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".
80
100%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines what the skill does, when to use it, and critically, when NOT to use it. The explicit pipeline positioning and boundary-setting with related skills (prd-to-issues, work-issues) make it highly distinctive. The inclusion of multiple natural trigger phrases and the third-person voice round out a strong description.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists concrete actions: 'Interview the user', 'produce issues/prd.md from a client brief, feature idea, or rough request'. Also specifies the output artifact and its place in a pipeline ('Step 1 of the build pipeline'). Clearly states what it does NOT do, adding further specificity. | 3 / 3 |
Completeness | Clearly answers 'what' (interview user and produce prd.md from briefs/ideas) and 'when' ('Use when no PRD exists yet and one is needed'). Also includes explicit NOT-when guidance to prevent misuse, and lists explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: '/write-a-prd', 'write a PRD', 'draft a spec', 'turn this brief into a PRD', plus contextual terms like 'client brief', 'feature idea', 'rough request'. Good coverage of natural language variations. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly distinguishes itself from related skills ('NOT for breaking an existing PRD into tasks (use prd-to-issues)', 'NOT for tracker-coupled output'). Names its position in a pipeline and specifies 'local markdown only', making it very unlikely to conflict with adjacent skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that is concise, actionable, and clearly structured. It provides a complete workflow from safety check through interview to output, with a concrete template that defines the expected deliverable. The instruction to skip unnecessary steps and the explicit guard against overwriting existing files show thoughtful design for real-world usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No unnecessary explanations of what a PRD is or how markdown works. The template is essential reference material, not padding. Instructions are terse and assume Claude's competence (e.g., 'Skip steps you judge unnecessary'). | 3 / 3 |
Actionability | Provides a concrete, step-by-step process with a complete PRD template including section headers, formatting conventions, and an example user story. The output path (`issues/prd.md`) is explicit, and the safety check in step 0 is specific and actionable. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced with a logical flow: check existing → gather input → explore repo → interview → design modules → write PRD. Step 0 includes an explicit validation/safety checkpoint (don't overwrite existing PRD) with clear recovery options. The 'Next' section provides pipeline continuity. | 3 / 3 |
Progressive Disclosure | The skill is appropriately self-contained for its scope. The PRD template is inline (correctly, since it's the core deliverable), and the 'Next' section cleanly points to the next pipeline step (`prd-to-issues`) without deep nesting. No bundle files are needed for this interview-driven skill. | 3 / 3 |
Total | 12 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- belchman/claude-skills
- Commit
be88d6c
- 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.