Agent skill

Recipe Update Doc

by shinpr in shinpr/claude-code-workflows

Update existing design documents (Design Doc / PRD / ADR) with review

MITAuto-check passedDevelopment

Install Recipe Update Doc

skills CLI
$ npx skills add shinpr/claude-code-workflows --skill recipe-update-doc -a claude-code

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

GitHub CLI
$ gh skill install shinpr/claude-code-workflows recipe-update-doc --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-update-doc .claude/skills/recipe-update-doc && 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-update-doc
GitHub stars
693
Token cost
~2.4k tokens
SKILL.md length
956 words
Files
1
Skills in repo
30
Repo updated
First seen
Licence
MIT

At a glance

Update existing design documents (Design Doc / PRD / ADR) with review

  • Works in 6 steps: Target Document Identification → Document Type and Layer Determination → Change Content Clarification → …
  • Tasks that involve Architecture decision records
  • SKILL.md covers Orchestrator Definition, Workflow Overview, Scope Boundaries and Execution Flow, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Recipe Update Doc is an agent skill from shinpr/claude-code-workflows. Update existing design documents (Design Doc / PRD / ADR) with review

Its SKILL.md is about 2.4k 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 and PRD writing. 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
  • Tasks that involve PRD writing

Example prompts

  • “/recipe-update-doc”

Workflow steps

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

  1. Target Document Identification
  2. Document Type and Layer Determination
  3. Change Content Clarification
  4. Document Update
  5. Document Review
  6. Consistency Verification and Final Approval [Stop: Final approval]

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 Update Doc loads about 2.4k tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 956 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

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). 956 words, ~2,369 tokens.

Download SKILL.mdSave it as .claude/skills/recipe-update-doc/SKILL.md (or your agent's skills folder).
name
recipe-update-doc
description
Update existing design documents (Design Doc / PRD / ADR) with review
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: llm-friendly-context before writing Agent prompts, handoffs, or generated artifacts. Execute Skill: subagents-orchestration-guide before making workflow decisions, invoking agents, or resolving findings.

Context: Dedicated to updating existing design documents.

Orchestrator Definition

Core Identity: "I am an orchestrator." (see subagents-orchestration-guide skill)

Local authority gate: Make this recipe's workflow decisions and validate each returned result directly; delegate semantic deliverable production to the named specialist.

Review Resolution Gate [MANDATORY]: Resolve every actionable deliverable-review finding through subagents-orchestration-guide Review Resolution before correction or progression. Before the first finding disposition, read references/review-resolution.md from the loaded subagents-orchestration-guide skill.

Execution Gate: Complete Steps 1-6 in order, following only the branches activated by document type and review result. Advance only through each step's stated evidence, review convergence, or approval condition. Complete after the final approval gate and every applicable Completion Criterion is satisfied.

Execution Protocol:

  1. Invoke named specialists for deliverable production — pass deliverable paths between them and validate their results (see subagents-orchestration-guide "Orchestrator Execution Boundary")
  2. Execute update flow:
    • Identify target → Clarify changes → Update document → Review → Consistency check
    • Stop at the [Stop: Final approval] marker → Wait for user approval before completing
  3. Scope: Complete when the user approves completing the update

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.

CRITICAL: Execute document-reviewer — it is the quality gate for document accuracy.

Workflow Overview

Target document → change clarification
                        ↓
              technical-designer / technical-designer-frontend / prd-creator (update mode)
                        ↓ (Design Doc only)
              code-verifier → document-reviewer
                        ↓ (Design Doc only)
              design-sync → [Stop: Final approval]

Scope Boundaries

Included in this skill:

  • Existing document identification and selection
  • Change content clarification
  • Document update with appropriate agent (update mode)
  • Document review with document-reviewer
  • Consistency verification with design-sync (Design Doc only)

Out of scope (redirect to appropriate skills):

  • New requirement analysis
  • Work planning or implementation

Responsibility Boundary: This skill completes when the user approves completing the update.

Target document: $ARGUMENTS

Execution Flow

Step 1: Target Document Identification

Discover the existing documents under docs/design/, docs/prd/, and docs/adr/.

