prd-to-issues
Read an existing PRD (typically issues/prd.md, written by write-a-prd) and break it into vertical-slice tracer-bullet issues at issues/NNN-short-title.md, tagged HITL (needs human) or AFK (autonomous). Step 2 of the build pipeline (write-a-prd → prd-to-issues → work-issues). Use when a PRD exists and needs to become work tickets. NOT for writing the PRD itself (use write-a-prd). Triggers: /prd-to-issues, "break this PRD into issues", "turn this spec into tickets".
77
96%
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 its purpose, pipeline position, and triggers. It excels at distinguishing itself from related skills (write-a-prd) with an explicit exclusion clause, provides concrete actions and file path conventions, and includes multiple natural trigger phrases users would actually say.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: reading a PRD, breaking it into vertical-slice tracer-bullet issues, placing them at specific file paths, tagging them as HITL or AFK. Also specifies the pipeline context (step 2) and references related skills. | 3 / 3 |
Completeness | Clearly answers both 'what' (reads PRD, breaks into tagged vertical-slice issues at specific paths) and 'when' (explicit 'Use when a PRD exists and needs to become work tickets') with explicit triggers and even a 'NOT for' exclusion clause. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: '/prd-to-issues', 'break this PRD into issues', 'turn this spec into tickets', plus domain terms like 'PRD', 'work tickets', 'issues'. Good coverage of variations including 'spec' and 'tickets'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in a defined pipeline. Explicitly differentiates itself from the related 'write-a-prd' skill with a 'NOT for' clause, and the specific trigger terms and pipeline position make conflicts unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%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 clearly guides Claude through breaking a PRD into vertical-slice issues. Its strengths are the concrete issue template, explicit constraints (no GitHub CLI, local files only), and the human validation loop in Step 4. The only minor weakness is that references to sibling skills (write-a-rubric, work-issues) aren't linked, and the skill could slightly benefit from a concrete example of a good vs. bad vertical slice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what PRDs, vertical slices, or tracer bullets are in excessive detail—it assumes Claude understands these concepts and focuses on the specific process and constraints. Every section earns its place. | 3 / 3 |
Actionability | The skill provides a concrete issue template, specific file naming conventions (issues/NNN-short-title.md), explicit rules about what NOT to do (no gh CLI, no GitHub issue numbers), and a clear checklist of questions to ask the user. The guidance is specific and directly executable. | 3 / 3 |
Workflow Clarity | The 5-step process is clearly sequenced with an explicit human-in-the-loop validation checkpoint (Step 4: Quiz the user) that includes specific questions to ask and an iterate-until-approved feedback loop. Dependency ordering for file creation is explicitly called out. The workflow handles the interactive nature of this task well. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and the issue template is appropriately inlined since it's core to the skill. However, the vertical-slice-rules could benefit from more examples or a reference to examples, and the 'Next' section references other skills (write-a-rubric, work-issues) without linking to them. No bundle files exist to offload content to, but the skill is borderline long enough that the issue template could potentially be a separate reference file. | 2 / 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
- 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.