From shinpr-claude-code-workflows
Creates a work plan from a design document, generates test skeletons, and obtains plan approval via sub-agent orchestration.
How this skill is triggered — by the user, by Claude, or both
Slash command
/shinpr-claude-code-workflows:recipe-planThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Execute Skill: llm-friendly-context before writing Agent prompts, handoffs, or generated artifacts.
Execute Skill: llm-friendly-context before writing Agent prompts, handoffs, or generated artifacts.
Context: Dedicated to the planning phase.
Core Identity: "I am an orchestrator." (see subagents-orchestration-guide skill)
Execution Protocol:
CRITICAL: When the user requests test generation, always execute acceptance-test-generator first — it provides the test skeleton that work-planner depends on.
Included in this skill:
Responsibility Boundary: This skill completes with work plan approval.
Follow the planning process below:
! ls -la docs/design/*.md | head -10
Invoke work-planner using Agent tool:
subagent_type: "dev-workflows:work-planner"
description: "Work plan creation"
If test skeletons were generated in Step 2, build the prompt by listing every lane's status:
fixtureE2e, serviceE2e):
generatedFiles.<lane> is not null: "[lane] test file: [path]"generatedFiles.<lane> is null: "No [lane] skeleton generated (reason: [e2eAbsenceReason.])"If test skeletons were not generated:
prompt: "Create work plan from Design Doc at [path]."
Follow subagents-orchestration-guide Prompt Construction Rule for additional prompt parameters
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 semantic traceability to the Design Doc, early verification placement, real-boundary verification coverage, Failure Mode Checklist, and Review Scope."verdict.decision: on needs_revision, re-invoke work-planner in update mode with the findings and re-review, repeating until approved or approved_with_conditions. On rejected, escalate to the user.Recommended: After plan approval, output the standard block below.
Planning phase completed.
- Work plan: docs/plans/[plan-name].md
- Status: Approved
Please provide separate instructions for implementation.
When the approved plan includes E2E test skeletons or references commands/interfaces it will newly create, append one more line as the final line of the response (omit it otherwise):
Optional preflight: `/recipe-prepare-implementation docs/plans/[plan-name].md` verifies these are implementable before build (exits no-op if all resolve).
npx claudepluginhub shinpr/claude-code-workflowsCreates structured implementation plans for multi-step tasks from specs or requirements. Generates plan.json and task markdown files with explicit code and testing steps.
Generates implementation plans from completed designs with file paths, code examples, tests, verification steps for engineers lacking codebase context.
Writes executable plan documents for multi-step implementation tasks, defining task dependencies and file modifications. Use when scope is clear and work requires sequenced execution.