CtrlK
BlogDocsLog inGet started
Tessl Logo

cs-keep

项目知识沉淀。触发:用户要沉淀可复用坑、技巧、调研或非 ADR 结论;结构性 ADR 决策走 cs-domain,一两行每次必读规则走 cs-note。

80

Quality

100%

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

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 a tight, well-structured instruction skill: it points to a preflight, specifies behavior precisely via a Haskell spec and naming/validation rules, sequences the workflow with checkpoints, and defines failure behavior. It earns full marks across all content dimensions.

DimensionReasoningScore

Conciseness

The body is lean — a preflight pointer, a small Haskell spec, a short Operation paragraph, and Failure Behavior — with no padding or explanations of concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.

3 / 3

Actionability

It gives concrete guidance: exact output path '.codestable/compound/YYYY-MM-DD-{slug}.md', validation rules (slug ≤30, non-empty evidence), and a real command 'grep -r "关键词" .codestable/compound/'; per scoring_notes, an instruction skill without executable code is not penalized when guidance is this specific.

3 / 3

Workflow Clarity

The sequence (preflight → read attention → dedup by keyword → validate → write three-section markdown → report path) has explicit validation checkpoints and NeedsHuman feedback loops for attention-missing and invalid-note cases, matching the 'clear sequence with explicit validation steps' anchor.

3 / 3

Progressive Disclosure

Under 50 lines with no bundle files and well-organized sections (preflight, Spec, Operation, Failure Behavior); the one external reference (.codestable/reference/execution-conventions.md) is one level deep and clearly signaled, which scoring_notes says can score 3 for simple skills.

3 / 3

Total

12

/

12

Passed

Description

100%

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 concise yet complete: it names the capability, gives an explicit trigger, and disambiguates two sibling skills. It is a strong, non-conflicting trigger description with no fluff.

DimensionReasoningScore

Specificity

Quotes '项目知识沉淀' and '沉淀可复用坑、技巧、调研或非 ADR 结论' list several concrete sedimentation targets, matching the 'multiple specific concrete actions' anchor rather than the single-domain 'score 2' anchor.

3 / 3

Completeness

It states what ('项目知识沉淀') and an explicit when ('触发:...'), the 'Use when...' equivalent; clearly above the 'has what but when missing/implied' score 2 anchor.

3 / 3

Trigger Term Quality

The explicit '触发:用户要沉淀可复用坑、技巧、调研' phrase covers natural user phrasing (reusable pitfalls, tips, research); it is not generic jargon-only and matches the 'good coverage of natural terms' anchor, though ADR is a domain term it is disambiguated rather than vague.

3 / 3

Distinctiveness Conflict Risk

'结构性 ADR 决策走 cs-domain,一两行每次必读规则走 cs-note' carves a distinct niche and routes away sibling skills, matching the 'clear niche with distinct triggers; unlikely to conflict' anchor.

3 / 3

Total

12

/

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.