Decision flow:

SituationAction
$ARGUMENTS specifies a pathUse specified document
$ARGUMENTS describes a topicSearch documents matching the topic
Multiple candidates foundPresent options with AskUserQuestion
No documents foundReport and end (document creation is out of scope)
Step 2: Document Type and Layer Determination

Determine type from document path, then determine the layer to select the correct update agent:

Path PatternTypeUpdate AgentNotes
docs/design/*.mdDesign Doctechnical-designer or technical-designer-frontendSee layer detection below
docs/prd/*.mdPRDprd-creator-
docs/adr/*.mdADRtechnical-designer or technical-designer-frontendSee layer detection below

Layer detection (for Design Doc and ADR): Read the document and determine its layer from content signals:

  • Frontend (→ technical-designer-frontend): Document title/scope mentions React, components, UI, frontend; or file contains component hierarchy, state management, UI interactions
  • Backend (→ technical-designer): All other cases (API, data layer, business logic, infrastructure)

ADR Update Guidance:

  • Minor changes (clarification, typo fix, small scope adjustment): Update the existing ADR file
  • Major changes (decision reversal, significant scope change): Create a new ADR that supersedes the original
Step 3: Change Content Clarification

Determine which sections need updating, the reason for the change, and the expected outcome after the update. Derive them from the request and the target document. Use AskUserQuestion only for an item the request and document leave undetermined, and only when a different answer would change which sections are updated or what the update must achieve.

Pass the resulting items, covered sections, and any stated total size budget to update or revision agents. Before the next approval gate, map every diff hunk to an approved item or required consistency update. Remove accidental unmapped changes; when a necessary change would alter the requested document outcome or explicit size constraint, return to the request clarification gate.

Show full SKILL.md (381 more words)Show less
Step 4: Document Update

Invoke the update agent determined in Step 2:

subagent_type: [Update Agent from Step 2]
description: "Update [Type from Step 2]"
prompt: |
  Operation Mode: update
  Existing Document: [path from Step 1]

  ## Changes Required
  [Step 3 statements for the sections to update, reason, and expected outcome, copied verbatim]

  Update the document to reflect the specified changes.
  Add change history entry.
Step 5: Document Review

For Design Doc updates only: Before document-reviewer, invoke code-verifier:

subagent_type: code-verifier
description: "Verify updated Design Doc"
prompt: |
  doc_type: design-doc
  document_path: [path from Step 1]
  Verify the updated Design Doc against current codebase.

  Verification focus: Pay special attention to literal identifier referential
  integrity in the updated sections (paths, endpoints, type names, config keys).

Store output as: $CODE_VERIFICATION_OUTPUT

Invoke document-reviewer with the applicable exact shape:

  • Design Doc: doc_type: DesignDoc, target: [path from Step 1], review_context: update, and verification_evidence: $CODE_VERIFICATION_OUTPUT.
  • PRD: doc_type: PRD and target: [path from Step 1].
  • ADR: doc_type: ADRBatch, targets: [path from Step 1], and review_context: update.

For each type, review consistency of the changed sections and their dependent statements, governing requirements, and change history.

Store output as: $STEP_5_OUTPUT

On review result:

  • Pass → Proceed to Step 6
  • Needs revision → Apply the Review Resolution Gate. Return to Step 4 when apply findings exist, using the following prompt:
    subagent_type: [Update Agent from Step 2]
    description: "Revise [Type from Step 2]"
    prompt: |
      Operation Mode: update
      Existing Document: [path from Step 1]
    
      ## Adjudicated Review Findings
      [complete reviewer finding objects verbatim, with only their orchestrator dispositions added]
    
      Treat these findings as the complete revision scope and preserve adjacent content.
  • On re-review pass prior_feedback as [{id, disposition, reason?, evidence}]
  • All actionable findings are decline → Proceed to Step 6
Step 6: Consistency Verification and Final Approval [Stop: Final approval]

For Design Doc only, invoke design-sync first:

subagent_type: design-sync
description: "Verify consistency"
prompt: "source_design: [path from Step 1]"

When conflicts are detected, apply the Review Resolution Gate and follow its bounded verifier handoff and convergence rules, returning selected corrections to Step 4 for the owning document.

For every document type, present the updated document, the review outcome, any resolved declines, and the sync result when one ran. This is the only approval gate in the flow: wait for the user's decision before completing.

Error Handling

ErrorAction
Target document not foundReport and end (document creation is out of scope)
Sub-agent update failsLog failure, present error to user, retry once

Completion Criteria

  • Identified target document
  • Change content determined from the request, the document, or a question whose answer changed the update
  • Updated document with appropriate agent (update mode)
  • Executed code-verifier before document-reviewer (Design Doc only)
  • Executed document-reviewer and addressed feedback
  • Executed design-sync for consistency verification (Design Doc only)
  • Obtained user approval to complete the update

Output Example

Document update completed.

