Agent Building Agent Skills

Configure tools and SDKs to route LLM requests through a single API key with native-compatible endpoints for Claude, GPT, and Gemini, including setup, base URLs, and code examples.

Builds a complete Uniswap V4 hook by delegating to a hook-builder agent, generating Solidity contracts, Foundry tests, CREATE2 address mining, and deployment scripts.

Orchestrates AI/ML workflows for building LLM applications, RAG systems, AI agents, and ML pipelines, covering design, integration, observability, and security.

Designs collaborative AI agent teams with CrewAI, covering agent roles, task definitions, crew orchestration, process types, memory, tools, and flows.

Build cross-platform AI chat interfaces with Makepad using MolyKit, covering async patterns, BotClient integration, and chat widgets.

Instrument LLM applications with Langfuse for tracing, prompt management, evaluation, and cost tracking, including integrations with OpenAI, LangChain, and LlamaIndex.

Orchestrates multi-agent teams using the ClawTeam CLI, enabling task management, inter-agent messaging, git context integration, runtime profiles, and monitoring dashboards.

Automates sequencing quality control by running FastQC and MultiQC, extracting quality metrics, and generating publication-ready visualizations via a CLI or MCP stdio server.

Discovers, finds, audits, repairs, adapts, crafts, runs, debriefs, saves, and prepares repeatable AI-agent loops for publication, treating loops as bounded feedback systems.

Creates cross-platform agent skills from workflow descriptions, files, URLs, or screenshots. Supports single skills, multi-agent suites, template-based creation, cross-platform export, spec validation, and security auditing of third-party skills before install.

Computes evidence-aware polygenic risk scores from local VCF or WGS files using the just-prs engine and a pinned local MCP server, with honest interpretation and model comparison.

Operate the Unity Editor through MCP tools and resources, covering scene management, script editing, testing, and automation workflows.

Launches coordinated agent teams for tasks requiring persistent cross-talk, shared state, and lifecycle management, with team design, advisor coordination, and quality gates.

Reviews a plan from a prior session by extracting the canonical reference prompt from seed/plan-reviewer-design.md and invoking the plan-reviewer agent with it, surfacing the verdict without auto-applying changes.

Recommends the best skill, agent, or command for a given task by classifying intent and scanning available tools.

Conducts autonomous multi-source research using a planner/executor architecture and an MCP server, with tools for deep research, quick search, report writing, and source retrieval.

Runs a multi-agent academic research pipeline covering systematic review, LaTeX paper writing, peer review, and end-to-end orchestration with integrity gates.

Scopes code-review blast radius and detects architectural hotspots using Tree-sitter AST analysis and GraphRAG, with an MCP server for graph-based analysis.

Manage agent skills from clawhub.com using the ClawHub CLI: search, install, update, list, and publish skill folders with version and changelog options.

Implements finite automata, regular expressions, parsers, and lexers for building text processors and pattern matchers.

Implements AI safety guardrails including input validation, output filtering, robustness testing, human oversight, and monitoring to prevent harmful outputs and ensure system reliability.

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, or extract information from web pages.

Provides guidance on using Anthropic's Claude API, covering message formats, context windows, tool use, and best practices for building conversational AI applications.

Build LLM-powered applications with modular components for chains, agents, memory, and retrieval, supporting Python and JavaScript frameworks.

Guides users through creating effective Agent Skills for Cursor, covering skill structure, best practices, and SKILL.md format.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

Runs independent AI CLI reviewers over phase plans and merges their feedback into a REVIEWS.md file.

Builds a scheduled, AI-powered data collection agent that scrapes public sources, enriches results with Gemini Flash, and stores them in Notion, Sheets, or Supabase.

Ingests video and audio from files, URLs, live feeds, or desktop capture; indexes and searches moments with timestamps; transcodes, edits timelines, generates media assets, and emits real-time alerts.

Builds an evidence-backed ECC install plan for a repository by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes.

Builds persistent multi-agent workflows on Claude Code using a kernel config, specialist agents, slash commands, file-based memory, and scheduled automation without external databases.

Measures whether coding agents actually follow skills, rules, or agent definitions by generating test scenarios, running agents, and classifying tool calls to report compliance rates.

Composes ad-hoc teams of AI agents from local markdown personas and dispatches them in parallel on a task, then synthesizes their outputs.

Creates agent company packages conforming to the Agent Companies specification, either from scratch or by wrapping an existing repository.

Orchestrates multi-agent project builds with persistent state, parallel execution, and atomic git commits.

Sets up Claude Code for a project by analyzing the tech stack, installing relevant skills from skills.sh, generating custom skills, and configuring MCP servers.