prd-to-plan
Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets".
94
92%
Does it follow best practices?
Impact
Pending
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 a strong skill description that clearly communicates what the skill does, how it does it (tracer-bullet vertical slices), where output goes (./plans/), and when to use it. It includes an explicit 'Use when' clause with multiple natural trigger terms. The description is concise, specific, and distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists concrete actions: turning a PRD into a multi-phase implementation plan, using tracer-bullet vertical slices, and saving as a local Markdown file in a specific directory (./plans/). These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as Markdown) and 'when' (explicit 'Use when' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'PRD', 'implementation plan', 'plan phases', 'tracer bullets', 'break down a PRD'. These cover the natural ways a user would phrase such a request. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: PRD-to-implementation-plan conversion using tracer-bullet methodology. The combination of PRD, tracer bullets, and specific output format (./plans/) makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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 efficiently guides Claude through a multi-step planning process. Its strengths are the clear sequential workflow with an explicit user feedback loop before committing output, the lean template, and the smart distinction between durable decisions and implementation details. The only minor weakness is that some steps (particularly codebase exploration) could be slightly more specific about what to look for.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No unnecessary explanations of what PRDs, tracer bullets, or vertical slices are conceptually—it jumps straight to actionable process steps. The template is lean and well-structured. | 3 / 3 |
Actionability | The process is clearly described with concrete steps and a usable template, but it's instruction-oriented rather than code-oriented. The guidance is specific (e.g., what goes in each section, the quiz step, the file naming convention), but some steps like 'explore the codebase' remain somewhat vague about what specifically to look for beyond the listed items. | 2 / 3 |
Workflow Clarity | The 6-step process is clearly sequenced with logical dependencies. Step 5 provides an explicit feedback loop (quiz the user, iterate until approved) before the destructive/final step of writing the plan file. Each step has clear entry/exit criteria. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with no need for external references, the content is well-organized with clear sections, a collapsible-style rules block, and a separate template block. The structure is easy to scan and navigate. | 3 / 3 |
Total | 11 / 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
- mattpocock/skills
- Commit
651eab0
- 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.