  • Updated document: docs/design/[document-name].md
  • Approval: user approved completing the update

When findings were declined during review, append their IDs, governing reasons, and evidence to this completion response.

© 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-update-doc of shinpr/claude-code-workflows.

Open the folder on GitHubat commit a4ecd62

Compare with similar skills

Recipe Update Doc 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 Update Doc compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Recipe Update Doc this skillshinpr/claude-code-workflows693—~2.4kAutomated safety check: PassMIT
Cabloy Spec Generationcabloy/cabloy982—~3.2kAutomated safety check: NotesMIT
Bmad Architectureaj-geddes/claude-code-bmad-skills488—~1.9kAutomated safety check: NotesCustom licence
Vibe CodingOfficeDev/microsoft-365-agents-toolkit781—~5.5kAutomated safety check: PassCustom licence
Ad ReviewCorridorTech/PoseCap224—~2.4kAutomated safety check: NotesApache-2.0
Squid Planiusztinpaul/squid203—~2.6kAutomated safety check: PassApache-2.0

Similar skills

  • A skill your agent uses to create or maintain Cabloy suite specifications under repo-specs, including PRD, SRS, PDP/WBS, acceptance planning, progress, and suite ADRs.

    982 GitHub stars~3.2k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Bmad Architecture

    aj-geddes/claude-code-bmad-skills

    Solutioning skill (Winston, the Architect). An agent skill from aj-geddes/claude-code-bmad-skills.

    488 GitHub stars~1.9k tokensUpdated 3 mo ago
    DevelopmentAuto-check: notes
  • Vibe Coding

    OfficeDev/microsoft-365-agents-toolkit

    End-to-end workflow for agent-driven changes that add or modify behavior in the toolkit packages.

    781 GitHub stars~5.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Ad Review

    CorridorTech/PoseCap

    Two-axis fresh-context code review per WORKFLOW §10. An agent skill from CorridorTech/PoseCap.

    224 GitHub stars~2.4k tokensUpdated 2 days ago
    DevelopmentAuto-check: notes
  • Squid Plan

    iusztinpaul/squid

    Turn a raw feature spec into an approved Tasks Plan — grill the spec, have the Product Architect groom draft tasks (+ optional ADR and glossary additions), then run ONE human gate that decides…

    203 GitHub stars~2.6k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Documentation Criteria

    shinpr/ai-coding-project-boilerplate

    Determines which PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires and where each is stored.

    233 GitHub stars~1.6k tokensUpdated 6 days ago
    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.

    693 GitHub stars~3.5k tokensUpdated 8 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.

    693 GitHub stars~3.9k tokensUpdated 8 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.

    693 GitHub stars~3k tokensUpdated 8 days ago
    Auto-check passed
  • Implementation Approach

    shinpr/claude-code-workflows

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

    693 GitHub stars~2.6k tokensUpdated 8 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.

    693 GitHub stars~1.1k tokensUpdated 8 days ago
    Auto-check passed
  • Subagents Orchestration Guide

    shinpr/claude-code-workflows

    Guides subagent coordination through implementation workflows.

    693 GitHub stars~9.3k tokensUpdated 8 days ago
    Auto-check passed

Questions about Recipe Update Doc

What does Recipe Update Doc do?

Update existing design documents (Design Doc / PRD / ADR) with review. Recipe Update Doc is an agent skill from shinpr/claude-code-workflows.

When should I use Recipe Update Doc?

Recipe Update Doc fits situations like: tasks that involve Architecture decision records; tasks that involve PRD writing.

How do I install Recipe Update Doc in Claude Code?

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

How do I install Recipe Update Doc in Codex?

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

Can I use Recipe Update Doc 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-update-doc -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-update-doc, .gemini/skills/recipe-update-doc, .github/skills/recipe-update-doc and .opencode/skills/recipe-update-doc in your project.

What does Recipe Update Doc need to run?

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

Does Recipe Update Doc 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 Update Doc 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 Update Doc use?

Recipe Update Doc 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 Update Doc use?

About 2.4k tokens (SKILL.md is roughly 9.5k 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 Update Doc?

Skills that share tags, products or a category with Recipe Update Doc: Cabloy Spec Generation (cabloy/cabloy, 982 stars), Bmad Architecture (aj-geddes/claude-code-bmad-skills, 488 stars), Vibe Coding (OfficeDev/microsoft-365-agents-toolkit, 781 stars) and Ad Review (CorridorTech/PoseCap, 224 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Recipe Update Doc?

shinpr (a GitHub user) maintains it in shinpr/claude-code-workflows, which has 693 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.