CtrlK
BlogDocsLog inGet started
Tessl Logo

write-a-prd

Interview the user and produce issues/prd.md from a client brief, feature idea, or rough request. Step 1 of the build pipeline (write-a-prd → prd-to-issues → work-issues). Use when no PRD exists yet and one is needed. NOT for breaking an existing PRD into tasks (use prd-to-issues), and NOT for tracker-coupled output (this writes local markdown only). Triggers: /write-a-prd, "write a PRD", "draft a spec", "turn this brief into a PRD".

71

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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, actionable instruction skill with a clear sequenced workflow and an explicit guardrail against overwriting an existing PRD. The inlined PRD template is appropriately kept inline given the skill's modest size, and the AFK fallback handles the headless case thoughtfully.

Suggestions

Add a brief explicit validation/verification checkpoint after writing the PRD (e.g., re-read issues/prd.md to confirm every section is populated) to push workflow_clarity toward 5.

Tighten the AFK fallback bullet on Assumptions by leading with the rule ('one falsifiable bullet per silent decision') and demoting the lengthy rationale, which would lift conciseness without losing the key instruction.

DimensionReasoningScore

Conciseness

Lean, directive prose that assumes competence ('Interview the user relentlessly', 'Walk each branch of the design tree') with no padding about concepts Claude already knows; the dense AFK fallback is justified by genuine conditional complexity rather than verbosity, leaving only minor trims possible.

4 / 5

Actionability

Concrete actionable guidance with specific paths (issues/prd.md), exact section labels (## Assumptions), and falsifiable-claim formatting rules; it is instruction-only rather than code-bearing, but the guidance is mostly executable with only minor gaps.

4 / 5

Workflow Clarity

A clearly numbered 0–5 sequence with an explicit validation checkpoint at step 0 (check for existing PRD, never silently clobber) and branching AFK-fallback logic; not as elaborately staged with feedback loops as the 5-anchor, and not a destructive/batch operation that would impose a cap.

4 / 5

Progressive Disclosure

A self-contained ~82-line skill under the simple-skill threshold with no bundle files, well-organized sections, and a clearly delimited inlined template — matching the simple-skill allowance for a top score on progressive disclosure.

5 / 5

Total

17

/

20

Passed

Description

95%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.

A strong, well-scoped description that crisply states what the skill does, when to use it, when not to use it, and supplies natural trigger phrases. Only specificity falls short of full marks, where the action list is thorough but could enumerate output artifacts more comprehensively.

DimensionReasoningScore

Specificity

Names several concrete actions ('Interview the user and produce issues/prd.md', 'Explore the repo to verify', 'Sketch the major modules', 'Write the PRD'), with only minor coverage gaps versus the comprehensive 5-anchor.

4 / 5

Completeness

Explicitly answers both what ('Interview the user and produce issues/prd.md from a client brief') and when ('Use when no PRD exists yet and one is needed') with concrete trigger phrases and explicit anti-triggers.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrasings — 'write a PRD', 'draft a spec', 'turn this brief into a PRD', plus the /write-a-prd slash command — match the synonyms-and-variations benchmark of the 5-anchor.

5 / 5

Distinctiveness Conflict Risk

Clear niche as step 1 of a named pipeline with explicit boundary disambiguation ('NOT for breaking an existing PRD... use prd-to-issues'), giving minimal conflict risk per the 5-anchor.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
belchman/claude-skills
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.