Loading...
Loading...
Found 10,410 Skills
Start Comment to Fix on HTML — preview with overlay, watch annotations, fix in a loop until stopped. Use when the user runs /comment-to-fix or wants to review HTML slides, proposals, or landing pages with live agent fixes.
Human-in-the-loop safety controls — approval routing via human, LLM judge, or auto-approve with guardrail overrides.
Use when creating a GitHub pull request or merge request from the current branch, especially when a project PR template may exist.
The orchestrator and entry point for the engineering skills suite. Use this skill whenever the task involves doing engineering work to a high bar — reviewing code or a design, designing a new system or component, debugging a hard problem or running an incident, implementing a substantive change, writing documentation, or sanity-checking an approach. Use it when the user phrases things casually ("rip into this", "be brutal", "is this approach right", "what am I missing", "what would you change", "look at this") or formally ("review this PR", "audit this design"). Use it proactively for any non-trivial engineering work, before declaring something done. The skill triages the work, dispatches to the right specialty skill(s), enforces verification, and produces an evidence-backed result. The goal is to ensure no AI shortcut, sycophantic agreement, or stylistic distraction gets in the way of work that holds up to senior-engineer scrutiny.
Cerrar e integrar el trabajo de una historia de usuario haciendo merge de la rama feature/US-XXX hacia la rama desde la que se creó, previa verificación de que progress.md tenga todas las tareas en Done. Activar cuando el usuario pida cerrar, entregar, mergear, integrar, finalizar o hacer submit del trabajo de una historia, una US o de la rama actual.
Crea o actualiza tareas técnicas (TK-XXX) asociadas a una historia de usuario existente. Activar cuando el usuario solicite planificar implementación, descomponer trabajo, definir alcance técnico, estructurar subtareas o documentar especificaciones técnicas sin generar código ni pruebas. Activar también — por defecto — cuando el usuario solo entregue una referencia a una historia (p. ej. «US-004», «planifica US-007», «tareas para esta historia») — en ese caso el propósito es proponer stubs agrupados por unidad de trabajo que cubran los escenarios (SC-XX) y consideren las reglas de negocio (BR-XX) de la US, sin redactar TKs completas.
Use when running Claude Fable on codebase-heavy or token-heavy work and the user wants Fable to orchestrate research, coding, and testing while cheaper subagents do bounded heavy lifting.
Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM. Use when the user wants to ground captions to bboxes, generate phrase-grounded annotations, auto-label images for grounding, or run the image_grounding pipeline. Triggers include 'image grounding', 'phrase grounding', 'ground captions', 'auto-label image grounding', 'image_grounding'.
Kubernetes execution platform — submits TAO container jobs as single-pod k8s Jobs with NVIDIA GPU scheduling. Use when running on EKS / GKE / AKS / on-prem clusters with the NVIDIA GPU Operator installed, or when integrating TAO into an existing k8s-native ML platform.
Run a second round on a contested question by circulating each subagent's independent proposal to the other authors and asking for structured pros and cons, then synthesize. Use this skill whenever you have multiple independent proposals or opinions on a contested decision — architecture tradeoffs, code review disagreements, design choices, competing root-cause theories — and want sharper analysis than you'd produce by synthesizing alone. Pairs naturally with the council and research skills; reach for it liberally whenever proposals diverge.
Creates a new Linear issue from a free-form description. Drafts a structured title and body, picks team/project/labels/priority from the connected workspace, shows the draft to the user for approval, then creates the ticket. Use when the user asks to "create a Linear ticket", "file an issue", "make a ticket", "open an issue in Linear", or any request to log a new bug/feature/task.
Trace upstream data lineage. Use when the user asks where data comes from, what feeds a table, upstream dependencies, data sources, or needs to understand data origins.