ai-toolkit-rules
Mandatory engineering, security, testing, git, performance, quality, and response rules.…
Splits a PRD into vertical-slice GitHub issues with HITL/AFK tagging and dependencies. Triggers: PRD to issues, create tickets, break down PRD, work items.
$ npx -y skills add softspark/ai-toolkit --skill prd-to-issues --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/prd-to-issuesContext preview
The summary Claude sees to decide when to auto-load this skill.
Splits a PRD into vertical-slice GitHub issues with HITL/AFK tagging and dependencies. Triggers: PRD to issues, create tickets, break down PRD, work items.
name: prd-to-issues description: "Splits a PRD into vertical-slice GitHub issues with HITL/AFK tagging and dependencies. Triggers: PRD to issues, create tickets, break down PRD, work items." effort: medium disable-model-invocation: true argument-hint: "[PRD issue number]" allowed-tools: Read, Grep, Glob, Bash
$ARGUMENTS
Break a PRD into independently-grabbable GitHub issues using vertical slices (tracer bullets).
/prd-to-issues [PRD issue number]
1. **Fetches** PRD from GitHub issue 2. **Explores** codebase for context 3. **Drafts** vertical slices with HITL/AFK classification 4. **Quizzes** user on breakdown 5. **Creates** GitHub issues in dependency order via `gh issue create`
Fetch with `gh issue view <number>` (with comments). If no number provided, ask.
Each issue is a thin vertical slice cutting through ALL layers end-to-end.
| Classification | Description | |---------------|-------------| | **AFK** | Can be implemented and merged without human interaction (prefer) | | **HITL** | Requires human decision — architectural choice, design review, etc. |
Present as numbered list. For each slice show:
Ask:
Iterate until approved.
Create in dependency order (blockers first) so real issue numbers can be referenced.
Use `gh issue create` with the template below for each slice.
<issue-template>
#{prd-issue-number}
Concise description of this vertical slice. End-to-end behavior, not layer-by-layer. Reference parent PRD sections, don't duplicate.
Or "None — can start immediately" if no blockers.
Reference by number from the parent PRD:
</issue-template>
AI coding toolkit with machine-enforced safety, 116 skills, 44 agents, lifecycle hooks, persona presets, opt-in plugin packs, and benchmark tooling.
Repo: softspark/ai-toolkit
Mandatory engineering, security, testing, git, performance, quality, and response rules.…
Searches past coding sessions for observations, decisions, context. Triggers: mem-search,…
Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. Triggers: a11y, accessibility, WCAG,…
Creates new specialized agents with frontmatter, tools, delegation. Triggers: new agent,…
Analyzes code quality, complexity, patterns across codebase. Triggers: quality report,…
API design: naming, versioning, pagination, idempotency, OpenAPI, error contracts and safe…