yc-apply
Guides a founder through the full Y Combinator batch application end-to-end. A 10-phase workflow that captures the live YC form, profiles the founders, stress-tests the idea via an embedded grill loop, runs a mandatory 5-agent parallel external research pass on the startup, drafts every form field with anti-pattern and accepted-example checks, produces founder-video bullet notes (no script), runs a final adversarial gate, generates paste-ready submission answers, unlocks an interview-prep simulator after invite, and supports reapplicant delta tracking and post-decision post-mortems. Writes a documented markdown trail under a user-chosen workspace. Use when a founder wants to prepare a YC batch application, build their founder video, drill mock YC interview questions, or reapply with delta evidence. Don't use for pitch-deck design unrelated to YC, generic startup advice without applying, or post-funding work.
What this skill does
# YC Apply
A founder-facing workflow that drives a Y Combinator batch application from blank workspace to paste-ready answers. The skill is the engine; the founder's data lives in a separate workspace they own and version. The body of this file is a dispatcher — load-bearing detail lives in `references/`. Inline content here is a tripwire, not the contract.
## Bundled Path Rule
Two distinct roots are in play and must never be confused:
- `<skill-dir>` — the directory that contains this `SKILL.md` (the bundled engine: `references/`, `assets/`, `scripts/`). Resolve it once at the start of a session (e.g. the absolute path of the directory holding this file).
- `<workspace>` — the founder's external application directory (resolved per the Invocation section). All founder data is written here.
Every `references/…`, `assets/…`, and `scripts/…` path in this file is **relative to `<skill-dir>`, never to `<workspace>` or the current working directory**. Because the agent often runs shell commands with the CWD set to `<workspace>`, always expand bundled helpers to an absolute path before invoking them: write `<skill-dir>/scripts/bootstrap-workspace.sh <workspace>`, not bare `scripts/bootstrap-workspace.sh`. The same applies to reading bundled files: read `<skill-dir>/references/partner-signals.md`. When a row or step below says `scripts/X` or `references/X`, treat it as `<skill-dir>/scripts/X` / `<skill-dir>/references/X`.
## Required Reading Router
Match the phase you are running to the row. Read the listed file in full **before** producing any output for that phase. The reference is load-bearing; the inline summaries in this SKILL.md are tripwires only.
| Phase / Trigger | MUST read |
| ------------------------------------------------------------ | ----------------------------------------------- |
| Any phase (background context on what YC partners look for) | `references/partner-signals.md` |
| Phase 2 idea-stress-test, Phase 4 drafting any high-stakes field | `references/seven-pitch-questions.md` |
| Phase 4 drafts of any field, Phase 6 final adversarial gate | `references/anti-patterns.md` |
| Phase 4 drafting (every high-stakes field) | `references/accepted-examples.md` |
| Phase 5 founder-video | `references/video-spec.md` |
| Phase 8 interview-prep | `references/interview-playbook.md` |
| Phase 0 detects reapplicant, Phase 4 "what changed" draft, Phase 9 post-mortem | `references/reapplicant-playbook.md` |
## Reference Index
- `references/partner-signals.md` — what YC partners explicitly look for in written answers, the founder video, and the interview. The "20-second skim" reader model, the Dalton story-shape heuristic, Sam Altman's four evaluation questions.
- `references/seven-pitch-questions.md` — Michael Seibel's Seven Pitch Questions, Jared Friedman's Idea Quality Score, the Email Test. The pre-flight checklist every founder must pass before drafting.
- `references/anti-patterns.md` — buzzword list, Catherine Cross's 10-item "never say" list, behavioral red flags. Used by `scripts/buzzword-scan.sh` and by every grill loop.
- `references/accepted-examples.md` — verbatim accepted answers and videos: Anja Health W22, Embark Trucks W16, Hera (4-attempt case), Static EV (reapp case), Nalify S25, Razorpay. Reference rubric, never invent.
- `references/video-spec.md` — the founder-video rules (≤60s, all founders on camera, bullet notes not script, splice OK), full accepted-video transcripts.
