MLOps
模型部署、评估与运维
fundraise-prep
jforksy
Data room preparation, VC Q&A prep, due diligence readiness, and fundraising materials
unstuck-scaling
Coowoolf
Use when AI agents frequently hit dead ends, when reliability is the main constraint on scaling utility, or when general model improvements don't solve specific blockers
3-Month PMF Treadmill
Coowoolf
Product-Market Fit is perishable in AI. LLM capabilities jump every 3 months, so you must pivot and reinvent your core value proposition quarterly. Accept high churn and throttle scaling for reinvention.
cfo
jforksy
CFO Co-Pilot - strategic finance, valuation narrative, and VC readiness
ollama-daemon
fast-gateway-protocol
Fast local Ollama model inference via FGP daemon. Use when user needs local LLM chat, text generation, embeddings, or model management. Triggers on "ollama chat", "local llm", "ollama generate", "ollama embed", "pull model", "run llama locally".
css-fundamentals
pluginagentmarketplace
CSS fundamentals - selectors, specificity, box model, positioning, units
media-craft
NanHeSam
Generate, edit, transform, and enhance media using the obra CLI. Use when the user asks to create/generate/edit images, videos, music, or audio. Covers text-to-image, image-to-image, image editing, upscaling, background removal, text-to-video, image-to-video, video-to-video, motion control, AI avatars, music generation, lyrics, and music videos.
Emerging Channel Evaluation Framework
Coowoolf
105 Product Management Skills extracted from Lenny's Podcast - For use with Claude Code / Cursor / Windsurf
cap-table
jforksy
Equity tracking, dilution analysis, option pool modeling, and cap table management
cognitive-baseline-eval
starwreckntx
Execute the Joseph Cognitive Baseline v2.1 (JC B-v2.1) 5-Scenario Test Suite to quantify AI alignment, friction maintenance, and protocol adherence.
frontend-razor
twofoldtech-dakota
Razor view patterns for Optimizely CMS projects
cpo
jforksy
CPO Co-Pilot - product strategy, roadmap prioritization, competitive positioning, and product-market fit validation
cross-model-handoff-testing
starwreckntx
Test cross-model context handoff integrity.
business-model-auditor
fefogarcia
Use this skill when users need to stress test their business model, identify scale limitations, find bottlenecks, determine if they're trading time for money, or evaluate unit economics. Activates for "can this scale," "what breaks at 10x," or business model viability questions.
Builder Operating Model
Coowoolf
Shift from rigid roles (PM, Designer, Engineer) towards a model where individuals use AI to bridge skill gaps, enabling smaller and flatter teams. Use in early-stage startups or innovation units where speed is critical.
frontend-razor
twofoldtech-dakota
Apply when working with Razor views, MVC layouts, partial views, and tag helpers
frontend-razor
twofoldtech-dakota
Apply when working with Razor views, MVC layouts, partial views, and tag helpers
fine-tuning
pluginagentmarketplace
LLM fine-tuning with LoRA, QLoRA, and instruction tuning for domain adaptation.
Constitutional AI
Coowoolf
105 Product Management Skills extracted from Lenny's Podcast - For use with Claude Code / Cursor / Windsurf
computational-model-design
starwreckntx
Design computational models for cognitive simulation and analysis.
three-layer-agent-stack
Coowoolf
Use when building AI-powered products or agents, when raw model intelligence isn't enough to solve user problems, or when designing the architecture for agentic workflows
replicate-daemon
fast-gateway-protocol
Fast Replicate model inference via FGP daemon. Use when user needs to run ML models (image generation, LLMs, audio processing, video generation) on Replicate. Triggers on "replicate run", "run model replicate", "stable diffusion", "SDXL", "replicate llama", "whisper replicate".
Hierarchy of Marketplaces
Coowoolf
A roadmap for marketplace domination. Level 1: Focus on a "thimble" to maximize Happy GMV. Level 2: Tip the market via growth loops. Level 3: Dominate to capture economic rents. Not all GMV is equal.
Google ADK Python Skill
wollfoo
Remember: ADK treats agent development like traditional software engineering - use version control, write tests, and follow engineering best practices.