Loading...
Loading...
Found 93 Skills
Orchestrate work through a team of agents coordinating via chat. Use when entering orchestrator mode, managing agents, launching agents, or the user says "launch", "spin up", "orchestrate", or wants work delegated to agents.
Claude Shannon's Six Techniques for Creative Problem Transformation. Spawns a team of specialist agents — Simplifier, Analogist, Reframer, Decomposer, Inverter — who each apply one of Shannon's problem-solving techniques to your stuck problem. The lead synthesizes into a transformation assessment: which reframings opened paths, which analogies map, and the honest Shannon verdict on whether the problem has been cracked open. Use when stuck on any problem — engineering, strategy, design, math, business. Works standalone or after other analysis skills surface a hard sub-problem.
Complete Guide for Migrating from Cursor Development Mode to Claude Code Development Mode. Use this skill when projects need to switch from Cursor AI IDE to Claude Code CLI, including configuration migration, document structure conversion, workflow adaptation, etc.
Create a 'how does X work' documentation file for a codebase component or concept. Use $ARGUMENTS as the doc topic if provided.
Use when one agent is implementing code and another agent must review the resulting changes, compare the summary against the actual files, decide whether to fix now or move on, and write the next tightly scoped prompt with context handoff guidance.
Expert research analyst specializing in comprehensive information gathering, synthesis, and insight generation. Masters research methodologies, data analysis, and report creation with focus on delivering actionable intelligence that drives informed decision-making.
Invoke MassGen's multi-agent system. Use when the user wants multiple AI agents on a task: writing, code, review, planning, specs, research, design, or any task where parallel iteration beats working alone.
Use beads (bd) for persistent task tracking in coding projects. A git-backed issue tracker designed for AI agents with dependency graphs, hierarchical tasks, and multi-agent coordination.
Research-driven code review and validation at multiple levels of abstraction. Two modes: (1) Session review — after making changes, review and verify work using parallel reviewers that research-validate every assumption; (2) Full codebase audit — deep end-to-end evaluation using parallel teams of subagent-spawning reviewers. Use when reviewing changes, verifying work quality, auditing a codebase, validating correctness, checking assumptions, finding defects, reducing complexity. NOT for writing new code, explaining code, or benchmarking.
Create and manage multi-repo development workspaces for complex tasks involving multiple repositories, dependencies, and parallel agent work. Use when the user wants to set up a workspace, add repos/worktrees/deps to an existing workspace, or initialize a project that spans multiple repositories. Triggers on requests like "create a workspace", "set up a multi-repo project", "add a repo to the workspace", or "create a worktree".
Use only when the user explicitly requests brainstorming, evaluating architecture choices, or comparing options where no single concern dominates
Create a comprehensive specification from a brief description. Manages specification workflow including directory creation, README tracking, and phase transitions.