spirewise 1.7.1 → 1.9.0

package/skills/nvidia-inception-starter/SKILL.md

@@ -4,17 +4,19 @@ description: >-
   Expert startup advisor that prepares, evaluates, and optimizes a startup for
   acceptance into NVIDIA Inception. Use when the user asks to "assess my startup
   for NVIDIA Inception", "am I ready for NVIDIA Inception", "improve my NVIDIA
-  application", "NVIDIA Inception readiness", or wants a scored audit + roadmap.
-  Researches NVIDIA Inception and accepted startups, scores the company 0–100,
-  audits website/product/AI/architecture/NVIDIA-alignment, and writes a full
-  readiness report to an `nvidia-inception/` folder in the project root.
+  application", "  NVIDIA Inception readiness", or wants a scored audit + roadmap. Ships with a
+  baked-in NVIDIA Inception knowledge base (eligibility, benefits, accepted-startup
+  patterns, ecosystem-tech reference) so research is optional and token-cheap;
+  scores the company 0–100, audits website/product/AI/architecture/NVIDIA-alignment,
+  and writes a full readiness report to an `nvidia-inception/` folder in the project root.
 ---
 
 # NVIDIA Inception Starter
 
-Prepare a startup for NVIDIA Inception: research the program and its accepted
-companies, score the startup, audit every dimension that affects acceptance, and
-produce a brutally honest readiness report with a 90-day action plan.
+Prepare a startup for NVIDIA Inception: using a **baked-in knowledge base** of the
+program and its accepted companies (live research optional), score the startup,
+audit every dimension that affects acceptance, and produce a brutally honest
+readiness report with a 90-day action plan.
 
 ## Persona
 
@@ -37,48 +39,83 @@ Gather (ask, or infer from the repo/website/links the user provides):
 If details are missing, mark them as `[UNKNOWN]` in the report and lower the
 relevant scores — do not invent facts.
 
