Loading...
Loading...
Found 1,152 Skills
Translate and dub a video into another language with voice cloning and lip-sync, powered by HeyGen Video Translation. The presenter keeps their face, their voice is cloned into the target language, and lips re-sync to the new audio — viewers see the same person speaking natively. Use when: (1) localizing an existing video into one or more languages ("translate this video to Spanish", "make this in French and German", "dub this into Japanese", "I need this in 10 languages for a launch"), (2) the user has a finished video and wants the SAME presenter speaking another language (not a new presenter — that's heygen-video), (3) podcast / audio-only translation ("translate this podcast", "dub the audio but keep my video"), (4) high-stakes translations where the user wants to review/edit subtitles before final render (the proofreads workflow), (5) "translate my video", "dub this", "localize this clip", "make a multilingual version", "subtitle and dub". Returns the translated video URL (or audio file for audio-only mode), one per target language. Chain signal: if the user wants to CREATE a new video in another language (no source video exists yet), route to heygen-video and write the script in the target language — do not use heygen-translate. Use heygen-translate only when there is an existing source video to localize. NOT for: creating new videos from scratch (use heygen-video), avatar creation (use heygen-avatar), TTS-only synthesis (use heygen-video with audio-only output), or text-only translation.
Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels. Covers: tune-once/cache/launch pattern, per-architecture configs (sm80–sm120), parameter space design (tile sizes, occupancy, num_ctas), and 7 common pitfalls with solutions.
Storyblok integration. Manage Stories, Spaces. Use when the user wants to interact with Storyblok data.
Use systematic spacing with 25% minimum jumps, start with excess whitespace
Autonomous research agent that reads RESEARCH.md, infers what's needed, dynamically adjusts TODOs, and delegates to the right skill. Supports opt-in BFS mode for autonomous design space search. Respects a configurable supervision policy (presets: manual / checkpointed / autonomous / wild) governing notifications, approval gates, resource limits, and idea-change handling. Proactively surfaces gaps and asks before acting. Trigger phrases: "start research", "continue project", "what's next?", "explore design space", "autoresearch".
Build and deploy a Next.js, Bigfish (@alipay/bigfish), or Vite project to the Morphe service (https://morphe.zenmux.app), targeting a linux-x64-gnu runtime. Use when the user asks to deploy, ship, publish, or release a Next.js, Bigfish, or Vite app to Morphe, run "morphe deploy", or otherwise push a build to the Morphe / zenmux platform. Handles login, framework detection, Next.js standalone validation / config fixing, Bigfish static-server wrapping, Vite SPA static wrapping or custom-server (server.ts/js) esbuild bundling, building, zipping, OSS upload, CRC64 checksum, .morphe.json management, and the deploy API call.
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
Use the local `5dive` CLI on a 5dive runtime VM to spawn, inspect, send to, and tear down sibling agents. Trigger when the user wants a worker, sub-agent, side task, parallel run, fan-out, or to delegate — or names a sibling agent ("ask X", "ping X", "tell X", "hand off to X", "coordinate with X"); confirm it exists via `5dive agent list --json`, then `agent send`. Also for inspecting/restarting/pairing an existing agent, a machine-readable health check (`5dive doctor --json`, `5dive selfcheck --json`), a task's causal history (`5dive trace <id|DIVE-N>`), the current model id per alias (`5dive models`), the host-shared task queue + org chart (`5dive task`, `5dive org`), grouping a multi-task effort under a project (`5dive project add`, `task add --project`), recurring/scheduled work (`task add --recurring`, `5dive heartbeat`), parking a question on a human (`task need`, risk-tiered via `--tier`) or snoozing work (`task park --wake`), searching the team's accumulated memory/wiki (`5dive memory search`) or compiling a durable one into it (`5dive memory add`), reading fleet health / token burn / the daily standup (`5dive supervisor`, `5dive usage`, `5dive digest`), building or editing multi-agent loops — a relay where each step hands off automatically with optional human gates (`task loop start`/`loop ls`) or a maker→verifier review loop (`task add --verifier`, `task reject`, `task loops`), or decomposing an outcome into a guardrailed task DAG (`5dive goal add`) — hiring a ready-made persona off the agent market (`5dive market`, `5dive hire --from-market`) or firing one (`5dive fire`), declarative fleets (`5dive up`, `5dive team import`), hosting a CrewAI crew (`5dive crew`), controlling agents on OTHER registered boxes (`5dive fleet`), running a self-steering objective bound to a live metric (`5dive objective`, `objective replan`), convening a governance vote (`5dive council convene`, `council gate-clear`, `council schedule add` for a recurring convene), the onboarding wizard (`5dive company`), or a delegated GitHub push-for-review (`5dive push`, needs `agent create --can-push`). When a request came over a chat channel (Telegram/Discord `<channel>` tag) and another agent should handle it, pass the chat context via `--reply-to-chat=<id> --reply-to-msg=<id>` so that agent replies from its own bot — don't relay. Always prefer `5dive` over running coding CLIs by hand.
Create and control VFX in Unreal Engine 5 with Niagara: systems and emitters, modules and the spawn/update stages, exposed User parameters, and spawning or driving effects from Blueprints or C++. Use when building particle effects, NS_/NE_ assets, spawning a Niagara system at runtime, setting User parameters, or when the user mentions Niagara, VFX, or a particle system in Unreal.
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
Implement distributed tracing with correlation IDs, trace propagation, and span tracking across microservices. Use when debugging distributed systems, monitoring request flows, or implementing observability.
Capture exceptions, add context, create performance spans, and use structured logging with Sentry.