Agent skill

Recipe Front Design

by shinpr in shinpr/claude-code-workflows

Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval

MITAuto-check passedDevelopment

Install Recipe Front Design

skills CLI
$ npx skills add shinpr/claude-code-workflows --skill recipe-front-design -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install shinpr/claude-code-workflows recipe-front-design --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/shinpr/claude-code-workflows.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/recipe-front-design .claude/skills/recipe-front-design && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
recipe-front-design
GitHub stars
694
Token cost
~3.1k tokens
SKILL.md length
1,348 words
Files
1
Skills in repo
30
Repo updated
First seen
Licence
MIT

At a glance

Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval

  • Works in 8 steps: Select the Governing Requirement Source → Collect Repository Decision Material → Determine UI Spec Applicability and… → …
  • Tasks that involve Architecture decision records
  • SKILL.md covers Outcome and Ownership, Flow, Step 1: Select the Governing… and Step 2: Collect Repository…, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Recipe Front Design is an agent skill from shinpr/claude-code-workflows. Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval

Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Architecture decision records. The repository describes itself as: Development workflows for Claude Code that keep broad exploration focused on the outcome you approved. The licence is MIT.

When your agent uses it

  • Tasks that involve Architecture decision records

Example prompts

  • “/recipe-front-design”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Select the Governing Requirement Source
  2. Collect Repository Decision Material
  3. Determine UI Spec Applicability and Resolve UI Evidence
  4. Confirm Scope and ADR Decisions
  5. Create and Approve the UI Spec
  6. Create and Approve an ADR Batch When Needed
  7. Create the Frontend Design Doc
  8. Verify, Review, and Approve

What it can do on your machine

Read from SKILL.md and the folder at commit a4ecd62. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Recipe Front Design loads about 3.1k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 1,348 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~3.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from shinpr/claude-code-workflows at commit a4ecd62, republished under its MIT licence (© shinpr). 1,348 words, ~3,074 tokens.

Download SKILL.mdSave it as .claude/skills/recipe-front-design/SKILL.md (or your agent's skills folder).
name
recipe-front-design
description
Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval
disable-model-invocation
true

Explicit User Instruction: The user explicitly instructs and authorizes every subagent call named in this recipe. Execute each applicable call when its prerequisites are met.

Execute Skill: documentation-criteria before document routing or creation. Execute Skill: llm-friendly-context before writing Agent prompts, handoffs, or generated artifacts. Execute Skill: subagents-orchestration-guide before invoking agents or resolving findings. Before the first finding disposition, read references/review-resolution.md from the loaded subagents-orchestration-guide skill.

Outcome and Ownership

Coordinate a Medium/Large frontend design from evidence to an applicable UI Spec and approved Design Doc. The user owns product requirements and exclusions; the orchestrator owns convergence readiness, Structural Scale, document routing, ADR qualification, evidence selection, and Review Resolution. Named specialists own semantic investigation and artifacts.

The frontend Design Doc always carries the complete implementation design. An ADR batch narrows qualifying technical choices; an applicable UI Spec owns UI structure and behavior that remain to be designed.

Requirements: $ARGUMENTS

Flow

text
requirement source -> codebase-analyzer -> scope/document routing confirmation [Stop]
                                               |
                             conditional UI analysis -> UI Spec review [Stop]
                                               |
                                   optional ADR batch/review [Stop]
                                               |
              Design Doc -> code-verifier/Resolution -> document-reviewer
                                               |
                               design-sync -> approval [Stop]

Use Review Resolution for every actionable finding. Wait at each [Stop] for explicit user confirmation.

At each Agent invocation below, build the prompt as a mechanical extraction: copy the named source values into the exact fields, apply only the declared serialization, then invoke immediately.

Step 1: Select the Governing Requirement Source

Use the approved PRD path when one exists. Otherwise use the confirmed requirements verbatim.

Set confirmed_requirement_context to the approved PRD path exactly. Only when no approved PRD exists, use the orchestrator-confirmed convergence record unchanged.

Step 2: Collect Repository Decision Material

Invoke dev-workflows-frontend:codebase-analyzer once for the complete confirmed scope with exactly prd_path: [approved PRD path], or requirements: [confirmed requirements verbatim] when no approved PRD exists.

Require one valid JSON result and let the analyzer discover affected paths, responsibility boundaries, and cross-layer contracts. Treat focusAreas as existing-behavior safeguards rather than requirements.

This independent discovery keeps scope and option convergence grounded in repository evidence rather than the orchestrator's unverified implementation hypothesis.

