Loading...
Loading...
Found 11,924 Skills
This skill should be used when the user asks to "check my inbox", "read my messages", "any unread messages?", "check for new messages", "see my inbox", or needs to read inter-agent messages from other hive sessions. Provides guidance on reading, filtering, and managing inbox messages.
Audit and prune bloated CLAUDE.md or AGENTS.md context files using evidence-based criteria from research on what actually helps coding agents. Use when a user asks to trim, audit, review, or improve their CLAUDE.md, AGENTS.md, or any repository context file for AI coding agents.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Execute update iterations of existing features (Single Agent Mode). Trigger condition: Requirements or design of completed features change (plan.md + summary.md exist in the directory). Responsible for the complete process from creating update-xxx.md to implementation and review. If the update scale is large and requires multi-role collaboration, create a new Spec and follow the spec-start process.
Tavily: web search optimized for AI agents, answer synthesis, domain filtering, depth control
Create and update CLAUDE.md and AGENTS.md files. Use when: (1) setting up Claude documentation for a project, (2) updating agent instructions after codebase changes, (3) validating docs match current structure. Triggers: CLAUDE.md, AGENTS.md, agent instructions, project documentation.
AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.
Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says "just do it".
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
Agent development workflow and discipline skills. Use when developing features, debugging issues, managing code branches, writing plans, or ensuring code quality through TDD and systematic processes. Triggers on any software development task that benefits from structured workflows.
Use this skill when generating AI-agent-friendly documentation for a git repo or directory, answering questions about a codebase from existing docs, or incrementally updating documentation after code changes. Triggers on codedocs:generate, codedocs:ask, codedocs:update, "document this codebase", "generate docs for this repo", "what does this project do", "update the docs after my changes", or any task requiring structured codebase documentation that serves AI agents, developers, and new team members.
TensorLake SDK for building agentic workflows, sandboxed code execution, and document parsing/extraction. Use when the user mentions tensorlake, or asks about TensorLake APIs/docs/capabilities. Also use when the user is building AI agents or agentic applications that need serverless workflow orchestration (parallel map/reduce DAGs), sandboxed execution of LLM-generated code, or document parsing, structured extraction, and OCR from PDFs/images. Works with any LLM provider (OpenAI, Anthropic), agent framework (LangChain, CrewAI, LlamaIndex), database, or API as the infrastructure layer.