grill
This skill should be used when the user says "grill me", "grill with docs", "stress-test this plan", "interview me", "interrogate this design", "poke holes in this", "am I missing anything", or wants to align on what to build before building it. Interviews the user one question at a time until every branch of the design tree is resolved, challenging the plan against the repo's domain glossary (CONTEXT.md) and recorded decisions (docs/adr/). Sharpens terminology and maintains the glossary inline. Front door to the PEP workflow.
What this skill does
# Grill
Close the gap between what the user wants and what the agent thinks they want.
The fix is interrogation: walk down each branch of the design tree, resolving
dependencies one decision at a time, until you reach shared understanding.
This is the intake step before planning. When the grilling is done, offer to
hand off to the PEP workflow (the resolved questions become the PEP's Context
and Open Questions, pre-grilled).
## How to interview
1. **One question at a time.** Ask, wait for the answer, then ask the next.
Never batch questions. A wall of questions gets a wall of half-answers.
2. **Recommend an answer with every question.** Don't just ask "how should
auth work?" Ask, then give your recommended answer and why. The user
corrects faster than they specify from scratch.
3. **Explore the codebase instead of asking when you can.** If a question is
answerable by reading code, read it. Only ask the user things the code
can't tell you (intent, trade-offs, priorities, constraints not in the
repo).
4. **Resolve dependencies in order.** Decisions depend on each other. Resolve
the upstream one before the downstream one, or you'll re-litigate.
5. **Stop when the tree is resolved**, not when you run out of questions.
When every branch that affects the build is settled, stop and summarise.
## Read the repo's documented context first
Before grilling, read what the repo already knows, so you challenge against it
rather than re-deriving it:
- `CONTEXT.md` at the repo root (the domain glossary). If a `CONTEXT-MAP.md`
exists instead, the repo has multiple contexts, infer which one applies.
- `docs/adr/` (recorded architectural decisions). Don't re-litigate decisions
already settled here, reference them.
- `agent-constraints/*.md` if present (this repo's per-repo conventions, same
files the PEP skill reads).
Files are lazy. If none exist, that's fine, create them only when you have
something to write (see below).
## During the session
**Challenge against the glossary.** When the user uses a term that conflicts
with `CONTEXT.md`, call it out: "Your glossary defines 'cancellation' as X, but
you seem to mean Y, which is it?"
**Sharpen fuzzy language.** When a term is vague or overloaded, propose a
precise canonical one: "You're saying 'account', do you mean the Customer or
the User? Those are different things."
**Discuss concrete scenarios.** When domain relationships come up, invent
specific edge-case scenarios that force the user to be precise about
boundaries.
**Cross-reference with code.** When the user states how something works, check
whether the code agrees. Surface contradictions: "Your code cancels entire
Orders, but you just said partial cancellation is possible, which is right?"
## Maintain the glossary inline
When a term resolves, update `CONTEXT.md` right then, don't batch. Use the
format in [references/glossary-and-adr.md](references/glossary-and-adr.md).
`CONTEXT.md` is a glossary and nothing else. No implementation details, no
specs, no scratch notes. Define what a term IS, not what it does. Only terms
specific to this project's domain, general programming concepts don't belong.
## Offer ADRs sparingly
Offer to record an ADR only when all three are true:
1. **Hard to reverse** — changing your mind later costs something real.
2. **Surprising without context** — a future reader will wonder "why this way?"
3. **A real trade-off** — there were genuine alternatives and you picked one
for specific reasons.
If any is missing, skip it. Format in [references/glossary-and-adr.md](references/glossary-and-adr.md).
## When the grilling is done
Summarise the resolved decision tree, then offer the handoff:
> Tree's resolved. {N decisions settled}. Want me to turn this into a PEP? The
> Context and Open Questions are already worked out, I'd draft the waves from
> here.
If the user says yes, invoke the `pep` skill in "create PEP" mode, feeding the
resolved questions as Context. If no, leave the glossary/ADR updates in place
and stop.
Related in Design
contribute
IncludedLocal-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".
architectural-analysis
IncludedUser-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).
mcp
IncludedModel 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.
react-native-skia
IncludedDesign, 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.
plaid
IncludedProduct 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".
nextjs-framer-motion-animations
IncludedAdds 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.