spec-dev

Included with Lifetime

$97 forever

Plan-first development workflow. Grill the idea, write one plan.md, then implement it phase by phase. Use this skill whenever the user wants to: stress-test a design, write or review an implementation plan, add or resolve review comments, track phased implementation progress, or audit open review threads. Also use when the user says things like "let's think this through", "poke holes in this", "what am I missing", "plan this out", or wants disciplined, reviewed code changes. Flow: Grill → Plan → Impl (phase by phase).

Design

What this skill does


The flow is **Grill → Plan → Impl (phase by phase)**. The only artifact is `plan.md`, which lives at `~/.agents/sessions/{project}/{date}-{feature}/plan.md` where `{project}` is the git repo name (if in a git repo) or the basename of the current working directory, `{date}` is `YYYY-MM-DD`, and `{feature}` is a short kebab-case label. That one file holds the plan, inline reviews, impl questions, and per-phase handoff notes.

## Grill

Stress-test the design before writing anything down. Read [grilling-guide.md](./references/grilling-guide.md) — interrogate one question at a time, sharpen fuzzy terms, cross-reference with code, probe reversibility.

Skip grilling when the approach is already clear — small bug fixes, straightforward changes, or work where the plan is obvious don't need interrogation.

## Plan

Write `plan.md` following [plan-template.md](./references/plan-template.md). The key principle: explain **why**, not just what. For each significant decision, cover what you decided, what alternatives you ruled out, and what tradeoffs you accepted. Break the work into phases, and give every phase an **Acceptance** block defining "done".

Inline reviews use the `> quote` + `**Review (name):**` pattern; resolve with `**Resolved:**` and update the plan text above. See [review-patterns.md](./references/review-patterns.md).

## Impl (phase by phase)

Each phase is its own catch-up → execute → verify → review-if-needed → commit → handoff cycle. Full workflow in [implementation-guide.md](./references/implementation-guide.md).

Two things to know up front:

- **Review gates** — pause for user approval after grilling (before writing the plan) and after the plan (before implementation). Within impl, don't gate every phase, but escalate on surprises or major rework.
- **Per-phase review is a judgment call** — for each phase, decide whether the work needs another pass before moving on. Trivial phases self-review; phases touching critical paths, security, data, or non-obvious logic warrant a closer look. When in doubt, review.

Impl questions raised mid-phase use the `**Question (name):**` / `**Answer:**` pattern from [review-patterns.md](./references/review-patterns.md). When an answer changes the plan, update the affected section.

## Quick reference

| Action             | What to do                                                                       | Reference                                                       |
| ------------------ | -------------------------------------------------------------------------------- | --------------------------------------------------------------- |
| Grill a design     | Interrogate one question at a time, sharpen terms, cross-reference code          | [grilling-guide.md](./references/grilling-guide.md)             |
| Write plan         | Create `~/.agents/sessions/{project}/{date}-{feature}/plan.md`                   | [plan-template.md](./references/plan-template.md)               |
| Add review         | `> quote` then `**Review (name):**`                                              | [review-patterns.md](./references/review-patterns.md)           |
| Resolve review     | `**Resolved:**` after the review block; update plan text above                   | [review-patterns.md](./references/review-patterns.md)           |
| Ask impl question  | `**Question (name):**` indented under the blocked task                           | [review-patterns.md](./references/review-patterns.md)           |
| Answer question    | `**Answer:**` directly below the question                                        | [review-patterns.md](./references/review-patterns.md)           |
| Run a phase        | Catch up on handoff → implement → verify Acceptance → review? → commit → handoff | [implementation-guide.md](./references/implementation-guide.md) |
| Check open threads | `grep -n "Review\|Resolved" plan.md` and `grep -n "Question\|Answer" plan.md`    |                                                                 |

Files: 5

Size: 19.6 KB

Complexity: 40/100

Category: Design

Source: https://github.com/vaayne/agent-kit/tree/main/skills/spec-dev

Related in Design

contribute

Included

Local-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".

Designscripts

architectural-analysis

Included

User-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).

Designscripts

mcp

Included

Model Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.

Designscripts

react-native-skia

Included

Design, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.

Designscripts

plaid

Included

Product Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".

Designscripts

nextjs-framer-motion-animations

Included

Adds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.

Designscripts