CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

recipe-quality-profile

Proposes repository-specific quality policy for implementation and review and, after confirmation, creates or updates docs/project-context/quality.yaml. Use when asked to create or update a repository quality profile.

Quality

89%

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

85%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.

A tight, self-contained instruction skill with a concrete artifact contract, an explicit confirmation gate, post-write verification, and a completion checklist. The only meaningful improvement would be a worked example of a completed dimension and light trimming of the densest flow steps.

DimensionReasoningScore

Conciseness

The body teaches nothing Claude already knows; every section is procedural policy (contract template, flow, reporting, checklist) with no padding. It is not a 5 because the explanatory sentence after the Profile Contract ("Each dimension owns one repository-specific quality decision. applies_when limits ... pass defines ... evidence identifies ...") partially restates the YAML template, and steps 4-5 are dense run-on sentences that could be tightened — anchor 4's "minor instances of over-explanation that could be trimmed".

4 / 5

Actionability

Concrete, executable guidance throughout: the exact profile path, a YAML contract with field semantics, a numbered flow that specifies how to derive candidates from repository evidence, when to ask vs. confirm, and post-write verification. Per the rubric's instruction-skill note, the absence of code is not penalized; it falls short of anchor 5 only because there is no worked example of a filled-in dimension — the contract shows placeholders ("stable-kebab-case-id") but never a real one.

4 / 5

Workflow Clarity

The Authoring Flow is a clear 6-step sequence with an explicit validation checkpoint ("Read the result and verify version 1, unique IDs, all required fields ..."), a confirmation gate before any repository write, a fallback when no dimensions remain, and a Completion Check checklist — matching anchor 5's "explicit validation steps; feedback loops ...; checklists for complex processes". The write is gated on user confirmation, so the destructive/batch cap does not apply, and validation is present regardless.

5 / 5

Progressive Disclosure

The body is ~60 lines of well-organized sections (Purpose, Profile Contract, Authoring Flow, Result, Completion Check), all of which is core process content that belongs inline; no bundle files exist or are needed, and no content is inlined that should be split out. This satisfies anchor 5 for a self-contained single-file skill under the rubric's small-skill guidance.

5 / 5

Total

18

/

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.

A strong description: third-person voice, concrete actions with an explicit output artifact, and an explicit "Use when" clause. The only gaps are a few missing natural synonyms (e.g., quality standards, review criteria) and unspecified policy internals, which keep specificity and trigger coverage at 4.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Proposes repository-specific quality policy for implementation and review", "after confirmation, creates or updates docs/project-context/quality.yaml" — including the exact artifact path. It is not a 5 because the coverage of what the policy contains is left abstract ("quality policy" internals unspecified), matching anchor 4's "several specific actions; minor gaps in coverage" rather than comprehensive coverage.

4 / 5

Completeness

It explicitly answers both questions: what ("Proposes repository-specific quality policy ... creates or updates docs/project-context/quality.yaml") and when ("Use when asked to create or update a repository quality profile") with a concrete trigger phrase, exactly matching anchor 5. Not below 5 because neither half is vague or merely implied.

5 / 5

Trigger Term Quality

Trigger terms like "quality policy", "repository quality profile", and "create or update" are natural phrases a user would say when requesting this. It is not a 5 because common synonyms such as "quality standards", "review rules", or "acceptance criteria" are absent; it clearly exceeds anchor 3's "some relevant keywords but missing common variations".

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche — a repository-specific quality profile materialized in a named artifact (docs/project-context/quality.yaml) — with triggers unlikely to fire for unrelated skills. It matches anchor 5's "clear niche with distinct triggers; minimal conflict risk"; no neighboring anchor fits better.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

shinpr/claude-code-workflows

Path

dev-workflows-frontend/skills/recipe-quality-profile/SKILL.md

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.