Loading...
Loading...
Found 2,174 Skills
Vercel AI SDK v6 development. Use when building AI agents, chatbots, tool integrations, streaming apps, or structured output with the ai package. Covers ToolLoopAgent, useChat, generateText, streamText, tool approval, smoothStream, provider tools, MCP integration, and Output patterns.
Generate AGENTS.md and CLAUDE.md files for a repository. AGENTS.md provides cross-tool agent instructions (supported by Claude Code, Cursor, Windsurf, Zed, Codex, and others). CLAUDE.md adds Claude-specific configuration and references AGENTS.md via @import. Use when a repo needs agent onboarding or when starting a new project.
Extract and structure fuzzy product ideas into validated problem statements, target users, and jobs-to-be-done. Use when a user has a raw idea, concept, or solution in mind but hasn't clearly articulated the problem, target user, or assumptions. This skill helps users communicate context to coding agents more effectively, reducing iteration cycles and "that's not what I meant" moments.
Use when an approved current phase has 3 or more independent ready tasks and parallel execution will materially reduce cycle time. Orchestrates bounded workers, monitors blockers and file conflicts, coordinates rescues, and hands off to planning or reviewing when the current execution scope is complete. Use for prompts about swarming, parallel workers, launching multiple agents, coordinating a worker pool, or running approved current-phase work at scale.
Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely. Supports AI agents, code generation, and experimentation. Use when executing user-generated or AI-generated code in isolation.
Core patterns for AI coding agents based on analysis of Claude Code, Codex, Cline, Aider, OpenCode. Triggers when: Building an AI coding agent or assistant, implementing tool-calling loops, managing context windows for LLMs, setting up agent memory or skill systems, or designing multi-provider LLM abstraction. Capabilities: Core agent loop with while(true) and tool execution, context management with pruning and compression and repo maps, tool safety with sandboxing and approval flows and doom loop detection, multi-provider abstraction with unified API for different LLMs, memory systems with project rules and auto-memory and skill loading, session persistence with SQLite vs JSONL patterns.
N coordinated agents on shared task list using tmux-based orchestration
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.
Validate, audit, and fix agent skills for agentskills.io spec compliance. Use when creating a new skill structure, auditing an existing skill against the specification, fixing common spec deviations, or reviewing frontmatter, directory layout, progressive disclosure, or script interfaces. Triggers on "validate skill", "audit skill", "spec compliance", "fix skill structure", "skill frontmatter", "SKILL.md format", or "agent skills spec".
Measure and optimize customer service performance using CSAT, NPS, CES, First Contact Resolution, and text mining on support tickets. Use this skill when the user needs to evaluate CS team performance, identify top complaint drivers, optimize staffing, or build CS dashboards — even if they say 'is our CS team doing well', 'what are customers complaining about', 'how many agents do we need', or 'build a CS dashboard'.
Multi-agent discussion rooms — debate or poll a problem from multiple perspectives. Standalone or invoked by other skills as a sub-routine. Mode=debate: N agents argue in rounds, converge. Mode=poll: N agents independently analyze, aggregate by consensus. Not for implementation (use system-architecture). Not for verification (use review-chain). For clarifying requirements first, see discover. For decomposing work after a decision, see task-breakdown.
Harness Engineering Phase 1 Step 2: Conduct in-depth analysis of project code and fill in the substantive content of each file in the docs/ knowledge base. Use this skill after the directory skeleton is created by harness-step1-create-agents-md. Immediately trigger this skill when the user says "fill document content", "improve docs/ files", "add substantive content to documents", "analyze project and write architecture document", "write ARCHITECTURE.md", or "write technical decision document". Prerequisite: The project already has AGENTS.md and the docs/ directory skeleton (created by harness-step1).