Step 3: Determine UI Spec Applicability and Resolve UI Evidence

Apply the documentation-criteria UI Spec creation condition. When it does not apply, skip UI analysis and Step 5.

When a UI Spec applies, load and apply external-resource-context only when an external resource can change the current UI direction, component contract, or verification boundary. Otherwise use external_resource_refs: [].

Ask for prototype code only when it supplies an unresolved approved UI decision or the target cannot be determined from requirements, repository UI, and recorded resources. A missing optional prototype is not a stop condition.

Invoke dev-workflows-frontend:ui-analyzer with exactly one governing source:

text
prd_path: [approved PRD path]

or, when no approved PRD exists:

text
requirements: [confirmed requirements verbatim]

Add only an existing ui_spec_path, a decision-relevant prototype_path, and selected external_resource_refs or [].

text
ui_spec_path: [existing UI Spec path]
prototype_path: [decision-relevant path]
external_resource_refs: [selected references or []]

Step 4: Confirm Scope and ADR Decisions

Execute Skill: requirement-convergence. Build and judge the convergence record from the governing requirement source, repository analysis, and applicable UI analysis.

Judge all four convergence fields. Assign cost from Step 2 structural evidence and record its unknowns; run the hearing only for fields below ready.

Determine Structural Scale from outcomes and responsibility boundaries; file count is supporting evidence only. Resolve candidate decision points against the governing source, applicable code/UI simplifications, reuse, and invalidations; applicable UI facts may support or contradict the remaining options. Apply documentation-criteria Choice and Durability filters only after this convergence and record passing points as adrDecisionPoints; an empty list is valid.

Present the requirement-convergence Scope Confirmation. Place affected responsibilities, applicable simplifications with their conditions, and qualifying ADR points or none under Decision evidence; place Structural Scale, UI Spec applicability, and the recommended document route under Workflow. Offer proceed, or correct and re-run. Ask a question only when its answer can change a convergence field, the confirmed outcome, or scope. Continue only when every convergence field is ready or weak-but-explicit. [Stop: Scope confirmation].

Step 5: Create and Approve the UI Spec

Run this step only when Step 3 determined that a UI Spec applies.

Invoke dev-workflows-frontend:ui-spec-designer with exact inputs:

text
confirmed_requirement_context: [the value fixed in Step 1]
ui_analysis: [complete Step 3 UI analyzer JSON unchanged]
codebase_analysis: [complete Step 2 codebase-analyzer JSON unchanged]
prototype_path: [decision-relevant path from Step 3 exactly, or absent]
prototype_reference_strength: [binding | reference, present with a prototype_path]
external_resource_refs: [selected Step 3 reference records unchanged, or []]

Invoke dev-workflows-frontend:document-reviewer with exact inputs: doc_type: UISpec and target as the UI Spec path returned by ui-spec-designer, unchanged. pass presents the UI Spec with issues: []; needs_revision applies Review Resolution and re-reviews after correction; rejected resolves the governing-source conflict before another review. [Stop: UI Spec approval].

Step 6: Create and Approve an ADR Batch When Needed

When adrDecisionPoints is non-empty:

  1. Route shared/backend-owned points to technical-designer first, then frontend-owned points to technical-designer-frontend. Invoke each owner with exact inputs: document_to_create: ADRBatch; confirmed_requirement_context; its ordered decision_points confirmed in Step 4, unchanged; decision_materials as the corresponding Step 2 decisionMaterials.candidateDecisionPoints objects copied unchanged in that order; and ui_spec_path only when the approved UI Spec constrains that owner's decision. Run owner batches serially so each batch allocates ADR numbers after the preceding batch exists.
  2. Collect all returned paths and invoke dev-workflows-frontend:document-reviewer once with exact inputs: doc_type: ADRBatch, targets: [all paths], and confirmed_requirement_context. The reviewer follows the approved UI Spec cited by the ADRs when it can change the decision review.
  3. Route the reviewer verdict first: pass proceeds with issues: []; needs_revision applies Review Resolution, updates one ADR per path serially, and re-reviews the complete batch; rejected resolves the governing-source conflict before another review.
  4. Present one batch decision only after a pass review. [Stop: ADR batch approval].
  5. After user approval, set every ADR status to Accepted and verify the status update.
Show full SKILL.md (491 more words)Show less

Step 7: Create the Frontend Design Doc

Create the complete frontend MVP implementation design from reviewed artifacts and unchanged repository/UI evidence; this keeps the Design Doc traceable to approved sources instead of an orchestrator-authored shadow design.

