Loading...
Loading...
Found 143 Skills
Launch multiple sub-agents in parallel to execute tasks across files or targets with intelligent model selection, quality-focused prompting, and meta-judge → LLM-as-a-judge verification
Lee una URL o lista de ClickUp con tareas de implementación de GoHighLevel y ejecuta automáticamente las que sean automatizables vía API/MCP, dejando claras las que requieren implementación manual. Usar cuando el usuario pase un link de ClickUp y diga "ejecutá", "implementá", "auto-implementá", "auto-ejecutá", "corré las tareas en GHL", "hacé esto en GHL", o cuando el output de `ghl-task-builder` (alias `ghl-clickup-task-builder`) ya esté en ClickUp y se quiera dispararlo. Esta skill es complementaria — `ghl-task-builder` GENERA tareas, esta skill las EJECUTA.
Executes Story Finalizer test tasks (label "tests") from Todo -> To Review. Enforces risk-based limits and priority.
Execute the currently claimed task end-to-end and move it to review with verifiable output.
Keeps a long Claude Code task on-track — breaks out of looping/circular thinking, watches the context budget, bounds internal reasoning, and triggers a clean handoff before the window fills. Use when the model is repeating steps, re-reading the same files, second-guessing in circles, stuck or spinning, or running a long multi-step task at risk of exhausting context. Also use when the user says it is "looping", "going in circles", "stuck", "repeating itself", or asks for a handoff before running out of context.
PRD construction for work planning. Compulsory in PLAN phase. Builds .prd file as frozen dependency graph of every possible work item before execution begins. Triggers on any new task, multi-step work, or when gm enters PLAN state.
(NS) Sync existing GitLab issues with local planning and execution — milestone, RF labels, status transitions, assignee, estimates, spent time. Use during implementation when tasks link to GitLab issues or after plan-version-from-gitlab sync — not for creating new issues (use mcp-gitlab-usage). Always use atomic set_issue_labels and three-step status cycle. Read mcp-gitlab-usage for tool contracts.
General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. Use when you need to perform comprehensive searches across codebase, find files that are not obvious in first few searches, or execute multi-step tasks requiring multiple tools and approaches.
Use when work should be delegated to Claude Code CLI, especially headless `claude -p` runs, automation scripts, CI jobs, resumable sessions, or requests to use Claude/Claude Code for a task.
Internal helper contract for calling the pi-companion runtime from Claude Code
Do the work. Pre-flight, build, detect drift, salvage if needed. Use when you have a clear aim and are ready to implement.
Analyze a task, pick the right fleet type, and generate a ready-to-launch fleet (fleet.json + prompt.md files). Discovers available fleet skills dynamically. Use when the user wants to run work in parallel, asks to "plan a fleet", or says "fleet-plan".