Loading...
Loading...
Found 13,656 Skills
Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and worktrees
cmux ターミナル内での操作スキル。ペイン分割、サブエージェント起動・監視・結果回収、コマンド送信、画面読み取り、通知に使用。CMUX_* 環境変数が存在する場合にトリガーされる。
Convert structured UX specs and product context into a sequenced prompts.md file for Claude Code. Use when a user has completed upstream design thinking (problem framing, PRD, UX spec) and needs to translate that into step-by-step prompts that coding agents can execute incrementally. This skill bridges design artifacts to code generation.
Guide for creating properly structured YAML configuration files for MassGen. This skill should be used when agents need to create new configs for examples, case studies, testing, or demonstrating features.
Apply Agency Theory (Jensen and Meckling, 1976) to diagnose principal-agent problems — moral hazard, adverse selection — and design governance mechanisms to align interests. Use this skill when the user needs to analyze conflicts of interest between owners and managers, design incentive or monitoring structures, evaluate corporate governance effectiveness, or when they ask 'how do we ensure managers act in shareholders interest', 'why is this incentive plan failing', or 'what governance mechanisms reduce agency costs'.
Create a new Harbor task for evaluating agents. Use when the user wants to scaffold, build, or design a new task, benchmark problem, or eval. Guides through instruction writing, environment setup, verifier design (pytest vs Reward Kit vs custom), and solution scripting.
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.
Comprehensive review of local uncommitted changes using specialized agents with code improvement suggestions
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the Task tool for architecturally enforced context isolation. Supports Jest, Vitest, pytest, Go test, cargo test, PHPUnit, and RSpec.
Register a Cognitum Seed device by endpoint and establish agent bridge
Design and engineer System Prompts, prompt templates, and multi-agent orchestration contracts for deterministic, leak-proof AI systems. Use when creating agents, writing skill definitions, designing prompt templates with safe variable injection, structuring I/O contracts, or building multi-agent pipelines.
Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live browser state.