recipe-reverse-engineer

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

77%

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-orchestrated, highly actionable multi-step workflow with strong sequencing, validation checkpoints, and feedback loops. Its main weaknesses are duplicated prompt structures that hurt conciseness and the absence of any progressive disclosure via separate reference files.

Suggestions

Factor the repeated subagent prompt blocks (Phase 1 vs Phase 2, standard vs fullstack) into shared parameterized templates to reduce duplication and token cost.

Extract the long per-step prompt templates into a reference file (e.g. references/prompts.md) and link to it one level deep, keeping SKILL.md as a concise orchestration overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly purposeful, but prompt blocks are duplicated across Phase 1/Phase 2 and across standard/fullstack modes; these could be factored into shared templates to tighten token use.	2 / 3
Actionability	It provides concrete subagent invocations with fully templated prompts, explicit output variables, and specific quantitative thresholds (consistencyScore >= 70, verifiableClaimCount >= 20).	3 / 3
Workflow Clarity	Steps are clearly sequenced with explicit quality gates, revision feedback loops (max 2 cycles), unit-completion checklists, and an error-handling table covering failure recovery.	3 / 3
Progressive Disclosure	The skill is a single monolithic file with no local bundle files (references/scripts/assets absent) and no one-level-deep references; it is well-sectioned but offers no progressive disclosure structure.	2 / 3
	Total	10 / 12 Passed

Description

60%

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 is specific about capabilities and domain but is missing an explicit 'when to use' trigger clause, which limits its completeness and trigger-term quality. Adding a 'Use when...' clause would raise both completeness and distinctiveness.

Suggestions

Add an explicit trigger clause such as 'Use when reverse-engineering or documenting an existing codebase, or when the user asks for PRDs/Design Docs from code.'

Include more natural trigger variations users would actually say (e.g., 'reverse engineer', 'document existing code', 'generate docs from code') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and multiple concrete actions: 'Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow'.	3 / 3
Completeness	It clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	It includes relevant domain terms ('PRD', 'Design Docs', 'codebase') but misses common natural variations like 'reverse engineer' or 'document existing code', and lacks natural trigger phrasing.	2 / 3
Distinctiveness Conflict Risk	The 'from existing codebase' framing is a recognizable niche, but the absence of explicit triggers means it could still overlap with other documentation-generation skills.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: shinpr/claude-code-workflows
Commit: 66e3b29

Reviewed: 1 day 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.