Claude Skills by huawolf

Use this skill when a user asks to automate a website with BrowserWorker, create a reusable browser action script, inspect a page, use page_semantics/semantic_key, use browser snapshots, ask the user to record/upload a flow, or turn recorded trace/interests/script_hints into a working action. It covers the BrowserWorker daemon, Chrome extension transport, semantic-first workflow, snapshot validation, recording fallback, DOM extraction, action development, validation, and debugging.

Delegate coding tasks to the Blackbox AI multi-model CLI.

Configure and troubleshoot Honcho memory for Hermes.

Read-only EVM client: wallets, tokens, gas across 8 chains.

Hyperliquid market data, account history, trade review.

Query Solana wallets, tokens, txs, and NFTs in USD.

1-3-1 decision briefs: problem, three options, one pick.

Generate flat, minimal educational SVG visuals as HTML.

Render MP4/WebM videos from HTML compositions.

Plan and run multi-agent video production pipelines.

Create meme PNGs from templates with Pillow text overlay.

Manage Docker containers, images, volumes, and Compose.

Zero-install localhost tunnels over SSH via Pinggy.

Roleplay a hostile user to find and triage UX pain points.

Give the agent its own inbox: send and receive email.

Build integrated IS/BS/CF financial workbooks in Excel.

Build comparable-company valuation workbooks in Excel.

Build discounted cash flow valuation workbooks in Excel.

Build auditable financial workbooks headless via openpyxl.

Build leveraged buyout workbooks with IRR/MOIC in Excel.

Build M&A accretion/dilution workbooks in Excel.

Build PowerPoint decks headless with python-pptx.

Stock quotes, history, search, compare, crypto via Yahoo.

Workout planning, macros, and body metrics via wger/USDA.

Use live BCI cognitive and mood state from NeuroSkill.

Build, test, and deploy Python MCP servers.

List, auth, and call MCP servers/tools from the terminal.

Import an OpenClaw setup (memories, skills) into Hermes.

Run PyTorch training across GPUs with minimal changes.

Embedding database for RAG and semantic search.

Zero-shot image classification and image-text search.

Fast vector similarity search at billion scale.

Speed up long-sequence transformer training and inference.

Constrain LLM output with grammars; guarantee valid JSON.

Fast BPE/WordPiece tokenization and custom vocab training.

Outlines: structured JSON/regex/Pydantic LLM generation.

Structured LLM outputs validated with Pydantic.

On-demand GPU cloud instances for ML training.

Vision-language chat: VQA, captioning, image dialogue.

Serverless GPU cloud for ML jobs and model APIs.

Curate LLM training data: dedupe, filter, PII redaction.

Fine-tune large LLMs with LoRA on limited GPU memory.

Managed vector DB for production RAG and search.

Fully sharded data-parallel training for large models.

Clean training loops with built-in distributed support.

Vector search engine for production RAG systems.

Train sparse autoencoders to interpret model features.

Reference-free preference alignment, simpler than DPO.

RL post-training for LLMs with Megatron and SGLang.

Text-to-image generation, inpainting, and img2img.