recipe-plan
Create work plan from design document and obtain plan approval
45
47%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/recipe-plan/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description conveys a basic idea of the skill's purpose—converting design documents into work plans and getting approval—but is too terse and lacks explicit trigger guidance. It would benefit significantly from a 'Use when...' clause, more concrete action details, and additional natural trigger terms to help Claude distinguish it from other planning or document-related skills.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to break down a design document into tasks, create an implementation plan, or needs plan approval.'
Include more natural trigger term variations such as 'implementation plan', 'task breakdown', 'project plan', 'spec', 'specification', 'technical design doc'.
Expand the 'what' portion with concrete actions, e.g., 'Parses design documents to extract requirements, generates a structured work plan with tasks and milestones, and submits the plan for approval.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names a domain (work planning from design documents) and two actions (create work plan, obtain plan approval), but lacks detail on what these actions entail concretely—e.g., how the plan is structured, what approval means, or what outputs are produced. | 2 / 3 |
Completeness | It describes what the skill does (create work plan, obtain approval) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also fairly thin, warranting a score of 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'work plan', 'design document', and 'plan approval' that users might naturally say, but misses common variations such as 'implementation plan', 'project plan', 'spec', 'specification', 'technical design', or 'task breakdown'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'design document' to 'work plan' with approval is somewhat specific, but 'work plan' and 'design document' are broad enough terms that could overlap with project management, task planning, or document processing skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured orchestration skill with clear workflow sequencing and good feedback loops for validation and approval. Its main weaknesses are moderate verbosity in places and reliance on external skills/sub-agents that aren't bundled, making it hard to verify completeness. The actionability is decent for an orchestration-style skill but leans toward description rather than fully executable guidance.
Suggestions
Tighten the prompt construction logic in Step 3 by using a concise template or table format instead of nested bullet points with conditional descriptions.
Provide links or verify bundle paths for referenced skills (subagents-orchestration-guide, acceptance-test-generator, work-planner, document-reviewer) to support progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy (e.g., restating 'Follow subagents-orchestration-guide skill' multiple times, explaining scope boundaries that could be more compact). The conditional logic in Step 3 is necessarily detailed but could be tightened. | 2 / 3 |
Actionability | Provides concrete sub-agent invocation parameters (subagent_type, prompt templates) and specific file paths, but relies heavily on external skills (subagents-orchestration-guide, acceptance-test-generator, work-planner, document-reviewer) without providing executable code or commands beyond a single ls command. The prompt construction details are specific but not fully copy-paste ready. | 2 / 3 |
Workflow Clarity | The 5-step process is clearly sequenced with explicit validation checkpoints: Step 4 includes a review loop with branching logic (needs_revision → re-invoke → re-review until approved), and Step 5 includes user approval with a change-request feedback loop. The escalation path for rejection is also defined. | 3 / 3 |
Progressive Disclosure | References external skills (subagents-orchestration-guide, acceptance-test-generator, work-planner, document-reviewer) but no bundle files are provided to verify these exist. The content is well-structured with clear sections, but the inline detail in Step 3 (conditional prompt construction) could potentially be extracted. References are one-level deep but not clearly signaled with links. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- shinpr/claude-code-workflows
- Commit
adf2e4d
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.