ai-toolkit-rules
Mandatory engineering, security, testing, git, performance, quality, and response rules.…
Converts PRD into phased plan via tracer-bullet vertical slices. Triggers: PRD to plan, break down PRD, implementation plan, tracer bullets, phased plan.
$ npx -y skills add softspark/ai-toolkit --skill prd-to-plan --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/prd-to-planContext preview
The summary Claude sees to decide when to auto-load this skill.
Converts PRD into phased plan via tracer-bullet vertical slices. Triggers: PRD to plan, break down PRD, implementation plan, tracer bullets, phased plan.
name: prd-to-plan description: "Converts PRD into phased plan via tracer-bullet vertical slices. Triggers: PRD to plan, break down PRD, implementation plan, tracer bullets, phased plan." user-invocable: true effort: high argument-hint: "[PRD issue number or paste PRD]" allowed-tools: Read, Grep, Glob, Bash, Agent
$ARGUMENTS
Break a PRD into a phased implementation plan using vertical slices (tracer bullets). Output is a Markdown file in `./plans/`.
/prd-to-plan [PRD issue number or description]
1. **Loads** the PRD (from GitHub issue or conversation) 2. **Explores** the codebase to understand architecture 3. **Identifies** durable architectural decisions 4. **Drafts** vertical slices (tracer bullets) 5. **Quizzes** user on granularity 6. **Writes** plan file to `./plans/`
If not provided, ask for the PRD GitHub issue number or content. Fetch with `gh issue view <number>` if needed.
Use Agent (subagent_type=Explore) to understand current architecture, existing patterns, and integration layers.
Before slicing, identify decisions unlikely to change:
Break PRD into **tracer bullet** phases. Each phase is a thin vertical slice cutting through ALL layers end-to-end.
| Rule | Description | |------|-------------| | Complete path | Each slice delivers narrow but COMPLETE path through every layer (schema, API, UI, tests) | | Demoable | A completed slice is demoable or verifiable on its own | | Thin over thick | Prefer many thin slices over few thick ones | | Durable | Do NOT include file names, function names, or implementation details likely to change | | Include decisions | DO include durable decisions: route paths, schema shapes, data model names |
Present breakdown as numbered list. For each phase show:
Ask:
Iterate until approved.
Create `./plans/` if needed. Write as `./plans/{feature-name}.md`.
# Plan: {Feature Name}
> Source PRD: #{issue-number}
## Architectural Decisions
Durable decisions that apply across all phases:
- **Routes**: ...
- **Schema**: ...
- **Key models**: ...
---
## Phase 1: {Title}
**User stories**: {list from PRD}
### What to build
Concise description of this vertical slice. End-to-end behavior, not layer-by-layer.
### Acceptance criteria
- [ ] Criterion 1
- [ ] Criterion 2
---
## Phase 2: {Title}
(repeat for each phase)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…