Skill catalog

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring cod…

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inferen…

Interactive onboarding tour for the context-matic MCP server. Walks the user through what the server does, shows all available APIs, lets them pick one to explore, explains it in their project language, demonstrates mod…

Use when generating or handling 3D assets through the Scenario MCP server, including text-to-3D or image-to-3D meshes, GPT-6 Astra 3D or Claude Opus 5.5 3D, GLB, FBX, OBJ, STL, or VOX files, PBR-textured or game-ready m…

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on…

Generate new Webflow Code Component boilerplate with React component, definition file, and optional styling. Automatically checks prerequisites and can set up missing config/dependencies.

No description provided.

No description provided.

Use this skill when creating or editing an agent.yaml (or .yml/.hcl) configuration file for Docker Agent (cagent), including defining agents, models/providers, built-in or MCP toolsets, multi-agent teams with sub_agents…

Automate multi-locale marketing screenshot capture for SwiftUI iOS apps with in-app capture system, demo data seeding, and element rendering.

Use to write a LinkedIn post — professional, thought-leadership, or founder/personal-brand content optimized for LinkedIn's specific mechanics (dwell time, early comments, the "see more" hook). Run when the user says "w…

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference…

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured genera…

Performance profiling principles. Measurement, analysis, and optimization techniques.

Hacker News from your terminal — with a local SQLite store, snapshot history, and agent-native output no other HN tool has. Trigger phrases: `check hacker news`, `search hn`, `what is hn saying about`, `diff the hn fron…

Apple Human Interface Guidelines for Apple Vision Pro. Use when building spatial computing apps, implementing eye/hand input, or designing immersive experiences. Triggers on tasks involving visionOS, RealityKit, spatial…

Export Webflow Designer components to React/Next.js code for external projects. Configure devlink settings in webflow.json, sync design updates with devlink sync, validate generated code, show diffs, and provide integra…

This skill should be used when the user wants to manage Railway deployments, view logs, or debug issues. Covers deployment lifecycle (remove, stop, redeploy, restart), deployment visibility (list, status, history), and…

No description provided.

Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for docume…

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or t…

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. U…

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignme…

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scal…

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tenso…

The teach-to-grow content type -- pick a genuinely useful topic, teach ONE thing completely, structure it as a clear lesson, keep it accurate, and route it to the right format. Use when someone wants to teach their audi…

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-he…

Spawn the comment-sicko subagent, fix accepted findings, and offer encodings for claimed constraints.

Draft process letters and bid instructions for sell-side M&A processes. Covers initial indication of interest (IOI) instructions, final bid procedures, and management meeting logistics. Triggers on "process letter", "bi…

SEO & content marketing command suite for keyword research, audits, technical SEO, competitor analysis, and content strategy workflows

Social selling and DM funnels — consent-first selling in the DMs, never spam. Use when someone wants to "sell in the DMs," "set up a comment-to-DM funnel," "do DM outreach," "turn comments/followers into leads or custom…

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposi…

AI-powered marketing copilot for China's 3C consumer electronics market (mobile, laptops, earphones, wearables, smart home)

Discover and launch the Excel CLI for ordinary Excel workbook requests on Windows, including reads, writes, formulas, data refreshes, and workbook automation. Use the installed excel-cli plugin's npx launcher and native…

Open-source marketing operations control center for AI agent teams with CRM, outreach, content ops, and analytics powered by OpenClaw + SQLite

md/html/docx/pdf/epub 多向流水线，落地「md 生产，多端消费」。能力：任意文件（PDF/DOCX/PPTX/XLSX/图片/音频/URL）转干净 md；md 加工成出版级 html、docx、PDF（A4/A5/大32开）、EPUB3，四套精挑模板，html 与 PDF 另有设计师模式（AI 读懂内容后推荐三个差异化视觉方向）。SKIP：需要新生成图片、或只做压缩截图的任务。

Create and manage Circle developer-controlled wallets where the application retains full custody of wallet keys on behalf of end-users. Covers wallet sets, entity secret registration, token transfers, balance checks, me…

Convert an existing React component into a Webflow Code Component. Analyzes TypeScript props, maps to Webflow prop types, generates the .webflow.tsx definition file, and identifies required modifications.

Creates and deploys Node.js HTTP web applications on AWS Lambda Web Functions. Guides users through building web apps and APIs with Express, Fastify, or Hono, packaging, deploying via the aws lambda-web CLI, and iterati…

Use this skill when running a Docker Agent with `docker agent run`, choosing a safety/approval mode, using the `--sandbox` isolation flag, setting up aliases, or troubleshooting a run (missing credentials, worktrees). E…

A/B testing and experimentation for social media content — evidence over opinion, at honest organic-scale rigor. Use when someone wants to "A/B test" or "split test" content, "test which version/hook/time/caption/thumbn…

No description provided.

Use for GDPR or DSGVO work: scanning a codebase for privacy risks, writing a DPIA or tracking data subject requests against the Art. 12(3) deadline. Runs gdpr_compliance_checker.py, dpia_generator.py and data_subject_ri…

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 prod…

SEO & content marketing command suite with keyword research, technical audits, SERP analysis, and automated content workflows

Expert patterns for Shopify app development including Remix/React Router apps, embedded apps with App Bridge, webhook handling, GraphQL Admin API, Polaris components, billing, and app extensions.

Give your agent the ability to speak to you real-time. Talk to your Claude! Ultra-fast TTS, text-to-speech, voice synthesis, audio output with ~90ms latency. 8 built-in voices for instant voice responses. For voice clon…

Free Google Trends data - real-time trending topics and keyword analysis over time (interest over time, related queries, interest by region).

Generate videos from briefs, prompts, images, audio, or reference clips. Choose a Seedance 2.5 generation mode, submit one or many clips, resume runs, and download results.