shinpr/claude-code-workflows / dev-workflows-frontend/skills/recipe-quality-profile
recipe-quality-profile
VerifiedProposes 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.
Execute Skill: llm-friendly-context before proposing profile conditions or writing the profile. Execute Skill: coding-principles to distinguish repository-owned policy from general code-quality knowledge.
Purpose
Establish repository-specific implementation and code-review acceptance conditions with the user, then create or update docs/project-context/quality.yaml.
Requested policy change: $ARGUMENTS
Profile Contract
version: 1
review_dimensions:
- id: stable-kebab-case-id
applies_when: Observable condition that makes this repository rule relevant to a change.
pass: Observable accepted state to verify.
evidence:
- "repository/path: section, identifier, or contract"
Each dimension owns one repository-specific quality decision. applies_when limits its implementation and review surface, pass defines the accepted state, and evidence identifies why the repository owns the rule.
Authoring Flow
- Use the current working repository as the target and read its
docs/project-context/quality.yamlwhen present. For an existing profile, use the requested policy change as the update boundary; when none is supplied, ask for it and keep the profile unchanged. - Build candidates from acceptance conditions expressed or enforced by repository instructions, contributor documentation, CI, manifests and scripts, schemas and public contracts, tests, or representative implementation patterns. For an update, derive candidates only from the requested policy change and preserve unrelated dimensions.
- For each candidate, inspect supporting and contradicting evidence wherever it can change the candidate's applicability, accepted state, or repository ownership. Separate observed repository facts from policy choices that require user confirmation.
- Retain a candidate only when failing its
passcondition would change implementation acceptance and every repository fact it depends on has cited evidence. Give it the narrowest usefulapplies_when, one positive observablepasscondition, and consolidate candidates that would produce the same finding and correction. Omit a candidate when required repository evidence is unavailable and report the exact evidence needed. - Present proposed additions, changes, and removals, confirm that other dimensions remain unchanged, show the supporting and contradicting evidence, and state unresolved policy choices with their effect on implementation and review acceptance. Obtain explicit user confirmation of a proposal with no unresolved choices before writing.
- Write only the confirmed profile content. Read the result and verify version
1, unique IDs, all required fields, observable conditions, readable evidence references, and consistency with the confirmed proposal.
When no repository-specific dimension remains and no profile exists, report that repository evidence supports no profile content and leave the repository unchanged.
Result
Before confirmation, report:
- proposed additions, changes, and removals, plus the unchanged remainder;
- supporting and contradicting evidence for each modification;
- omitted candidates and the exact missing evidence;
- policy choices requiring the user's decision and their effect on implementation and review acceptance.
After confirmation, report:
- the profile path and whether it was created, updated, or left unchanged;
- dimensions added, changed, or removed;
- evidence used for each changed dimension;
- an exact validation limitation when the result could not be verified.
Completion Check
- Every retained dimension changes an implementation or review decision and cites repository or user-confirmed policy evidence
- Conditions are positive, observable, and limited by
applies_when - The profile contains repository-specific acceptance conditions only
- Supporting and contradicting evidence were compared where they could change the proposal
- The user confirmed the complete proposal before the repository write
- Dimensions outside the update boundary remain unchanged
- The written profile satisfies the Profile Contract
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 466k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 196k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |