Skill rating

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

TRL: SFT, DPO, GRPO, RLOO reward modeling for LLM RLHF.

Fast BPE/WordPiece tokenization and custom vocab training.

llama.cpp local GGUF inference + HF Hub model discovery.

Agent payments via Stripe Link — cards, SPT, approvals.

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

OBLITERATUS: abliterate LLM refusals (diff-in-means).

Pretrain LLMs at scale with PyTorch 4D parallelism.

Train sparse autoencoders to interpret model features.

Apple Reminders via remindctl: add, list, complete.

Reference-free preference alignment, simpler than DPO.

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

Build explorable isometric architecture atlases as HTML.

Generate one- or two-ink editorial print poster images.

After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, anal

Manage, optimize, and troubleshoot the OpenClaw memory system — MEMORY.md curation, daily logs (memory/YYYY-MM-DD.md), memory_search tuning, compaction survival, and vector/hybrid search configuration

Build high-performing OpenClaw agents end-to-end. Use when you want to design a new agent (persona + operating rules) and generate the required OpenClaw workspace files (SOUL.md, IDENTITY.md, AGENTS.m

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

Discovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or workflow applies to the piece of work at hand. This is the meta-skill that governs how all ot

Any-to-any AI sub-agent — research, images, video, audio, music, podcasts, avatars, voice cloning, documents, spreadsheets, dashboards, 3D models, diagrams, and code in one request. Agent-to-agent pro

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, tes

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Dr

Check Claude Code OAuth usage limits (session & weekly quotas). Use when user asks about Claude Code usage, remaining limits, rate limits, or how much Claude usage they have left. Includes automated m

Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similar

Use when converting a PDF into another format such as Markdown, HTML, text, JSON, DOCX, or structured notes and the agent must choose the best extraction route, settings, and cleanup strategy for maxi

Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc. ) into focused tools people will pay for. Not just "ChatGPT but different" - products that solve specific problems with AI.

Use when designing expensive agency-grade interfaces with premium fonts, spatial rhythm, soft depth, and fluid microinteractions.

Use when a supervisor, swarm, graph, planner-worker system, or parallel agent workflow needs review for task boundaries, shared state, branch joins, retries, cancellation, context handoffs, budgets, d

Architecture and integration sketches for LLM applications, with explicit retrieval, tool, privacy and verification boundaries.

Automate Google Sheets operations (read, write, format, filter, manage spreadsheets) via Rube MCP (Composio). Read/write data, manage tabs, apply formatting, and search rows programmatically.

RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization.

Claiming work is complete without verification is dishonesty, not efficiency. Use when ANY variation of success/completion claims, ANY expression of satisfaction, or ANY positive statement about work

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.

Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas.

Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workfl

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

Automate SendGrid email delivery workflows including marketing campaigns (Single Sends), contact and list management, sender identity setup, and email analytics through Composio's SendGrid toolkit.

Build Model Context Protocol (MCP) servers and tools from scratch. Full-stack MCP development with TypeScript/Python, testing, deployment, and registry publishing.

Operate GitHub issues, pull requests, branches, checks, workflows, and permissions through Rube MCP. Use when GitHub work must be queried or changed programmatically with repository-policy safeguards.

Automate Notion tasks via Rube MCP (Composio): pages, databases, blocks, comments, users. Always search tools first for current schemas.

Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.

Automate Shopify tasks via Rube MCP (Composio): products, orders, customers, inventory, collections. Always search tools first for current schemas.

Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.

Use when an agent, harness, gateway, MCP workflow, or multi-step automation claims completion and the available traces, checkpoints, approvals, tool calls, or deployment records must be judged without

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-com

Embed Photopea in web apps using photopea.js. Covers embedding, file I/O, scripting, exporting, layers, text, filters, and the full Photoshop-compatible API.

Automate Slack workspace operations including messaging, search, channel management, and reaction workflows through Composio's Slack toolkit.

Automate Stripe tasks via Rube MCP (Composio): customers, charges, subscriptions, invoices, products, refunds. Always search tools first for current schemas.