-## Step 1 — Research (do this before scoring)
-
-Research to current, real sources. Do not rely on memory alone.
-- **Official program:** eligibility, application process, tiers, benefits, FAQ
-  (nvidia.com/startups and the Inception FAQ).
-- **Accepted startups:** study a broad sample (aim for many, ideally 50–100+)
-  from NVIDIA startup showcases, member spotlights, case studies, and blogs.
-- For each accepted startup, note: industry, problem, market, product/AI
-  category, funding stage, tech stack, NVIDIA tech used, homepage headline,
-  value prop, traction, and competitive edge.
-- **Detect patterns:** most common categories, AI use cases, funding stages,
-  founder backgrounds, website structures, messaging, and NVIDIA-tech usage.
-- Convert patterns into **acceptance signals** (what accepted startups share)
-  and **risk signals** (what rejected/ineligible profiles share).
-
-## Verified program facts (ground truth — keep current by re-checking)
-
-Eligibility (typical):
-- **Free, equity-free, no fees.** No application deadline; rolling review
-  (usually a few business days to ~2 weeks).
+## Step 1 — Research is OPTIONAL (defaults are baked in below)
+
+A current, distilled NVIDIA Inception knowledge base is **embedded in this skill**
+(next section). **Use it as the default ground truth and do NOT browse the web for
+the basics** — this saves tokens and time. Only do live research when:
+- the user explicitly asks for the latest/verified data, or
+- the startup sits in a niche the baked-in patterns don't cover, or
+- you need a fresh accepted-startup example to cite.
+
+When you do research, confirm eligibility/benefits on nvidia.com/startups and skim
+a handful of accepted-startup spotlights; fold anything new into your analysis and
+note "verified <date>". Otherwise, proceed straight to scoring with the baked-in KB.
+
+## Baked-in NVIDIA Inception knowledge base (default ground truth)
+
+Treat the following as known facts — no research needed to use them.
+
+### Program facts & eligibility
+- **Free, equity-free, no fees.** No application deadline; rolling review (usually
+  a few business days to ~2 weeks).
 - Must be **incorporated** (registered legal entity), have a **working company
   website**, use a **business email** (no generic/alias addresses), and employ
   **at least one developer**.
 - Generally **under 10 years old**, and **building AI / ML / data-science /
   accelerated-computing products** — not selling consulting or outsourced dev.
 - **Open to all funding stages** (bootstrapped → growth).
-
-Commonly **not eligible**: consulting / outsourcing dev shops, crypto
-(mining/trading), pure cloud service providers, resellers/distributors, and
-public companies.
-
-Tiers (startups progress as they grow): **Emerging → Scale → Premier**. Higher
-tiers unlock more cloud credits, deeper engineering support, DLI training,
-co-marketing, and investor access.
-
-Benefits: NVIDIA SDKs + developer tools, Deep Learning Institute (DLI) training,
-preferred hardware pricing, partner **cloud credits**, **Inception Capital
-Connect / VC Alliance** investor access, co-marketing, badges, and events.
-
-NVIDIA technologies to align with (cite the ones that genuinely fit): CUDA,
-cuDNN, TensorRT, Triton, RAPIDS, NIM, NeMo, Riva, Metropolis, Holoscan,
-Omniverse, Isaac (robotics), Jetson (edge), DGX / NVIDIA AI Enterprise.
+- Commonly **not eligible**: consulting / outsourcing dev shops, crypto
+  (mining/trading), pure cloud service providers, resellers/distributors, and
+  public companies.
+- **Tiers:** **Emerging → Scale → Premier**. Higher tiers unlock more cloud
+  credits, deeper engineering support, DLI training, co-marketing, and investor access.
+- **Benefits:** NVIDIA SDKs + developer tools, Deep Learning Institute (DLI)
+  training, preferred hardware pricing, partner **cloud credits**, **Inception
+  Capital Connect / VC Alliance** investor access, co-marketing, badges, and events.
+
+### Accepted-startup category patterns (what members commonly build)
+Healthcare/biotech & drug discovery · Robotics & autonomy · Manufacturing/
+industrial & digital twins · Generative AI / LLM apps & infrastructure · Computer
+vision & video analytics · Agentic AI & AI copilots · Climate/energy & Earth
+modeling · Cybersecurity AI · Fintech & fraud AI · Retail/e-commerce AI · Agritech
+· Autonomous vehicles · Edge AI · Data analytics & vector/RAG platforms · Scientific
+computing/HPC.
+
+### NVIDIA ecosystem reference (tech → what it's for → recommend when)
+| NVIDIA tech | What it's for | Recommend when the startup… |
+|---|---|---|
+| CUDA / cuDNN | Core GPU compute primitives | runs any custom GPU kernels / training |
+| TensorRT | Optimized low-latency inference | needs fast/cheap production inference |
+| Triton Inference Server | Multi-model serving at scale | serves many models / high throughput |
+| RAPIDS | GPU-accelerated data science | does heavy tabular/ETL/analytics |
+| NIM | Prebuilt inference microservices | deploys LLMs/models fast in enterprise |
+| NeMo (+ Retriever, Guardrails) | Build/customize/RAG LLMs | trains, fine-tunes, or RAGs custom models |
+| Riva | Speech AI (ASR/TTS) | does voice, transcription, or speech UX |
+| Metropolis | Vision AI for cities/industry | does video analytics / smart spaces |
+| Holoscan | Real-time sensor/edge AI | does medical/industrial sensor streams |
+| Omniverse | 3D simulation & digital twins | builds digital twins / synthetic worlds |
+| Cosmos | World foundation models for Physical AI | needs world models / sim data for robots/AV |
+| Isaac (Sim/Lab/ROS, GR00T) | Robotics dev & simulation | builds robots / embodied agents |
+| Jetson | Edge AI compute | deploys AI on-device / at the edge |
+| DGX / HGX | Large-scale training clusters | trains large models / needs big compute |
+| NVIDIA AI Enterprise | Supported enterprise AI platform | sells AI into regulated enterprises |
+| Domain stacks: BioNeMo (drug discovery), Clara (healthcare), DRIVE (AV), Morpheus (cybersecurity), Earth-2 (climate), Aerial (telecom), Maxine (media) | Vertical accelerators | operates in that specific vertical |
+
+### Strategic focus areas NVIDIA is pulling toward (2024–2026)
+Physical AI & robotics · Agentic AI · Digital twins & simulation · Sovereign &
+enterprise AI · Healthcare/biotech · Manufacturing/industrial · Climate/energy ·
+Cybersecurity · Scientific computing. Mapping to these raises perceived fit.
+
+### Acceptance signals vs. risk signals
+- **Acceptance signals:** GPUs are essential (training/large-scale inference/sim);
+  real models or novel IP (not a thin wrapper); a data flywheel/moat; clear
+  enterprise buyer; technical founding team; maps to a strategic focus area.
+- **Risk/rejection signals:** GPUs only "nice to have"; AI-wrapper with no real
+  compute; consulting/outsourcing; crypto; vague market; no technical depth or
+  differentiation; ineligible category.
+
+If the platform/program changes, prefer the live value and note the update.
 
