add-library-railStep-by-step contribution guide for adding a new rail to nemoguardrails/library/: manifest, actions returning RailOutcome, config schema, flows, HTTP rules for vendor backends, Python package requirements, unit and recorded tests, docs and examples. Use when…recorded-testsDecides when a code change requires a recorded/VCR test, whether a test belongs in tests/recorded/ or the plain unit suite under tests/, and how to structure it in either place. Use when adding, reviewing, or relocating tests that involve LLM calls,…review-library-railReview a pull request that adds or modifies a rail in nemoguardrails/library/ (built-in or vendor guardrail integration). Runs the mechanical gates first, then judgment dimensions tests cannot check (privacy honesty, retry semantics, fail-closed behavior,…guardrails-developer-create-guardrailsHelps developers create a NeMo Guardrails configuration for an LLM application. Use when users want to build, scaffold, configure, test, or iterate on input, output, retrieval, dialog, execution, Colang, or catalog-based guardrails. Trigger keywords - create…guardrails-developer-guideRoutes NVIDIA NeMo Guardrails library product-usage questions to the canonical documentation. Use when users ask how to install, configure, integrate, evaluate, observe, deploy, troubleshoot, or use the NVIDIA NeMo Guardrails library. Trigger keywords -…
explorador de repositórios
NVIDIA-NeMo · Repositórios e skills representativas - Página 2
Visão por repositório de 323 skills coletadas em 27 repositórios do GitHub.
getting-startedSet up NeMo Curator for data curation (text, image, video, audio)audio-curationBuild and run a NeMo Curator audio curation pipeline from a natural-language goal (host-driven planner over the audio_agent tool core). Use for any audio, speech or audio-dataset task - quality filtering, transcription, WER filtering, VAD, diarization, ALM…audio-stage-authoringMake a new or existing NeMo Curator audio stage agent-ready so the audio agent can discover, configure and chain it. Use when adding an audio stage, writing or fixing its describe() contract or StageContract, adding *_key fields or semantic roles, writing a…checkpoint-placementSelect a core-proven metadata checkpoint for same-dataset parameter feedback. Use after recipe validation and semantic critique, before authoritative smoke, when the user expects to tune a declared downstream decision after seeing results.nemo-curator-docsMaintain the NeMo Curator Fern docs site — add, update, move, or remove pages under fern/. Use for any documentation changes.
github-cliInteract with the Safe-Synthesizer GitHub repository using the gh CLI. Activate when users want to list or create pull requests, check out PRs, work on someone else's PR, check CI status, investigate workflow failures, view job logs, create or triage issues,…uv-builduv package management, dependency groups, PyTorch index handling, hatch build system, and versioning for this repo. Triggers on: uv, uv sync, uv lock, uv add, uv build, dependency, pyproject.toml, extras, cpu, cu129, hatch, wheel, version, publish.git-worktreesCreate, clean up, or prune isolated Safe-Synthesizer git worktrees for feature development, PR review, and parallel branches across Cursor, Claude Code, Codex, and plain shells.safe-synthesizerUse NeMo Safe Synthesizer through task-specific routing: running the CLI or SDK, configuring parameters, troubleshooting runtime failures, inspecting artifacts, and interpreting evaluation outputs. Use when the user asks about safe-synthesizer, NeMo Safe…
lens-reviewReviews pending changes in the NeMo Lens repo against the library's load-bearing invariants — SDK-import isolation, hot-path gating, fallback signature parity, span-group and preset placement, semconv naming, value classification, test state isolation, and…lens-respond-to-issueResearch and draft a maintainer response to a GitHub issue or community question on the NeMo Lens repo. Grounds the answer in the actual code and docs, verifies every citation, and hands the draft back for approval rather than posting it.lens-create-issueInvestigate a failing GitHub Actions run or job in the NeMo Lens repo and file a well-structured GitHub issue for the failure. Covers log extraction for each of this repo's CI jobs, duplicate detection, triggering-PR resolution, and assignee lookup.lens-pre-pr-checkRuns the full local gate before opening or updating a pull request in the NeMo Lens repo — tests, lint, pre-commit, copyright headers, docs registration, commit sign-off, and PR title conventions. Catches the failures this repo's CI is known to reject.
eval-authorBuild first evals from a required Ethos, work on existing evaluation suites in a user's repository, derive an environment from trace evidence (experimental), or understand an agent run from NeMo Intake. Owns the evidence standard that every Eval Author…eval-author-discoverRecord whether a repository's Harbor and NeMo Gym evaluations are ready to run, proven in four phases rather than guessed. Probe finds the installed runtimes, Explore finds job configs, datasets, task directories, and Gym manifests, Judge has Harbor and Gym…eval-author-auditGuide coverage audits with milestone check-ins and user-confirmed eval and trace sources. Generate, validate, measure, and report on an audit-spec coverage denominator for Eval Author. Use when the user wants a hand-editable audit.md file derived from Ethos,…ethosExplore an agent's code and documentation, confirm its intended behavior with the user, and create or update a local ETHOS.md for evaluation and trace analysis. Use when capturing an agent's purpose, boundaries, success criteria, or change permissions.
pr-reviewReview Molt pull requests for critical bugs, test coverage, and documentation affected by the change.train-inference-consistencyMake molt's training forward produce bitwise-identical per-token logprobs to vLLM's rollout (true on-policy RL) for a given model, validate it with the gate workflow (C0–C10), diagnose train/rollout mismatch, and recover throughput to within the 20 % rollout…
eval-result-analyzerAnalyze a NeMo-Voice-Agent eval result directory and produce a thorough structured report. Reads every artifact under the run directory (judge_result.json, final_agent_response.json, final_scenario_db_hash.txt, metrics.json,…pr-reviewReview NeMo Voice Agent pull requests for critical bugs, test coverage, and affected documentation.
review-codeReview a Data Designer Plugins branch or GitHub pull request for correctness, plugin contracts, packaging, and test coverage. Use when asked for a code review.data-designer-plugin-authoringUse when creating, updating, documenting, or preparing a pull request for a Data Designer plugin in the NVIDIA-NeMo/DataDesignerPlugins repository, including ddp scaffolding, plugin implementation, validation, and per-plugin Zensical docs.