Invoke dev-workflows-frontend:technical-designer-frontend with exactly:

  • document_to_create: DesignDoc;
  • confirmed_requirement_context;
  • structural_scale;
  • applicable approved ui_spec_path exactly and selected external-resource reference records unchanged;
  • adr_paths: [accepted paths or []];
  • codebase_analysis: [complete Step 2 JSON unchanged];
  • ui_analysis: [complete Step 3 JSON unchanged; omit when absent].

The Design Doc owns the full component-to-service implementation and retains all applicable downstream safeguards.

Step 8: Verify, Review, and Approve

Keep verifier observations unchanged so corrections remain traceable to observed repository evidence instead of becoming orchestrator-authored design instructions.

Invoke dev-workflows-frontend:code-verifier with doc_type: design-doc and document_path as the Design Doc path returned by technical-designer-frontend, unchanged, to verify current premises and feasibility while treating planned behavior as intent. Apply Review Resolution before document review; send applied findings to a fresh technical-designer-frontend update invocation with Operation Mode: update, Existing Document: [Design Doc path], and correction_findings: [complete findings unchanged except for their dispositions]. The designer applies its review-triggered bounded self-verification gate for an unverified decision-changing premise; this fresh designer is the sole correction specialist and selects the evidence route. Rerun verification after an applied correction with the previous complete result, dispositions, and correction diff or paths as prior_feedback, then build one verification_evidence object from the latest result. Continue at the Review Resolution convergence condition.

Invoke dev-workflows-frontend:document-reviewer with exact inputs: doc_type: DesignDoc; target as the returned Design Doc path unchanged; review_context: creation; original user requirements unchanged as requirements_verbatim; the Step 1 confirmed_requirement_context unchanged; the same unchanged codebase_analysis and optional ui_analysis supplied to the designer; and Step 8 verification_evidence unchanged. The reviewer follows an applicable UI Spec and accepted ADR paths cited by the Design Doc only when they can change an in-scope finding.

  • pass: continue.
  • needs_revision: apply Review Resolution, update through a fresh technical-designer-frontend invocation using the existing path and complete applied findings, and rerun verification/review for the affected boundary.
  • rejected: resolve technical governing-source conflicts through Review Resolution; ask the user only when confirmed outcome, desired-future requirements, and non-goals cannot all remain true and the user must choose which changes.

Invoke dev-workflows-frontend:design-sync with source_design as the returned Design Doc path unchanged, apply Review Resolution to actionable conflicts, and report SKIPPED distinctly when only one Design Doc exists.

Present the applicable UI Spec, Design Doc, accepted ADR paths, resolved limitations/declines, and sync result. [Stop: Design approval].

Completion Criteria

  • External and prototype evidence was requested only when it controlled a current decision.
  • Scope and Structural Scale were confirmed from outcomes and responsibility boundaries.
  • ADRs exist only for points passing both filters, and the batch received one review and approval.
  • An applicable UI Spec and a complete frontend Design Doc exist regardless of ADR need.
  • Applicable existing UI behavior, contracts, assumptions, states, equivalence, and verification safeguards reached the Design Doc.
  • Review Resolution routed only needs_revision issues into correction work.
  • All stop points received explicit user confirmation.

© shinpr, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/recipe-front-design of shinpr/claude-code-workflows.

Open the folder on GitHubat commit a4ecd62

Compare with similar skills

Recipe Front Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Recipe Front Design compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Recipe Front Design this skillshinpr/claude-code-workflows694—~3.1kAutomated safety check: PassMIT
PR Design DocOpenHands/OpenHands91k—~2.4kAutomated safety check: PassMIT
Cto AdvisorIbrahim-3d/orchestrator-supaconductor3814 repos~2.4kAutomated safety check: PassMIT
Domain Modelingbrim-borium/spotify_sdk1667 repos~806Automated safety check: PassApache-2.0
Architecture DecisionDonchitos/Claude-Code-Game-Studios26k—~1.7kAutomated safety check: PassMIT
Improve Codebase Architectureywwynm/EverythingDone14415 repos~1.3kAutomated safety check: PassGPL-3.0

Similar skills

  • PR Design Doc

    OpenHands/OpenHands

    For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…

    91k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Cto Advisor

    Ibrahim-3d/orchestrator-supaconductor

    Technical leadership guidance for engineering teams, architecture decisions, and technology strategy.

