recipe-design
Execute from codebase analysis to design document creation
40
38%
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-design/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is extremely vague and lacks the specificity, trigger terms, and completeness needed for Claude to reliably select this skill. It reads more like a high-level category label than a functional skill description, providing no concrete actions, no explicit trigger guidance, and no distinguishing characteristics.
Suggestions
List specific concrete actions the skill performs, e.g., 'Analyzes codebase architecture, identifies component dependencies, and generates technical design documents including system diagrams, API specifications, and data flow descriptions.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to create a design doc, technical specification, architecture document, or wants to analyze code structure for documentation purposes.'
Include file types or output formats to improve distinctiveness, e.g., 'Produces markdown design documents covering system overview, component interactions, and implementation plans.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'codebase analysis' and 'design document creation' without listing any concrete actions. It doesn't specify what kind of analysis, what kind of design documents, or what steps are involved. | 1 / 3 |
Completeness | The description weakly addresses 'what' (codebase analysis to design document creation) but provides no 'when' clause or explicit trigger guidance. There is no 'Use when...' or equivalent, and the 'what' itself is too vague to be useful. | 1 / 3 |
Trigger Term Quality | The terms 'codebase analysis' and 'design document creation' are somewhat technical and not natural phrases users would say. Users are more likely to say things like 'write a design doc', 'create a technical spec', or 'analyze my code'. The description lacks common variations. | 1 / 3 |
Distinctiveness Conflict Risk | The description is very generic and could overlap with many skills related to code analysis, documentation, technical writing, or architecture. 'Codebase analysis' and 'design document' are broad enough to conflict with numerous other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
77%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 strong actionability and workflow clarity—concrete subagent invocation schemas, explicit stop points, conditional paths, and a completion checklist. Its main weaknesses are moderate verbosity (some redundancy between sections) and reliance on external subagent skills that aren't bundled, making progressive disclosure harder to fully evaluate. Overall it provides clear, executable guidance for the design phase workflow.
Suggestions
Trim the 'subagents-orchestration-guide usage' paragraph—the list of exclusions (HC-01, First Action Rule, Call Examples) is defensive detail that could be reduced to a single sentence.
Consider extracting the detailed subagent invocation prompts in Step 4 into a separate reference file to reduce the main skill's length and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but contains some redundancy—e.g., the scope boundaries section largely restates the workflow overview, and the subagents-orchestration-guide usage paragraph is verbose with its list of exclusions. Some tightening is possible without losing clarity. | 2 / 3 |
Actionability | The skill provides concrete, executable guidance: specific subagent invocation parameters (subagent_type, description, prompt templates), exact bash commands for scope bootstrap (rg/grep), structured JSON fields to populate, and precise handoff data. Each step tells Claude exactly what to do and what to pass. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced with an ASCII diagram, numbered steps, explicit [STOP] markers for user approval gates, conditional branching (ADR vs Design Doc), fallback handling (no files found, too many files), and a completion checklist. Validation is built in via code-verifier, document-reviewer, and design-sync as quality gates. | 3 / 3 |
Progressive Disclosure | The skill references external subagent skills (codebase-analyzer, technical-designer, code-verifier, document-reviewer, design-sync, subagents-orchestration-guide) but no bundle files are provided, making it impossible to verify those references. The content is well-structured with sections but is somewhat long for a single file with no supporting reference documents to offload detail into. | 2 / 3 |
Total | 10 / 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.