CtrlK
BlogDocsLog inGet started
Tessl Logo

build-cs-skill

CodeStable skill authoring and evolution protocol. Use when creating, refactoring, simplifying, or reviewing cs-* skills under plugins/codestable/skills or .claude/skills. Produces a thin harness, an explicit context plan, evidence gates, and an optional agent collaboration contract. Do not use for product implementation; use eval-cs-skill only for measured experiment loops.

68

Quality

83%

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

78%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 a well-structured methodology skill: concise protocol prose, concrete decision functions and thresholds, a numbered build workflow with validation, and clean one-level-deep references to real bundle files. Minor tightening and a few more inline validate-retry checkpoints would push it to full marks.

Suggestions

Tighten the methodology rationale in sections like 'Preserve hard contracts' and 'Add collaboration only when useful' to reduce protocol prose that an expert agent could infer.

Add an explicit inline validate-fix-retry loop (e.g., on placeRule output or context-plan checks) rather than relying on the distributed step-8 validation pass.

Consider moving the Haskell spec block into a reference file so the harness body stays closer to its own 60-120 workflow-front-door threshold.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — compact Haskell decision signatures and protocol prose with no padding of basic concepts — but a few sentences of methodology rationale could still be trimmed, placing it at 4 rather than a fully lean 5.

4 / 5

Actionability

Concrete, executable guidance is present (explicit line thresholds 30-80/60-120/40, the placeRule and selectSkillShape decision functions, an ordered kernel recipe, a packet contract), with only minor gaps, so 4 rather than 5.

4 / 5

Workflow Clarity

The eight-step Build Protocol is clearly sequenced with validation in step 8 (quality-gates plan, repository tests, git diff --check) and a placeRule feedback loop plus a Failure Behavior recovery section, but some checkpoints are distributed rather than inline validate-fix-retry loops, so 4 not 5.

4 / 5

Progressive Disclosure

Three real one-level-deep references (cs-skill-spec-standard.md, cs-skill-quality-gates.md, cs-skill-fixture-patterns.md) are each clearly signaled with their content and gated by "Load only the reference needed," matching the score-5 anchor for clear overview with well-signaled navigation.

5 / 5

Total

17

/

20

Passed

Description

87%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 specific, well-triggered, and complete, clearly stating both what the skill does and when to use it with a distinct cs-* niche. It is concise and avoids fluff or over-claims.

DimensionReasoningScore

Specificity

Names the domain and lists several concrete actions — "creating, refactoring, simplifying, or reviewing" and "Produces a thin harness, an explicit context plan, evidence gates, and an optional agent collaboration contract" — with only minor coverage gaps, fitting the score-4 anchor rather than the fully comprehensive 5.

4 / 5

Completeness

Explicitly answers both what ("CodeStable skill authoring and evolution protocol" producing named artifacts) and when ("Use when creating, refactoring, simplifying, or reviewing cs-* skills..."), plus a negative boundary, matching the score-5 anchor.

5 / 5

Trigger Term Quality

"Use when creating, refactoring, simplifying, or reviewing cs-* skills under plugins/codestable/skills or .claude/skills" gives good natural keyword coverage including path locations, missing only a few common synonyms, so 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

Scoped to cs-* skills under specific paths and explicitly distinguished from eval-cs-skill and product implementation, giving a clear niche with minimal conflict risk.

5 / 5

Total

18

/

20

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.