gat-workflow-start
Inspect the repo state and show a status panel across all milestones, recommending the earliest actionable next step in the workflow.
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
26,319 results
Inspect the repo state and show a status panel across all milestones, recommending the earliest actionable next step in the workflow.
Use when you need to see/drive user's live Chrome via CDP.
SINLIMITE: Gauntlet Loop mode, split-build-judge-repeat.
Grill al usuario para afilar un plan o decisión.
Compacta la conversación en un handoff para otro agente.
Prompt engineering reference and workflow for creating, refining, and reviewing high-quality prompts for AI tools, agents, and skills.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
Use when the user asks Codex to bridge a task to ChatGPT, use ChatGPT Temporary Chat for a small one-off task, continue an existing ChatGPT conversation, or…
Context-aware router that detects work type and dispatches to the right skill. Ships with a minimal default routing table; extend it in a fork, or register…
Parallel delegation fan-out on Agy. The coordinating session decomposes and integrates while task units run in parallel as Agy processes (Gemini through the…
Use this skill when the user wants a Claude Code project's context to become "AGENTS.md as the single source of truth (SSOT), with CLAUDE.md reduced to a thin shell containing only Claude-specific content"—generate a tool-agnostic AGENTS.md (Claude Code imports it via the thin-shell CLAUDE.md's @AGENTS.md; read…
Build and reuse the Lingxing ERP OpenAPI integration foundation, handling token, sign, store/site mapping, documentation caching, and basic smoke testing. When to use: when preparing to integrate Lingxing APIs, writing new skills that depend on Lingxing data, or troubleshooting Lingxing OpenAPI authentication and request issues. Trigger word: /zach-lingxing-openapi-client
Use when executing a frozen plan — hand the work to superpowers execution skills, and carry each stage's expected-value × how-to-verify into every sub-agent…
Must-read before modifying ZCode session management (left task list, tasks-index.sqlite, sessions-index, CLI session store, title/status/pin/archive/unread/delete, virtual projects and roots, workspace identity, related migration). It distills 2026-09…
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when executing implementation plans with independent tasks in the current session
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Use when you face 2 or more mutually independent tasks (no shared state, no ordering dependency): dispatch one agent for each independent problem domain to advance in parallel.
This skill should be used when the user asks to "install an MCP server", "add this MCP server", "set up MCP", "configure this MCP tool", "add this to my MCP…
Scope and validate whether an agent workflow is well-suited for Kitaru's durable execution model, then design the flow architecture — checkpoint boundaries,…
Migrate Flyte workflows, tasks, LaunchPlans, and Flytekit code to idiomatic ZenML pipelines. Handles concept mapping (`@task`->`@step`,…