Loading...
Loading...
Found 4,883 Skills
Decomposes complex, multi-day tasks into optimized milestones using parallel reviewer agents (ultraplan). Spawns 5 independent reviewers that analyze the problem from different angles, then synthesizes their findings into a milestone dependency DAG. Triggers when the user says "plan milestones", "break this into milestones", "ultraplan", or when long-run harness needs milestone generation.
Internal conversation-entry router for Claude Code. Performs a lightweight intake pass at the start of substantive work: decide whether a more specific skill should be invoked first, whether specialized agent delegation is warranted, how much context is actually needed, and whether the task needs planning or can proceed directly. Not a user-facing slash command.
Background knowledge for droid-control workflows -- not invoked directly. Agent-browser driver mechanics for web page and Electron desktop app automation.
Send physical mail (letters and postcards) in the US via PostalForm using x402 USDC payments on Base from the awal agent wallet. Use when the user asks to send mail, post a letter, mail a document, send a postcard, mail a PDF, send physical mail, or "mail it to [someone]". Supports user-provided PDFs, auto-generation from text, and AI image generation for postcards via fal.ai (also paid with x402). Recipient must be in the US. Single recipient per send.
Maintain a reviewable LLM Wiki from immutable raw notes, including ingest planning, querying, linting, and guarded raw Graphify maps that help agents generate better wiki pages.
Builds production AI/ML systems — model training, fine-tuning, MLOps pipelines, model serving, evaluation frameworks, RAG optimization, and agent orchestration at scale. Use when the user asks to build, train, or deploy ML models, set up MLOps pipelines, optimize RAG systems, create inference endpoints, or design production AI agents.
Generate or update AGENTS.md for a repository or VS Code workspace, create CLAUDE.md and GEMINI.md shims, build a project matrix with stable project codes, and include UBIQUITOUS_LANGUAGE.md as required context.
Initialize a full ML research project control root with independent paper, code, and optional slide repositories, shared project memory, root-level agent guidance, code-owned worktree policy, and component handoffs. Use when starting a new research project, setting up a project root for agents, connecting paper/code/slides repos, or replacing a simple paper+code workspace with a lifecycle-aware research project structure.
Creates or updates TODO_LIST.md by reading all .md files in the project using sub-agents, then verifies which TODOs are already done by checking the actual code. Use when the user wants to build a comprehensive TODO list from existing documentation, verify TODO status against code, or says "build TODO list".
Verify AI agent patterns including loop safety, retry limits, tool consistency, context size, and graph cycle analysis. Use when asked to "verify agent patterns", "check loops", "verify tools", or "check retry limits".
Full agent verification suite. Runs security, patterns, quality, and language-specific checks. Use when asked to "verify agent", "verify my agent", "audit agent", or "full verification".
Build local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Agent SDK agent complete browsing tasks without raw browser, shell, or CDP access. Use when the user wants an agent to browse or scrape while staying on approved domains, demo blocked off-domain navigation, or generate a safe browser client.