Loading...
Loading...
Found 2,167 Skills
Execute proactive auto-loading: automatically detects and loads agents.md files. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
Complete workflow for building, implementing, and testing goal-driven agents. Orchestrates hive-* skills. Use when starting a new agent project, unsure which skill to use, or need end-to-end guidance.
Intelligent multi-topic in-depth research tool that supports input of any materials, uses independent research Agents for parallel in-depth retrieval and generates systematic research documents. This skill should be used when users need to conduct in-depth research on multiple related topics, perform systematic information retrieval, and integrate multi-angle analysis.
Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.
Fetch source code for npm, PyPI, or crates.io packages and GitHub/GitLab repos to provide AI agents with implementation context beyond types and docs. Use when needing to understand how a library works internally, debug dependency issues, or explore package implementations.
Use the xurl CLI to resolve unified agents:// URIs (and legacy provider URIs) for Amp, Codex, Claude, Gemini, Pi, and OpenCode thread reading workflows.
Use when coordinating non-trivial implementation work, executing implementation plans, or modifying AGENTS.md/CLAUDE.md.
Manage parallel development with cmux-style git worktrees in one repository. Use this skill whenever the user asks to run multiple agents in parallel, create or resume isolated worktrees, list/switch/merge/remove worktrees, set up `.cmux/setup`, or recover from worktree conflicts. In this environment, always use the `cmx` alias in commands.
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or the loop cap is reached. Use when: implementing features from a spec or plan, hardening existing code, fixing a batch of issues, or any multi-file task that benefits from a build-verify-fix cycle.
Generate type-safe React Query hooks, Prisma-like ORM client, or inquirerer-based CLI from GraphQL endpoints, schema files/directories, databases, or PGPM modules using @constructive-io/graphql-codegen. Also generates documentation (README, AGENTS.md, skills/, mcp.json). Use when asked to "generate GraphQL hooks", "generate ORM", "generate CLI", "set up codegen", "generate docs", "generate skills", "export schema", or when implementing data fetching for a PostGraphile backend.
Claude Code extensibility: agents, skills, output styles. Capabilities: create/update/delete agents and skills, YAML frontmatter, system prompts, tool/model selection, resumable agents, CLI-defined agents. Actions: create, edit, delete, optimize, test extensions. Keywords: agent, skill, output-style, SKILL.md, subagent, Task tool, progressive disclosure. Use when: creating agents/skills, editing extensions, configuring tool access, choosing models, testing activation.
Coordinate Claude Code Agent Teams through filesystem-based protocol. Use when orchestrating multiple Claude agents on parallel tasks, need task dependency management, multi-agent code review or implementation. Do not use when single-agent work suffices, task is not parallelizable.