recipe-reverse-engineer
Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow
50
55%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/recipe-reverse-engineer/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 identifies a clear domain—generating PRDs and design documents from existing code—but lacks the specificity and explicit trigger guidance needed for reliable skill selection. The workflow phases mentioned (discovery, generation, verification, review) are too abstract to convey concrete capabilities, and the absence of a 'Use when...' clause significantly weakens its utility for skill matching.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'generate PRD', 'create design doc from code', 'reverse engineer requirements', 'document existing codebase', 'product requirements document'.
List specific concrete actions such as 'analyzes code structure and dependencies', 'extracts API contracts', 'generates architecture diagrams', 'produces requirement specifications'.
Include common term variations users might use: 'product requirements document', 'technical specification', 'design specification', 'tech spec', 'reverse engineer documentation'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (PRD and Design Docs from codebase) and mentions a workflow (discovery, generation, verification, review), but doesn't list specific concrete actions like 'analyze code structure', 'extract API contracts', or 'generate architecture diagrams'. | 2 / 3 |
Completeness | Describes what it does (generate PRD and Design Docs from codebase) but has no explicit 'Use when...' clause or trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also only moderately detailed, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'PRD', 'Design Docs', and 'codebase', but misses common variations users might say such as 'product requirements document', 'technical spec', 'design specification', 'reverse engineer documentation', or 'document existing code'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of PRD/Design Docs from an existing codebase is somewhat distinctive, but 'Design Docs' is broad enough to overlap with general documentation skills, and the workflow terms (discovery, generation, verification, review) are generic. | 2 / 3 |
Total | 7 / 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 excellent actionability and workflow clarity — every step has concrete agent invocations, quality gates with numeric thresholds, and explicit feedback loops. The main weaknesses are its length (could benefit from splitting Phase 2 or fullstack mode into separate files) and the lack of bundle files to support the many referenced sub-agents. The skill assumes appropriate Claude competence for orchestration patterns while providing all necessary specifics.
Suggestions
Consider splitting fullstack-mode details and/or Phase 2 into separate referenced files to improve progressive disclosure and reduce the monolithic nature of the document.
Include bundle files for referenced sub-agents (scope-discoverer, prd-creator, etc.) or at minimum a manifest listing them, so the orchestrator can verify available tools.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lengthy but most content is necessary for the complex multi-phase orchestration workflow. However, there's some redundancy — the fullstack mode patterns repeat similar invocation blocks with minor variations, and some explanations (like 'No additional discovery required') could be trimmed. The agent invocation blocks are well-structured but verbose. | 2 / 3 |
Actionability | Every step includes concrete agent invocation blocks with specific subagent_type, description, and prompt templates. Quality gates have explicit numeric thresholds (consistencyScore >= 70, verifiableClaimCount >= 20), trigger conditions are clearly enumerated, and variable passing ($STEP_N_OUTPUT) is explicit throughout. The workflow is copy-paste ready for an orchestrator agent. | 3 / 3 |
Workflow Clarity | The multi-step workflow is exceptionally well-sequenced with explicit quality gates at Steps 3 and 8, feedback loops for revision (Steps 5 and 10 with max 2 cycles), human review checkpoints, unit completion checklists, and clear error handling table. Validation is built into every phase with specific pass/fail criteria and escalation paths. | 3 / 3 |
Progressive Disclosure | The skill references external sub-agents (scope-discoverer, prd-creator, code-verifier, document-reviewer, technical-designer, technical-designer-frontend) and a 'subagents-orchestration-guide' but no bundle files are provided to verify these exist. The content is monolithic — the fullstack mode details and Phase 2 could potentially be split into separate files. The workflow overview diagram at the top helps navigation, but the document is very long for a single file. | 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.