CtrlK
BlogDocsLog inGet started
Tessl Logo

prp-prd

Interactive PRD generator - problem-first, hypothesis-driven product spec. Use when the user wants to create a PRD, write a product or feature spec, scope a new product, or invokes /prp-prd.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

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

A highly actionable, well-sequenced interactive workflow with explicit gates and copy-paste templates, but it is monolithic: the long PRD template and the redundant ASCII flow summary could be externalized or trimmed for better token efficiency and progressive disclosure.

Suggestions

Move the ~150-line PRD template (lines 232-384) into a references/prd-template.md file and link to it from Phase 7, keeping only the output-path and invocation logic inline.

Remove or compress the Question Flow Summary ASCII diagram (lines 437-465) since it duplicates the Process Overview (line 29) and the per-phase GATEs already described above.

Consider extracting the repeated Task-tool subagent prompt blocks (web-researcher, codebase-explorer, codebase-analyst) into a references/agent-prompts.md to reduce repetition across Phase 3 and Phase 5.

DimensionReasoningScore

Conciseness

The body is mostly actionable instruction rather than concept-explaining fluff, but the ASCII Question Flow Summary restates phases already detailed and the ~150-line PRD template is large; both could be tightened without losing clarity.

2 / 3

Actionability

Provides executable bash (the PRP store resolver), concrete subagent_type invocations with copy-paste prompt blocks, exact question sets, and a complete fill-in PRD template with a real output path.

3 / 3

Workflow Clarity

Eight phases are clearly sequenced with explicit GATE validation checkpoints ("Wait for user response before proceeding"), a process overview, and a flow diagram; the task is interactive rather than destructive/batch so no cap applies.

3 / 3

Progressive Disclosure

Everything lives in a single ~470-line SKILL.md with no external references, and the large inline PRD template is content that could reasonably be split into a reference file; structure is present but disclosure is flat.

2 / 3

Total

10

/

12

Passed

Description

90%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an explicit Use-when trigger clause, good natural trigger terms, and a clear niche; its only weakness is that it states a single action (generator) with approach adjectives rather than enumerating multiple concrete capabilities.

DimensionReasoningScore

Specificity

Names the domain and one concrete action ("Interactive PRD generator") plus approach adjectives ("problem-first, hypothesis-driven"), but does not enumerate multiple distinct actions like the score-3 anchor; it describes a generator rather than listing several operations.

2 / 3

Completeness

Explicitly answers both what ("Interactive PRD generator - problem-first, hypothesis-driven product spec") and when ("Use when the user wants to create a PRD...") with an explicit trigger clause.

3 / 3

Trigger Term Quality

Covers natural phrases a user would say — "create a PRD", "write a product or feature spec", "scope a new product", "invokes /prp-prd" — giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The PRD/product-spec niche and the explicit "/prp-prd" invocation give it a clear, distinct trigger set unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

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.

Validation15 / 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
Wirasm/prp
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.