 ## Step 2 — Score the startup (0–100)
 

package/skills/nvidia-product-inventor/README.md

@@ -1,14 +1,16 @@
 # nvidia-product-inventor
 
-Reads your **existing startup-idea files** and invents **3–6 concrete products**
-(not marketing copy) engineered to fit NVIDIA Inception. Each product gets a
-short brandable name (**4–10 letters**) and an explicit NVIDIA stack —
-**physical/compute hardware (GPUs, Jetson, DGX…) first**, then SDKs, then
-software.
+Reads your **existing startup-idea files** and invents **4–6 highly strategic
+products** (not marketing copy) that all stay in your **same industry, category,
+market, and founder vision** — together forming a stronger **multi-product AI
+ecosystem** engineered to maximize NVIDIA Inception acceptance. Each product gets a
+short brandable name (**4–10 letters**), a full spec (problem, AI + NVIDIA
+opportunity, architecture, revenue model, GPU strategy, acceptance impact), and a
+**complete enterprise-grade brand kit**.
 
 > Builds on **`nvidia-inception-idea-booster`** (preference levers) and
-> **`nvidia-inception-starter`** (acceptance lens). Products only — no website
-> or landing-page copy.
+> **`nvidia-inception-starter`** (acceptance lens). Products only — no website or
+> landing-page copy. NVIDIA acceptance knowledge is **baked in** (research optional).
 
 ## Install
 
@@ -30,7 +32,7 @@ npx spirewise remove -s nvidia-product-inventor -a claude,cursor -sc both
 
 Put your idea notes anywhere in the project, then ask your agent:
 
-> "Invent products for NVIDIA Inception from our idea"
+> "Invent a product ecosystem for NVIDIA Inception from our idea"
 
 It reads those files and writes a **`products_raw/`** folder with one subfolder
 per product.
@@ -39,44 +41,46 @@ per product.
 
 ```
 products_raw/
-├── _overview.md            # all products: name, letters, one-liner, primary GPU
+├── _overview.md            # locked space + ecosystem thesis + all products (both 10/10 scores)
 ├── <Product1>/
 │   ├── product.md
-│   ├── logo-brief.md
-│   ├── <Product1>-logo-dark-1080x1080.png   # dark bg + light mark
-│   └── <Product1>-logo-light-1080x1080.png  # light bg + dark mark
+│   ├── logo-brief.md       # brief + AI prompt + SVG prompt + brand guide + type + palette
+│   ├── <Product1>-logo-primary-1080x1080.png
+│   ├── <Product1>-logo-square-1080x1080.png
+│   ├── <Product1>-app-icon-1024x1024.png
+│   ├── <Product1>-favicon-512x512.png
+│   ├── <Product1>-logo.svg
+│   └── <Product1>-logo-transparent-1080x1080.png
 ├── <Product2>/…
-└── …                       # 3–6 products total
+└── …                       # 4–6 products total
 ```
 
