user might actually say alongside the technical 'design-review' / 'cs-feat-design-review' identifiers.

State the concrete capability in third-person action voice (e.g., 'Forwards legacy design-review requests to the cs-feat protocol') rather than framing purely as a deprecation notice.

DimensionReasoningScore

Specificity

The description names a concrete forward target and stage ('转交 cs-feat --stage design-review') but as a deprecation notice it lists only one action rather than multiple specific capabilities.

2 / 3

Completeness

It states what the skill does (forwards to cs-feat design-review stage) and implies when via deprecation ('新请求不要主动选择'), but lacks an explicit 'Use when...' trigger clause, which caps completeness at 2.

2 / 3

Trigger Term Quality

It surfaces the relevant domain terms ('design-review', 'cs-feat-design-review') but these are technical identifiers; natural user phrasings and common variations are missing.

2 / 3

Distinctiveness Conflict Risk

The named entry 'cs-feat-design-review' with explicit deprecation and a distinct forward stage makes it clearly distinguishable and unlikely to trigger for the wrong skill.

3 / 3

Total

9

/

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
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.