recipe-reverse-engineer

Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/recipe-reverse-engineer/SKILL.md

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-sequenced, highly actionable orchestrator workflow with strong validation checkpoints and feedback loops. Its main weakness is moderate repetition and limited use of progressive disclosure via local reference files.

Suggestions

Factor the repeated prompt boilerplate ('Document current architecture as-is...', 'Treat these findings as the complete revision scope...') into shared snippets or a reference to reduce repetition.

Move the large per-step prompt templates into a references/ file (e.g. prompts.md) and signal them one level deep to improve progressive disclosure.

Tighten recurring standard-vs-fullstack blocks by templating the shared fields once and listing only the differing fields per mode.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural instruction, but phrases like 'Document current architecture as-is. Use Unit Inventory as a completeness baseline' and 'Treat these findings as the complete revision scope and preserve adjacent content' recur across standard and fullstack modes and could be tightened.	3 / 5
Actionability	Each step provides copy-paste-ready Agent tool invocations with concrete subagent_type, description, and fully-specified prompt fields covering both standard and fullstack cases.	5 / 5
Workflow Clarity	The multi-phase workflow is clearly sequenced with explicit Quality Gates and Verification gates, feedback loops (re-run verifier then reviewer after each revision), and Unit Completion checklists.	5 / 5
Progressive Disclosure	Section structure is clear, but substantial prompt-template content is inlined and the only reference (references/review-resolution.md) belongs to an external skill rather than this bundle; no bundle files exist to offload detail.	3 / 5
	Total	16 / 20 Passed

Description

58%Weight 40%Scale 1-5

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 clear, specific capability but omits explicit trigger guidance, which limits its completeness and trigger-term quality. It is reasonably distinct from other skills.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when reverse-engineering a PRD or Design Docs from an existing codebase'.

Include common user phrasings/synonyms such as 'reverse-engineer', 'document existing code', or 'generate specs from code'.

Consider naming the output artifacts explicitly (e.g. 'Product Requirements Document') so non-PRD-familiar users still match.

Dimension	Reasoning	Score
Specificity	Names the domain ('PRD and Design Docs from existing codebase') and lists several concrete actions including the discovery/generation/verification/review workflow phases, with only minor coverage gaps.	4 / 5
Completeness	It clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords like 'PRD', 'Design Docs', and 'codebase' are present, but it leans technical and misses common natural variations or synonyms a user might say (e.g. 'reverse-engineer', 'documentation').	3 / 5
Distinctiveness Conflict Risk	The PRD-and-Design-Docs-from-codebase niche is fairly distinct with minimal overlap risk against general doc skills, though 'generate docs from code' could brush against related documentation skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: shinpr/claude-code-workflows
Path: skills/recipe-reverse-engineer/SKILL.md
Commit: 83cf695

Reviewed: about 22 hours ago

Table of Contents

Discovery Implementation Validation

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.