Total 54,390 skills, AI & Machine Learning has 9052 skills
Showing 12 of 9052 skills
Dub audio and video into other languages using the ElevenLabs Dubbing API (dubbing_v2), preserving the original speakers' voices. Use when translating videos, podcasts, or recordings into other languages, localizing media content, reviewing or correcting dubbing transcripts and translations, or regenerating a dub after edits.
Canonical workflow for a task. Read and follow strictly end to end while working on the task.
Scaffold a minimal local LangGraph agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a LangGraph agent locally.
Use when agents must debate, conference, deliberate, or reach consensus on a goal — competing positions argue and converge on one deliverable, adversarial review with synthesis, multi-stakeholder deliberation, structured disagreement with a forcing-field deliverable. Triggers: 'have agents debate X', 'reach consensus on Y', 'argue distinct positions and converge'. Not for saved team configs, agents/<slug> artifacts, implementation, or open-ended research.
The always-on protocol for the loam skill namespace. Use at session start and whenever a loam task appears. Routes goals and other loam work, explains the memory model (memory = umbrella; wiki, guidance, and checkpoints are substrates), and lists cross-cutting rules. This is a routing/meta skill — delegate to a specific loam skill rather than performing work itself.
Retired — /ultracook no longer exists as a standalone skill. Any /ultracook invocation resolves to /cook, which now owns the single implementation pathway (including the fan-out mechanics this skill used to run). Use /cook instead.
Mark a checkpoint in the current conversation — compact it into a durable handoff document so a fresh agent can resume the work without context loss. Use when the user wants to preserve session state for a later or parallel session — phrases like "hand this off", "write a handoff", "drop a wheypoint", "checkpoint this", "compact the conversation", "I'm running low on context", "save where we are for the next session", "prep a handoff for another agent", "/wheypoint". Use even when the user just says "wrap up" or "I need to clear context" mid-task. Do NOT use for per-phase pipeline handoffs — those belong to `/cook`, `/press`, `/age`, and `/cure`.
Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types, concept tags, optional Telegram alerts, bot setup, worker restart, and startup-context verification. Use this whenever someone asks to customize what claude-mem remembers, create or change a mode, track domain-specific notes, add observation types or tags, or send Telegram notifications for particular memories—even if they do not use the word "mode."
Audits instrumentation health of existing Arize traces. Runs deterministic checks over a bounded span sample (orphaned/uncategorized/duplicate spans, flat structure, blank root I/O, unset status, missing token counts or children) and returns a ranked report. Use when the user asks why traces look empty/flat/broken, wants to verify instrumentation is healthy, find instrumentation issues, or why evals or token/cost dashboards show n/a or zero. To debug app behavior or errors, use arize-trace.
Selects, deploys, and customizes AI models on Amazon SageMaker. Fine-tuning (SFT, DPO, RLVR, RLAIF), model selection, dataset preparation, evaluation, deployment to SageMaker endpoints or Bedrock, and endpoint diagnostics. Covers the full lifecycle from planning through production. Use when fine-tuning models on SageMaker, selecting base models from SageMaker Hub, finding a model to deploy without fine-tuning, transforming datasets for training, checking data readiness, evaluating model quality, deploying to endpoints, setting up IAM roles and S3 buckets for training jobs, or managing a SageMaker Managed MLflow app. Also use to check endpoint health, diagnose failures, debug latency or errors, or view container logs and CloudWatch metrics. Covers Serverless Model Customization, Nova and OSS deployment paths, and PySDK v3 usage. NOT for Ground Truth labeling, Feature Store, or general-purpose AWS infrastructure.
Генерация фото, видео и аудио через VelsVisual CLI и KIE API (kie.ai). Используй, когда пользователь просит «сгенерируй картинку/изображение/фото/видео/музыку/песню/озвучку/голос/саунд-эффект», text-to-image, image-to-video, TTS или апскейл изображения.
Clearly restate a human's request so they can confirm alignment before work begins. Use when the human explicitly invokes /readback or $readback after a long, dictated, unclear, or complex prompt; never invoke automatically.