code-to-prd

Reverse-engineer a frontend codebase into a PRD. Usage: /code-to-prd [path]

Quality

62%

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 ./.gemini/skills/cmd-code-to-prd/SKILL.md

Quality

Content

71%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 body is lean, actionable, and sequenced as a clear four-step workflow with batch-operation validation, but progressive disclosure is weakened by a flat reference manifest and an unclear self-referential 'Phase 2 workflow' pointer.

Suggestions

Replace the flat 'Skill Reference' path list with signaled pointers, e.g. 'See prd-quality-checklist.md for PRD quality criteria' and 'See codebase_analyzer.py output schema in ...'.

Clarify or inline the 'SKILL.md Phase 2 workflow' referenced in Step 3, since this body contains no 'Phase 2' section.

Add a brief validation/error-recovery note for the analyzer script (e.g. what to do if framework detection fails) to push workflow clarity to 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete bash commands and no over-explanation of basic concepts; the only redundancy is the 'What It Does' summary overlapping the 'Steps' section, a minor instance that could be trimmed.	4 / 5
Actionability	Provides concrete, executable commands for the Analyze and Scaffold steps (python3 {skill_path}/scripts/...), with the Fill step being appropriately instructional rather than code, leaving only minor gaps versus fully copy-paste-ready coverage.	4 / 5
Workflow Clarity	A clear four-step sequence (Analyze, Scaffold, Fill, Finalize) with checkpoints (display summary in Step 1, user confirmation after each batch in Step 3), satisfying validation for the batch operation; docked from 5 for lacking an explicit error-recovery feedback loop for the analyzer script.	4 / 5
Progressive Disclosure	Sections are well organized and content is appropriately split (scripts external, workflow inline), but the 'Skill Reference' is a flat path manifest without 'See X for Y' signaling, and Step 3 references an undefined 'SKILL.md Phase 2 workflow' that is not present in this body.	3 / 5
	Total	15 / 20 Passed

Description

53%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 clearly states what the skill does in third person and carves out a distinct niche, but it lacks an explicit 'Use when...' trigger clause and offers only one concrete action with limited keyword variation.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to document or reverse-engineer a frontend app into a Product Requirements Document.'

List one or two more concrete actions (e.g. 'detects framework, routes, and APIs; scaffolds a prd/ directory') to broaden keyword coverage and specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ("frontend codebase") and one concrete action ("Reverse-engineer ... into a PRD"), but lists only a single action rather than comprehensive coverage, matching the anchor for 1-2 concrete actions.	3 / 5
Completeness	Provides a clear "what" (reverse-engineer a frontend codebase into a PRD) but the "when" is only an invocation hint ("Usage: /code-to-prd [path]") rather than an explicit trigger clause, so per the missing 'Use when...' guidance completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes relevant keywords ("frontend codebase", "PRD") a user might say, but misses common synonyms or variations, fitting the anchor for some relevant keywords without comprehensive coverage.	3 / 5
Distinctiveness Conflict Risk	The niche (frontend codebase to PRD) is specific and mostly distinct from other skills with only minor overlap risk, fitting the 'mostly distinct' anchor rather than the fully distinct anchor at 5 due to the weak trigger signaling.	4 / 5
	Total	13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/cmd-code-to-prd/SKILL.md
Commit: 19392f7

Reviewed: ~3 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.