发现 Skills

Browser automation CLI for AI agents. Use when automating web interactions, testing user flows, scraping web content, or performing browser-based tasks. Fast Rust CLI with Node.js fallback, optimized for AI agent workflows with snapshot-based element selection using refs.

REQUIRED for ANY changes to Linux desktop, QML Shells, QuickShell/Qt environment, window manager, or system config. Use when editing ~/.config/Ambxst/ or ~/Ambxst/. Triggers: themes, wallpaper, night light, idle, lock screen, screenshots, layer rules, workspace settings, display config.

Multi-Path Payments (MPP) — split a payment across multiple parallel routes; same payment_hash, payment_secret binds parts. AMP (Atomic Multipath) — variant where each part has different hash; receiver derives shared secret. USE WHEN: implementing payment splitting, debugging "couldn't route full amount", evaluating MPP vs AMP.

Channel jamming attacks: slow-jam (long-held HTLCs exhaust slots), fast-jam (rapid hold/release exhausts liquidity). Mitigations: upfront fees, reputation, hold-fee proposals. USE WHEN: assessing LN security model, designing reputation systems, evaluating jamming-resistant routing.

Per-tenant, per-feature, per-query RAG cost tracking. Covers token counting (tiktoken, Anthropic count_tokens), structured metadata logging, aggregation in BigQuery/Snowflake/ClickHouse, dashboards (Grafana, Metabase), LangSmith and Langfuse native cost reports, and budget alerts. Schema + example queries. USE WHEN: user mentions "RAG cost", "cost per tenant", "cost per query", "token counting", "chargeback", "showback", "LangSmith cost", "Langfuse cost", "budget alerts" DO NOT USE FOR: reducing cost - use `rag-production`; batch-discount strategy - use `batch-inference`; routing for cheaper models - use `llm-gateway`

Krux: DIY airgap signer running on Sipeed M5StickV / Maix Amigo. Open-source, multi-language, stateless. USE WHEN: integrating Krux, evaluating M5StickV-based signers.

Lightning Dev Kit (LDK): modular Rust crates for embedding Lightning in apps. ldk-node for opinionated quick-start. Bindings to Swift / Kotlin / JS. USE WHEN: embedding Lightning in mobile/desktop apps, building custom LN logic.

libsecp256k1: the canonical secp256k1 C library. Used by Bitcoin Core, rust-secp256k1, and all major language bindings. USE WHEN: low-level crypto in C/C++, building bindings, performance-critical paths.

taproot-assets daemon (tapd): Go implementation of the Taproot Assets Protocol by Lightning Labs. Companion to LND. USE WHEN: integrating with tapd, building Taproot Assets apps in Go.

Export Claude Hangar skills and rules to other AI coding tool formats. Use when: "export rules", "cursor rules", "windsurf rules", "export-rules", "convert to mdc".

Use when you need to deploy a Modal app to production or update an existing deployment.

Segmenting home networks into VLANs for IoT, guest, trusted, and server traffic using UniFi, pfSense/OPNsense, and MikroTik — including switch trunk config, firewall rules, and wireless SSID mapping.

Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk, implementing risk limits, or building risk monitoring systems.

Federated variant lookup across 9 genomic databases — GWAS Catalog, Open Targets, PheWeb (UKB, FinnGen, BBJ), GTEx, eQTL Catalogue, and more.

HLA allele typing from WGS/WES VCF data

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

This skill provides reference guidance for citation verification in academic writing. Use when the user asks about "citation verification best practices", "how to verify references", "preventing fake citations", or needs guidance on citation accuracy. This skill supports ml-paper-writing by providing detailed verification principles and common error patterns.

Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

Comprehensive Markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (Markdown + Mermaid), 24 diagram type references, and 9 document templates.