CtrlK
BlogDocsLog inGet started
Tessl Logo

cs-domain

领域模型维护。触发:记决策、加术语、拆 context、维护 CONTEXT/ADR。不要用于功能实现(cs-feat)、对外文档(cs-docs)、大需求拆解(cs-epic)、需求澄清与能力 doc(cs-req)。

72

Quality

88%

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

92%

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

A tight, highly actionable methodology body with explicit validation gates and clear sequenced workflows. The only gap is progressive disclosure: everything is inline with no external reference structure.

Suggestions

Extract the ADR writing guide (gate criteria, frontmatter template, Nygard sections) and the CONTEXT.md writing guide into separate reference files under references/, keeping SKILL.md as an overview that links one level deep.

Add a short 'References' section pointing to those extracted files so the body acts as a navigable overview rather than the full detailed material.

DimensionReasoningScore

Conciseness

Lean and dense throughout — a compact Haskell contract plus terse rules; it assumes competence and never explains basic concepts like what an ADR is.

3 / 3

Actionability

Exact paths ('.codestable/requirements/adrs/NNN-{slug}.md'), numbering rules, and copy-paste-ready YAML/frontmatter/Nygard templates give fully concrete guidance.

3 / 3

Workflow Clarity

Topology upgrade is a numbered 6-step sequence, ADR writing is gated by the explicit 守门 3 判据 validation, and 退出条件 provides a verification checklist with failure-behavior feedback.

3 / 3

Progressive Disclosure

Sections are well-organized with clear navigation, but the full methodology and all templates live inline in SKILL.md with no overview-to-reference split, and no bundle files are provided.

2 / 3

Total

11

/

12

Passed

Description

85%

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 positive and negative trigger guidance and clear delineation from sibling skills. The only weakness is trigger-term quality, where natural phrasings are partly diluted by technical jargon.

DimensionReasoningScore

Specificity

Lists four concrete actions — '记决策、加术语、拆 context、维护 CONTEXT/ADR' — naming the domain and specific operations rather than vague language.

3 / 3

Completeness

Explicit '触发:' clause answers when, the opening phrase answers what, and a '不要用于…' exclusion clause adds explicit trigger guidance in both directions.

3 / 3

Trigger Term Quality

Natural action verbs ('记决策', '加术语') are present but mixed with technical jargon ('拆 context', 'CONTEXT/ADR') and missing common user-phrasing variations.

2 / 3

Distinctiveness Conflict Risk

Explicitly names and excludes four sibling skills (cs-feat, cs-docs, cs-epic, cs-req), carving a clear niche unlikely to trigger the wrong skill.

3 / 3

Total

11

/

12

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.