- `references/interview-playbook.md` — 10-minute interview signals, inverted-pyramid rule, "I don't like your idea" adversarial probe, mock-interview format, demo-readiness, co-founder choreography.
- `references/reapplicant-playbook.md` — delta-doc pattern, how to surface "what changed since last application," explicit feedback-engagement rule.
## Invocation
Founder calls `/yc-apply` with optional flags. The skill autodetects state and resumes where it left off.
```
/yc-apply # autodetect: workspace + phase
/yc-apply --new # bootstrap fresh workspace
/yc-apply --workspace ~/apps/acme # explicit path override
/yc-apply --phase 4 # jump to phase
/yc-apply --resume ~/apps/acme # resume specific workspace
/yc-apply --force-submit # bypass Phase 6 gate (logs warning)
```
Workspace resolution order:
1. `--workspace` flag.
2. `$YC_APPLY_WORKSPACE` env var.
3. Current working directory if it contains `00_meta.md`.
4. Prompt the founder to choose: bootstrap new, resume by path, or cancel.
## Workspace Layout
The skill is the engine; the workspace is the artifact. The founder owns and may version the workspace. Bootstrap creates this exact tree.
```
<workspace>/
├── 00_meta.md # batch, deadline, company-slug, status
├── 01_form-spec.md # canonical form (operated on, never bundled)
├── 02_founder-profile.md # founders, cool-things, hardest-built
├── 03_idea-narrative.md # Seven Pitch Questions + Idea Quality Score + Email Test
├── 04_research/ # 5-agent parallel external research
│ ├── 01_founder-footprint.md
│ ├── 02_competitive-landscape.md
│ ├── 03_market-tam.md
│ ├── 04_regulatory-context.md
│ ├── 05_traction-signals.md
│ └── summary.md
├── 04_reapplicant-delta.md # only if Phase 0 marked reapplicant
├── 05_drafts/ # one .md per form field, versioned
├── 06_video/
│ ├── notes.md # bullet talking notes (always)
│ └── script.md # only if founder explicitly opts in
├── 06_gate.md # Phase 6 result: the 10 checks + RESULT: PASS|FORCE-SUBMIT
├── 07_interview/ # only after invite (Phase 8)
├── 08_final/ # paste-ready locked answers
├── 09_journal.md # milestone log
└── 10_post-mortem.md # only after rejection (Phase 9)
```
## Phase Map
Ten phases, idempotent. The skill detects the current phase from workspace state via `<skill-dir>/scripts/phase-status.sh` and offers to resume there.
| # | Phase | Definition of done |
|---|----------------------|----------------------------------------------------------------------------------------------------------|
| 0 | bootstrap | Workspace exists; `00_meta.md` has real `batch`/`company_slug`/`target_deadline`/`reapplicant` values (no `{{}}`); `01_form-spec.md` captured. |
| 1 | founder-profile | Every founder has cool-things + hardest-thing-built logged; no `{{}}` left; named versioned section; grill loops journaled. |
| 2 | idea-stress-test | Seven Pitch Questions answered; numeric Idea Quality Score ≥6/10 avg w/ weakest dim addressed; Email Test logged.|
| 3 | external-research | All 5 slice files + `04_research/summary.md` present; each slice has a Findings section and ≥1 real URL. |
| 4 | drafts | A draft per high-stakes field in `05_drafts/` (count ≥ `[HIGH]` fields); fields grilled; coding-agent session staged. |
| 5 | founder-video | `06_video/notes.md` exists; estimated ≤60s; founders named with credentials. |
| 6 | pre-submit-gate | `06_gate.md` written with all 10 boxes `[x]` and `RESULT: PASS` (or `FORCE-SUBMIT`); final adversarial grill logged. |
| 7 | submission-pack | Gate passed; `08_final/SUBMIT.md` populated with paste-ready answers. |
| 8 | interview-prep | Unlocked only after operator confirms interview invite. Mock drills journaled. 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.