Loading...
Loading...
Found 7,591 Skills
Safe experimentation framework for AI agents. Creates isolated sandbox environments for trying new features, testing approaches, and exploring solutions without polluting the main codebase. USE WHEN: Agent needs to try something uncertain, explore multiple approaches, test a new library, prototype a feature, or run a technical spike before committing to implementation. PRIMARY TRIGGERS: "experiment with" = Setup sandbox + run experiment "try this approach" = Quick experiment in sandbox "spike" / "POC" / "prototype" = Time-boxed technical investigation "tinker" / "tinkering mode" = Enter experimentation workflow "explore options" = Multi-approach comparison in sandbox NOT FOR: Debugging (use debugger), testing (use test runner), or committed feature work (use git branches). DIFFERENTIATOR: Unlike git branches (for committed direction), tinkering is for "I don't know if this will work" exploration. Try 5 things in sandbox before committing to a branch. Faster feedback, zero codebase pollution.
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".
Design tools that agents can use effectively. Use when creating new tools for agents, debugging tool-related failures, or optimizing existing tool sets.
Fix all ESLint and TypeScript errors with parallel processing using snipper agents
Consolidate agent output results into structured final output, supporting multiple formats. Suitable for consolidating analysis reports and generating structured reports
Orchestrator workflow for running ZeroContext Lab (ZCL) attempts/suites with deterministic artifacts, trace-backed evidence, and fast post-mortems (shim support for "agent only types tool name").
Validates permission inheritance between parent and child agents. Ensures child permissions are equal to or more restrictive than parent. Activate on 'validate permissions', 'permission check', 'inheritance validation', 'permission matrix', 'security validation'. NOT for runtime enforcement (use dag-scope-enforcer) or isolation management (use dag-isolation-manager).
FORGE + Agent Teams — Exploits Agent Teams for true parallel execution of FORGE agents. 3 patterns: pipeline (full pipeline with parallel stories), party (multi-agent debate), build (parallel story development). Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. Usage: /forge-team pipeline "objective" | /forge-team party "topic" | /forge-team build [STORY-IDs]
Create or revise Claude Code-compatible Agent Skills (SKILL.md with optional references/, scripts/, and assets/). Use when designing a new skill, improving an existing skill, or updating/refactoring an existing skill while preserving the original author's intent (avoid semantic drift unless explicitly requested/approved by the author). Also use when integrating skills with subagents (context fork, agent).
Best practices, patterns, and examples for building goal-driven agents. Includes client-facing interaction, feedback edges, judge patterns, fan-out/fan-in, context management, and anti-patterns.
MixSeek Agent Skills collection for AI coding assistants. Provides workspace management, team configuration, evaluation setup, and debugging tools for MixSeek-Core.
Deploy and orchestrate Vertex AI ADK agents using A2A protocol. Manages AgentCard discovery, task submission, Code Execution Sandbox, and Memory Bank. Use when asked to "deploy ADK agent" or "orchestrate agents". Trigger with phrases like 'deploy', 'infrastructure', or 'CI/CD'.