    381 GitHub starsUsed in 4 repos~2.4k tokens
    DevelopmentAuto-check passed
  • Domain Modeling

    brim-borium/spotify_sdk

    Build and sharpen a project's domain model. An agent skill from brim-borium/spotify_sdk.

    166 GitHub starsUsed in 7 repos~806 tokens
    DevelopmentAuto-check passed
  • Architecture Decision

    Donchitos/Claude-Code-Game-Studios

    Create an ADR documenting a technical decision: context, alternatives considered, consequences.

    26k GitHub stars~1.7k tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Improve Codebase Architecture

    ywwynm/EverythingDone

    Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/.

    144 GitHub starsUsed in 15 repos~1.3k tokens
    DevelopmentAuto-check passed
  • Design Doc Mermaid

    SpillwaveSolutions/design-doc-mermaid

    Create Mermaid diagrams (flowchart, sequence, class, ER, state, C4, architecture) from text or source code.

    176 GitHub starsUsed in 1 repo~5.6k tokens
    DevelopmentAuto-check passed

More from shinpr/claude-code-workflows

All 30 skills in this repo
  • Integration E2E Testing

    shinpr/claude-code-workflows

    Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria.

    694 GitHub stars~3.5k tokensUpdated 9 days ago
    Auto-check passed
  • AI Development Guide

    shinpr/claude-code-workflows

    Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates.

    694 GitHub stars~3.9k tokensUpdated 9 days ago
    Auto-check passed
  • Frontend AI Guide

    shinpr/claude-code-workflows

    Applies React/TypeScript-specific technical decision criteria, anti-pattern detection, debugging, and frontend quality gates.

    694 GitHub stars~3k tokensUpdated 9 days ago
    Auto-check passed
  • Implementation Approach

    shinpr/claude-code-workflows

    Implementation strategy selection framework. An agent skill from shinpr/claude-code-workflows.

    694 GitHub stars~2.6k tokensUpdated 9 days ago
    Auto-check passed
  • Recipe Quality Profile

    shinpr/claude-code-workflows

    Proposes repository-specific quality policy for implementation and review and, after confirmation, creates or updates docs/project-context/quality.yaml.

    694 GitHub stars~1.1k tokensUpdated 9 days ago
    Auto-check passed
  • Subagents Orchestration Guide

    shinpr/claude-code-workflows

    Guides subagent coordination through implementation workflows.

    694 GitHub stars~9.3k tokensUpdated 9 days ago
    Auto-check passed

Categories

Questions about Recipe Front Design

What does Recipe Front Design do?

Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval. Recipe Front Design is an agent skill from shinpr/claude-code-workflows.

When should I use Recipe Front Design?

Recipe Front Design fits situations like: tasks that involve Architecture decision records.

How do I install Recipe Front Design in Claude Code?

Run `npx skills add shinpr/claude-code-workflows --skill recipe-front-design -a claude-code`. Or copy the skill folder (skills/recipe-front-design in shinpr/claude-code-workflows) into .claude/skills/recipe-front-design in your project. Claude Code loads it when a task matches its description.

How do I install Recipe Front Design in Codex?

Run `npx skills add shinpr/claude-code-workflows --skill recipe-front-design -a codex`. Or copy the skill folder (skills/recipe-front-design in shinpr/claude-code-workflows) into .agents/skills/recipe-front-design in your project. Codex loads it when a task matches its description.

Can I use Recipe Front Design in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shinpr/claude-code-workflows --skill recipe-front-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recipe-front-design, .gemini/skills/recipe-front-design, .github/skills/recipe-front-design and .opencode/skills/recipe-front-design in your project.

What does Recipe Front Design need to run?

SKILL.md names no scripts, command-line tools or credentials: Recipe Front Design is instructions for the agent only.

Does Recipe Front Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Recipe Front Design safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Recipe Front Design use?

Recipe Front Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Recipe Front Design use?

About 3.1k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Recipe Front Design?

Skills that share tags, products or a category with Recipe Front Design: PR Design Doc (OpenHands/OpenHands, 91k stars), Cto Advisor (Ibrahim-3d/orchestrator-supaconductor, 381 stars), Domain Modeling (brim-borium/spotify_sdk, 166 stars) and Architecture Decision (Donchitos/Claude-Code-Game-Studios, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Recipe Front Design?

shinpr (a GitHub user) maintains it in shinpr/claude-code-workflows, which has 694 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 1, 2026.

Source: shinpr/claude-code-workflows on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.