-Each `product.md` covers the problem, what it does, **why GPU compute is
-essential**, the NVIDIA stack (hardware → SDKs → software), physical/edge angle,
-moat, market, Inception fit, and MVP scope. Each product also ships a **real
-1080×1080 PNG logo mark** (abstract symbol only, no letters, centered) in **two
-high-contrast variants** — dark bg + light mark, and light bg + dark mark.
+Each `product.md` covers tagline, vision, description, customer problem, target
+market, **AI opportunity**, **NVIDIA alignment**, core features, technical
+architecture, technology stack (**hardware → SDKs → software**), revenue model,
+market size, competitive advantage, defensibility, **GPU utilization strategy**,
+**NVIDIA Inception acceptance benefits**, the ecosystem link, a dual-10/10
+scorecard, and the brand identity.
 
 ## Rules it enforces
 
-- **Same space only** — all products share the startup's industry, category, core
-  idea, and users (variations/components of the one idea), never new categories or
-  unrelated businesses.
-- **Dual 10/10 gate** — every product must self-score **10/10 on NVIDIA Inception
-  approval fit AND 10/10 on same-space fit** (both recorded in `product.md` and
-  `_overview.md`); redesign or discard anything below 10 on either axis.
-- **Research-backed approval criteria** — products are engineered to the qualities
+- **Same space only** — never changes the startup name, industry, category, or
+  market; products complement each other as one ecosystem, never unrelated plays.
+- **Ecosystem goal** — make reviewers see a long-term AI platform, not a single
+  feature (maximizing AI depth, scalability, enterprise value, GPU usage, moat).
+- **Dual 10/10 gate** — every product self-scores **10/10 on NVIDIA Inception
+  approval fit AND 10/10 on same-space/ecosystem fit** (recorded in `product.md`
+  and `_overview.md`); redesign or discard anything below 10.
+- **Research-backed criteria (baked in)** — products fit the qualities
   NVIDIA-approved startups share (deep-tech & GPU-essential core, authentic NVIDIA
-  platform alignment, physical/agentic AI lean, defensible moat, real market +
-  scalability) and trip **zero disqualifiers** (no AI wrappers, consulting, crypto,
-  or reseller plays).
-- **3–6 products**, each in its own folder under `products_raw/`.
-- Product names are **4–10 letters, letters only**, brandable; folder name = product name.
-- NVIDIA stack ordered **physical/GPU first**, then SDKs, then software.
-- Every product must genuinely need accelerated compute (no AI wrappers).
-- Each product gets a **proper designed logo MARK** — 1080×1080 PNG, **mark/symbol
-  only and center-aligned** (no full wordmark or name text, **no letters,
-  initials, or monogram**), in **two high-contrast variants** (dark bg + light
-  mark, and light bg + dark mark — never low-contrast), each on a **solid
-  background** (no transparency or gradient), a letter-free custom brand symbol
-  (not an SVG/UI icon or emoji), saved in the product's folder.
-
-See `SKILL.md` for the full method and the per-product template.
+  platform alignment, physical/agentic/enterprise AI, defensible moat, real market)
+  and trip **zero disqualifiers** (no AI wrappers, consulting, crypto, or reseller).
+- **4–6 products**, each `4–10 letters` (letters only), in its own folder; folder
+  name = product name; NVIDIA stack ordered **GPU/hardware first**.
+- **Complete brand kit per product** — primary & square logos (1080×1080), app icon
+  (1024×1024), favicon, SVG, and a **transparent-background** version, plus a
+  `logo-brief.md` with the design brief, AI image prompt, SVG prompt, brand usage
+  guide, typography, and color palette. Logos must be enterprise-grade, work on dark
+  **and** light backgrounds, and **avoid generic AI clichés** (no brains/circuits).
+
+See `SKILL.md` for the full method, the per-product template, and the brand-kit spec.