craft-spec
Turn messy ideas into a clear, structured PRD. Use when you have rough notes, Slack threads, or half-formed ideas that need to become a product requirements document.
73
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./product-skills/skills/craft-spec/SKILL.mdQuality
Discovery
89%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 a well-crafted description that clearly communicates both purpose and trigger conditions. It includes an explicit 'Use when' clause with natural, relatable input scenarios. The main weakness is that the specific capabilities could be more detailed—listing concrete actions like defining user stories, acceptance criteria, or prioritization would strengthen it further.
Suggestions
Add 2-3 more specific concrete actions to boost specificity, e.g., 'Defines user stories, acceptance criteria, scope, and prioritization from messy ideas.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (PRD creation) and describes the core action ('Turn messy ideas into a clear, structured PRD'), but doesn't list multiple specific concrete actions like outlining sections, defining user stories, specifying acceptance criteria, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (turn messy ideas into a structured PRD) and 'when' (explicit 'Use when' clause specifying rough notes, Slack threads, or half-formed ideas needing to become a PRD). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'PRD', 'rough notes', 'Slack threads', 'half-formed ideas', 'product requirements document'. These cover multiple realistic user scenarios and phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche around PRD creation from unstructured inputs. The specific mention of PRDs, rough notes, and Slack threads makes it unlikely to conflict with general writing or documentation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
44%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a usable prompt template for PRD generation but lacks depth in actionability and workflow guidance. It would benefit significantly from an example input/output pair showing the transformation from messy notes to a structured PRD, and from a clearer iterative refinement workflow with specific checkpoints for evaluating draft quality.
Suggestions
Add a concrete example showing sample messy input (e.g., a few bullet points) and the expected PRD output, so Claude understands the quality bar for the transformation.
Define an explicit iteration workflow: e.g., 1) Generate draft PRD, 2) Review each section against a checklist (problem clarity, measurable metrics, scoped boundaries), 3) Flag weak sections, 4) Revise targeted sections.
Remove the introductory paragraph that restates the skill description — the prompt template is self-explanatory and the framing adds no new information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The intro paragraph restates what the description already says and includes some unnecessary framing ('maybe some bullet points, a Slack thread'). The prompt template itself is reasonably lean, but the surrounding prose could be tightened. The 'Tips' section adds modest value but the first tip explains something obvious. | 2 / 3 |
Actionability | It provides a concrete prompt template that can be copy-pasted, which is useful. However, this is essentially a prompt-only skill with no executable code, no example input/output pair showing what a good PRD looks like, and no concrete demonstration of the transformation from messy notes to structured PRD. The guidance remains at the template level without showing expected output quality. | 2 / 3 |
Workflow Clarity | There is no clear multi-step workflow. The tips mention 'run it once to get a draft, then iterate' but provide no structured iteration process, no validation checkpoints, and no guidance on how to evaluate or improve the draft. For a skill that involves iterative refinement, the absence of any feedback loop or sequenced steps is a significant gap. | 1 / 3 |
Progressive Disclosure | For a simple, single-purpose skill with no bundle files, the content is appropriately organized into clear sections (prompt template, tips) without unnecessary nesting or monolithic walls of text. The cross-reference to the Stakeholder Comms skill is a nice touch for discoverability. | 3 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- amplitude/builder-skills
- Commit
221ffaa
- 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.