Automate Adrapid tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Addresszen tasks via Rube MCP (Composio). Always search tools first for current schemas.

Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.

Verify completed implementation against the plan. Checks that all tasks were implemented, nothing was forgotten, code compiles, tests pass, and quality standards are met. Use after "/aif-implement" completes, or when user says "verify", "check work", "did we miss anything".

Generate CI/CD pipeline (GitHub Actions / GitLab CI) with linting, static analysis, tests, security. Use when user says "ci", "setup ci", "github actions", "gitlab ci", "pipeline".

Guides the user through an interactive conversation to define their research project, then generates research_brief.json and tasks.json. Use when starting a new project, when no research_brief.json exists, when the user wants to start from a specific pipeline stage, or when the user wants to redefine their research pipeline.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.

Trigger `skvm jit-optimize` with post-task evidence so it generates a reviewable optimization proposal for a skill. Use after finishing a task that was driven by any skill (not just SkVM-compiled ones) when the outcome was a failure, was partial, or the skill's instructions clearly caused confusion or an unnecessary detour. Clean successful runs usually do not need an optimization pass. For general skvm usage (profile/aot-compile/bench/proposals), use the sibling `skvm-general` skill instead.

Fetch a region of cis-eQTL summary statistics from EBI eQTL Catalogue v7+ via tabix-on-FTP. Use when an agent needs eQTL beta / SE / p-value for every variant in a window around a gene's TSS for one specific dataset (study × tissue × quantification method). Input: dataset_id, chromosome, start, end, optional molecular_trait_id. Output: harmonised TSV slice.

Orchestrator that runs first for lead generation requests. Gathers business context via website analysis or questions, identifies competitors, builds ICP, and routes to signal skills with pre-filled inputs.

Generate a voiceover (VO) clip via ElevenLabs text-to-speech, ROUTED THROUGH THE elevenlabs-proxy so it bills the Ads agent. Voice id + script text come from the template recipe. Use for the spoken narration of VO-driven video-ad formats (cgi-app-sizzle, flat-vector-explainer, hypermotion). Never call ElevenLabs directly — the proxy attribution is required.

Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a `source-sample.json` in the exact shape the `upload-ad-sample` skill writes to the Goose Ads library. Also links every character and voice to the central character library at `<repo-root>/assets/character-library/` (repo-root derived from the run-dir, not a hardcoded path), and if a character isn't in the library yet, adds it first then links. Use when the user wants to remix one of their existing ads — this skill produces the source JSON that the script-rewriting step and `remix-ad` consume.

Assemble an absurdist animated-explainer video ad (~38s, 9:16) from per-scene i2v clips + their measured VO windows — retime each clip to its VO, re-encode every segment to identical 30fps/libx264/yuv420p so the concat demuxer never drops frames, concat, build a REAL-product PIL end card (never AI) with a slow Ken-Burns, mix VO (loudnorm I=-14) under music (loudnorm I=-26, volume 0.62, amix normalize=0), and burn libass captions last. FREE deterministic assembly (bash-free, Python + ffmpeg + PIL); the recipe supplies the clips, VO, music, product photo, palette, and caption table and gates the paid keyframe/clip/VO/music calls to their own capabilities. Use for the absurdist-explainer format.

Use when running or scheduling periodic repository review cycles that must dispatch the correct reviewer, aggregate findings, and escalate outcomes into reports, issues, or corrective PRs across API contracts, documentation freshness, code quality, and CloudBase skill quality.

Create a Discord-ready Neva release announcement from a GitHub release payload. Use for official Neva Discord release posts.

CodeStable skill authoring and evolution protocol. Use when creating, refactoring, simplifying, or reviewing cs-* skills under plugins/codestable/skills or .claude/skills. Produces a thin harness, an explicit context plan, evidence gates, and an optional agent collaboration contract. Do not use for product implementation; use eval-cs-skill only for measured experiment loops.

Use when evaluating whether a skill belongs in a library. Preview content, check frontmatter, validate structure, and decide whether to keep, curate, or remove.