Total 56,862 skills, AI & Machine Learning has 9456 skills
Showing 12 of 9456 skills
When the user wants to build or improve a sales bot's ability to introduce scarcity or time-sensitivity without being pushy. Also use when the user mentions "creating urgency," "scarcity," "time-sensitive offers," "limited availability," or "driving action."
How agentmemory is built, the iii engine primitives it runs on, its storage model, ports, and the viewer. Use when reasoning about how memory is stored or retrieved end to end, when extending the system, or when answering how agentmemory works under the hood.
Runs the DEFT embed-then-mine workflow for VCN AOI iterations — embeds the gap-analysis target parquet, embeds a source pool, and mines nearest-neighbour source images for downstream augmentation. Use as the immediate next step after `tao-route-visual-changenet-samples` when expanding a real-image augmentation queue from the mining subset.
Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
Performs gap analysis on NVIDIA TAO Visual ChangeNet (VCN) Classify experiments by invoking the data-services container (`tao_toolkit.data_services` from `versions.yaml`) directly via `docker run … gap_analysis vcn_aoi …` — picks the optimal decision threshold, ranks per-sample weakness, and emits a top-K weakest parquet expanded per-lighting for downstream augmentation. Use when analyzing VCN classification failures, picking SDA augmentation targets, auditing PASS/NO_PASS boundary cases, or running DEFT gap analysis on an AOI ChangeNet model.
Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable attention across camera views and time for end-to-end 3D perception, with an instance bank for temporal tracking. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Sparse4D model. Trigger phrases include "train Sparse4D", "multi-camera 3D detection", "temporal 3D tracker", "sparse query 3D perception".
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger. Do NOT use for: bug fixes, code review, documentation, refactoring, dependency updates, or single-file changes.
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.
Use at the start of any conversation—establishes how to find and use skills, requiring the Skill tool to be called before any response (including clarifying questions)
Third-party Claude Code token/context/code-review tools. Use when choosing or recommending an external tool to reduce token usage, manage context, or review large codebases.
A shared, file-based town square where multiple coding agents talk, coordinate, and debate — no server required. Use whenever more than one agent works the same repo (parallel Claude Code or Codex sessions, separate git worktrees, a fleet splitting a task) and they must stay out of each other's way or think together. TRIGGER on phrasings like "coordinate with the other agent/session", "post to / check the agora", "ask the other agents", "leave a message for whoever's working on X", "announce what files you're touching", "is anyone else editing this?", or any time you're about to edit shared code while other agents are live. Also trigger when an agent is stuck and wants a peer's second opinion, or when several agents each drafted a design (an API, a schema, an architecture) and the group needs to compare the proposals and converge on the best one. Works for any agent that can run a Python script, not just Claude Code.
THE workflow for picking up and carrying ONE ticket/card forward, for an autonomous worker agent or for a human doing it locally. Resolves the repo's tracker from the AFK registry (~/.claude/afk.json; GitHub Projects or Linear), picks one ticket by priority, routes by status x label (interview / human walkthrough / execute), loads LEARNINGS.md as binding constraints, implements test-first, verifies end-to-end and simplifies the diff (the /go finish), then branches to a PR for the reviewer. Use when the user says "pick up <id>", "work on issue <id>", invokes /engineer, invokes /pickup, says "pickup", or at the very start of working any card.