CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

78

Quality

98%

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

96%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.

The body is a tight, actionable playbook with a clear sequenced workflow and validation checkpoints; the only minor gap is progressive-disclosure organization, where some edge-case guidance could be separated to streamline the primary flow.

Suggestions

Consider moving the 'Narrow-feature note' and 'Blocking direction' edge-case guidance into a short reference block or details section so the core 5-step flow reads cleanly for the common multi-layer case.

Add a one-line acceptance criterion to the issue template reminding the author that AFK issues should be mergeable without human review, to reinforce the HITL/AFK distinction at creation time.

DimensionReasoningScore

Conciseness

Lean and dense throughout: no explanation of what a PRD or tracer bullet is, just actionable repo-specific conventions (issues/NNN layout, lane splits, blocking direction) that Claude would not already know. Every section earns its tokens.

5 / 5

Actionability

Fully executable guidance—exact filenames, a copy-ready issue template, explicit do-nots ('Do NOT use gh issue create'), a quiz checklist, and concrete 2-issue shape patterns with named examples—covers the common cases directly.

5 / 5

Workflow Clarity

Five clearly sequenced steps with an explicit feedback loop ('Iterate until approved') and a checkpoint for batch file creation (create in dependency order so Blocked-by references resolve to real filenames), plus an AFK fallback branch.

5 / 5

Progressive Disclosure

Well-organized into numbered process steps with a clearly signaled inline issue template; no external references are needed, though the dense narrow-feature and blocking-direction guidance is inlined where a short reference could keep the main flow tighter.

4 / 5

Total

19

/

20

Passed

Description

100%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.

The description is exemplary: third-person voice, concrete actions, explicit when/trigger guidance, and a clear negative boundary against the sibling skill. It hits the top anchor on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—read a PRD, break it into vertical-slice tracer-bullet issues written to issues/NNN-short-title.md, and tag each HITL or AFK—giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (break a PRD into tagged vertical-slice issue files) and 'when' ('Use when a PRD exists and needs to become work tickets', with concrete triggers), and adds a negative boundary excluding PRD authoring.

5 / 5

Trigger Term Quality

Provides natural trigger phrases users would actually say ('break this PRD into issues', 'turn this spec into tickets') plus the slash command, with synonyms spanning PRD/spec and issues/tickets.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche as step 2 of a named pipeline (write-a-prd → prd-to-issues → work-issues) and explicitly excludes the adjacent write-a-prd case, minimizing wrong-skill triggering.

5 / 5

Total

20

/

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.