agentleFS
shinprshinpr/claude-code-workflows/skills/recipe-plan/SKILL.md

recipe-plan

Skill712 starsChanged 8 months agoMITView on GitHub

Create work plan from design document and obtain plan approval

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before the first finding disposition, read references/review-resolution.md from the loaded subagents-orchestration-guide skill.

    line 21
  2. Distinctive:

    Test skeleton generation with acceptance-test-generator

    line 38
  3. Distinctive:

    Follow the planning process below:

    line 45
  4. Very specific:

    Use the Design Doc explicitly supplied in $ARGUMENTS when present

    line 50
  5. Distinctive:

    Follow subagents-orchestration-guide HC-06 for generated-path and empty-lane coverage checks

    line 56
  6. Distinctive:

    Run the Review Resolution Gate through correction re-review, its parent requirement or authority exits, and convergence, using work-planner …

    line 73
  7. Distinctive:

    Recommended: After plan approval, output the standard block below.

    line 81
  8. Distinctive:

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

    line 91

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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 the planning phase.

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 Protocol:

  1. Invoke named specialists for deliverable production — pass data between them and validate their results
  2. Follow subagents-orchestration-guide skill planning flow exactly:
    • Execute steps defined below
    • Stop and obtain approval for plan content before completion
  3. Scope: See Scope Boundaries below

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.

Acceptance-test-generator is part of this planning flow and may return no selected lanes when the Design Doc has no justified integration/E2E proof boundary.

Scope Boundaries

Included in this skill:

  • Design document selection
  • Test skeleton generation with acceptance-test-generator
  • Work plan creation with work-planner
  • Work plan review with document-reviewer
  • Plan approval obtainment

Responsibility Boundary: This skill completes when the user authorizes implementation of the reviewed plan.

Follow the planning process below:

Execution Process

Step 1: Design Document Selection

  • Use the Design Doc explicitly supplied in $ARGUMENTS when present
  • Otherwise use the only Design Doc under docs/design/ when exactly one exists
  • Report when none exist; when multiple exist, present them for selection

Step 2: Test Skeleton Generation

  • Invoke acceptance-test-generator with design_docs: [selected Design Doc path] and requirement_context as the approved PRD path named by its Requirement Convergence section, or that section's unchanged convergence record when no PRD exists
  • Follow subagents-orchestration-guide HC-06 for generated-path and empty-lane coverage checks
  • Pass every non-null generated skeleton path to the next process; treat an evidence-backed empty lane as complete for that lane and continue to the next process

Step 3: Work Plan Creation

Invoke work-planner using Agent tool:

  • subagent_type: "dev-workflows:work-planner"
  • description: "Work plan creation"
  • mode: create
  • designDoc: [selected Design Doc path]
  • prd: [approved PRD path] when one exists
  • testSkeletons: [non-null generatedFiles paths]

Step 4: Work Plan Review

Invoke document-reviewer to review the work plan:

  • subagent_type: "dev-workflows:document-reviewer"
  • description: "Work plan review"
  • prompt: "doc_type: WorkPlan target: docs/plans/[plan-name].md. Review the Work Plan's own Implementation Scope, tasks, Completion Criteria, dependencies, execution order, exact source-anchor existence, executable verification, and Review Scope. Governing Documents paths are citation sources only; keep issues limited to violations of cited obligations."
  • Run the Review Resolution Gate through correction re-review, its parent requirement or authority exits, and convergence, using work-planner in update mode for rerouted corrections. Present the plan for approval only at its convergence condition.

Step 5: Present for Approval

  • Present the reviewed work plan to the user for batch approval. If the user requests changes, re-invoke work-planner with the user's requested changes verbatim and re-run Step 4.
  • Return to the requirements gate only when the outcome, desired-future requirements, and non-goals cannot all remain true without a user choice.

Response at Completion

Recommended: After plan approval, output the standard block below.

Planning phase completed.
- Work plan: docs/plans/[plan-name].md
- Implementation authorization: granted for this task set

Please provide separate instructions for implementation.

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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.