CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-to-prd

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

55

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

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.

A well-structured, concise, and largely executable workflow with concrete commands and sensible batch checkpoints. Its main weaknesses are progressive disclosure: referenced bundle files are missing from the bundle, and the fill step defers to an undefined "Phase 2 workflow."

Suggestions

Define or inline the "Phase 2 workflow" (fields, interactions, API dependencies, page relationships) instead of pointing at an undefined section of SKILL.md.

Fix the Skill Reference paths to real, relative bundle paths (scripts/, references/) and include the referenced files in the bundle so navigation actually resolves.

Add an explicit validation step after Step 1 (e.g., confirm .code-to-prd-analysis.json exists and lists pages before scaffolding) with a fix-and-retry path to close the remaining workflow gaps.

DimensionReasoningScore

Conciseness

The body is lean with no explanations of concepts Claude already knows; minor trimmable redundancy remains — the Usage block duplicates the frontmatter argument-hint, and the "What It Does" section re-summarizes the four Steps.

4 / 5

Actionability

Steps 1, 2, and 4 provide copy-paste-ready commands with explicit output paths, and Step 3's fill loop with batching is concrete; the gap keeping it below 5 is Step 3's instruction to follow "the SKILL.md Phase 2 workflow," which is undefined/dangling in this body.

4 / 5

Workflow Clarity

A clear four-step sequence with checkpoints present: Step 1 ends in a displayed summary, Step 3 includes a batch-confirmation loop ("Ask the user to confirm after each batch"), and there is a cleanup step; minor validation gaps (no check that the analyzer output is valid before scaffolding) keep it at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

Sections are well-organized, but scored against the actual bundle: the referenced files (scripts/codebase_analyzer.py, scripts/prd_scaffolder.py, references/prd-quality-checklist.md) do not exist in the bundle, the "Skill Reference" section lists opaque repo paths instead of clear relative links, and the "Phase 2 workflow" pointer dangles — references are present but neither real nor clearly signaled (anchor 3).

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 delivers a clear, specific "what" in third person, but has no "use when" trigger guidance and a sparse keyword set (unexpanded "PRD", no synonyms). It distinguishes itself reasonably well from other skills despite the missing trigger clause.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for a PRD, product requirements document, or spec derived from an existing frontend codebase."

Expand the acronym and add synonyms in the description ("PRD (Product Requirements Document)", "spec", "requirements doc") so natural user phrasings match.

Briefly enumerate the concrete outputs (page inventory, API inventory, enum dictionary) to raise specificity from one stated action to a comprehensive capability list.

DimensionReasoningScore

Specificity

"Reverse-engineer a frontend codebase into a PRD" names the domain and one concrete action with a concrete deliverable, but only one action is stated — the PRD's contents (pages, APIs, enums) are not enumerated, so coverage is not comprehensive (anchor 3, not 4 which requires several specific actions).

3 / 5

Completeness

The "what" is clear (reverse-engineer a frontend codebase into a PRD) but the "when" is entirely absent — there is no "Use when..." clause or equivalent explicit trigger guidance, capping this dimension at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Relevant keywords exist ("frontend codebase", "PRD") but the acronym is never expanded and natural synonyms like "spec", "requirements doc", or "product requirements document" are missing; "Usage: /code-to-prd [path]" is invocation syntax, not a natural trigger term.

3 / 5

Distinctiveness Conflict Risk

"Reverse-engineer a frontend codebase into a PRD" carves a mostly distinct niche with only minor overlap risk against codebase-documentation or analysis skills; not a 5 because the thin trigger surface does not clearly differentiate it from adjacent docs-generation skills.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Revision

19392f7

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill