{"results":[{"identifier":"urn:ai:org.agntcy:cid:baeareiaxyjthvnpkk3fy4vkcmbvqy6rpligtg4uizqtax54de4ya5luogu", "displayName":"arize-annotation", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"compatibility":["Requires the ax CLI and a configured Arize profile."], "description":"Creates and manages annotation configs (categorical, continuous, freeform label schemas) and annotation queues (human review workflows) on Arize. Applies human annotations to project spans via the Python SDK. Use when the user mentions annotation config, annotation queue, label schema, human feedback, bulk annotate spans, update_annotations, labeling queue, annotate record, or human review.", "frontmatter_metadata":{"author":"arize", "version":"1.0"}, "name":"arize-annotation", "version":"1.0"}}, "version":"1.0", "description":"Creates and manages annotation configs (categorical, continuous, freeform label schemas) and annotation queues (human review workflows) on Arize. Applies human annotations to project spans via the Python SDK. Use when the user mentions annotation config, annotation queue, label schema, human feedback, bulk annotate spans, update_annotations, labeling queue, annotate record, or human review.", "tags":["oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T08:09:26Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareid73jhtwfbvhs227gr4y2biq4rcivvezcl3hvudfkcnkfdocm55ke", "displayName":"arize-ai-provider-integration", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"compatibility":["Requires the ax CLI and a configured Arize profile."], "description":"Creates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features. Supports any LLM provider (e.g. OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Vertex AI, Gemini, NVIDIA NIM). Use when the user mentions AI integration, LLM provider credentials, create integration, list integrations, update credentials, delete integration, or connecting an LLM provider to Arize.", "frontmatter_metadata":{"author":"arize", "version":"1.0"}, "name":"arize-ai-provider-integration", "version":"1.0"}}, "version":"1.0", "description":"Creates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features. Supports any LLM provider (e.g. OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Vertex AI, Gemini, NVIDIA NIM). Use when the user mentions AI integration, LLM provider credentials, create integration, list integrations, update credentials, delete integration, or connecting an LLM provider to Arize.", "tags":["oasf:1.0.0:domains:technology/cloud_computing", "oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:retrieval_augmented_generation/document_or_database_question_answering", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T08:09:18Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareihwcyyunjxvoyxkjtgpfo3jgroqhgtfyjpzsajtqxco5nlgusfxuq", "displayName":"ai-team-orchestration", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"description":"Bootstrap and run a multi-agent AI development team. Use when: starting a new software project with AI agents, setting up parallel dev/QA teams, creating sprint plans, writing brainstorm prompts with distinct agent voices, recovering a project workflow, or planning sprints.", "name":"ai-team-orchestration", "version":"v1.0.0"}}, "version":"v1.0.0", "description":"Bootstrap and run a multi-agent AI development team. Use when: starting a new software project with AI agents, setting up parallel dev/QA teams, creating sprint plans, writing brainstorm prompts with distinct agent voices, recovering a project workflow, or planning sprints.", "tags":["oasf:1.0.0:domains:technology/cloud_computing", "oasf:1.0.0:domains:technology/internet_of_things", "oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:agent_orchestration/multi_agent_planning"], "updatedAt":"2026-06-18T08:09:11Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareiadqc7hhhobtf6wdzilfmoggv3yvzojfpi7erb7v7wsm4q7eukqim", "displayName":"acreadiness-policy", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"description":"Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scoring, custom weights, CI gating, or wants org-wide standardisation.", "name":"acreadiness-policy", "version":"v1.0.0"}}, "version":"v1.0.0", "description":"Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scoring, custom weights, CI gating, or wants org-wide standardisation.", "tags":["oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T08:09:02Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareicytopcwcnivpnz3m6yz5rxl2m5uch4kbs2upoaspshr7n5gddu2a", "displayName":"acreadiness-generate-instructions", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"description":"Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.", "name":"acreadiness-generate-instructions", "version":"v1.0.0"}}, "version":"v1.0.0", "description":"Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.", "tags":["oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T08:09:02Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareid5okoeodop3u7allmi34sdbwbmkclc4rlhqdeuci2tfmmqlv3bre", "displayName":"digital-health-clinical-asr-build", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"compatibility":["NVIDIA_API_KEY (required) for hosted Magpie TTS via NVCF. DICTIONARY_API_KEY (optional) for Merriam-Webster Medical Dictionary lookup. Stage 1 (/digital-health-clinical-asr-setup) must have been completed first. All TTS, IPA, and synthesis recipes are inlined — no sibling agent skill required."], "description":"Stage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring (use /digital-health-clinical-asr-eval).", "frontmatter_metadata":{"- clinical-asr":"", "- dataset":"", "- flywheel":"", "- ipa":"", "- magpie":"", "author":"Ben Randoing <brandoing@nvidia.com>", "domain":"ai-ml", "next_skill":"digital-health-clinical-asr-eval", "previous_skill":"digital-health-clinical-asr-setup", "stage":"2", "tags":"", "team":"healthcare-tme"}, "license":"Apache-2.0", "name":"digital-health-clinical-asr-build", "version":"v1.0.0"}}, "version":"v1.0.0", "description":"Stage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring (use /digital-health-clinical-asr-eval).", "tags":["oasf:1.0.0:domains:healthcare/healthcare_informatics", "oasf:1.0.0:domains:healthcare/medical_technology", "oasf:1.0.0:skills:retrieval_augmented_generation/document_or_database_question_answering", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T02:13:40Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareicne5unccbmcvvo2cprfxzypwm4wj7ctgufvyym5jrfhfrj6o4mmy", "displayName":"dicom-series-to-volume", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"allowed_tools":["Bash"], "description":"Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.", "frontmatter_metadata":{"- DICOM":"", "- MedTech":"", "- NIfTI":"", "author":"NVIDIA MedTech Team", "tags":""}, "license":"Apache-2.0", "name":"dicom-series-to-volume", "version":"v1.0.0"}}, "version":"v1.0.0", "description":"Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.", "tags":["oasf:1.0.0:domains:technology/cloud_computing", "oasf:1.0.0:domains:technology/internet_of_things", "oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T02:13:34Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareibx7wibgy6mn4k4ivcuhxvprgfcgtc5qsoto6fknfkympg2idh4lu", "displayName":"dicom-series-preflight", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"allowed_tools":["Bash"], "description":"Used for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or clinical clearance.", "frontmatter_metadata":{"- DICOM":"", "- MedTech":"", "- preflight":"", "author":"NVIDIA MedTech Team", "tags":""}, "license":"Apache-2.0", "name":"dicom-series-preflight", "version":"v1.0.0"}}, "version":"v1.0.0", "description":"Used for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or clinical clearance.", "tags":["oasf:1.0.0:domains:healthcare/medical_technology", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T02:13:27Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareigqjfebnrcyvwrbdhygz6w57clrwszniq3746hyr3gpq34xpzui7q", "displayName":"dicom-metadata-extract", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"allowed_tools":["Bash"], "description":"Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.", "frontmatter_metadata":{"- DICOM":"", "- MedTech":"", "- metadata":"", "author":"NVIDIA MedTech Team", "tags":""}, "license":"Apache-2.0", "name":"dicom-metadata-extract", "version":"v1.0.0"}}, "version":"v1.0.0", "description":"Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.", "tags":["oasf:1.0.0:domains:healthcare/medical_technology", "oasf:1.0.0:skills:retrieval_augmented_generation/document_or_database_question_answering", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T02:13:18Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareibtuyaiyfn27artspw7x3djzx6ihqcdiy2zufswxvsbgxch3lvaca", "displayName":"deepstream-import-vision-model", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"description":">", "frontmatter_metadata":{"author":"NVIDIA CORPORATION", "version":"1.2.1"}, "license":"CC-BY-4.0 AND Apache-2.0", "name":"deepstream-import-vision-model", "version":"1.2.1"}}, "version":"1.2.1", "description":">", "tags":["oasf:1.0.0:domains:technology/data_science", "oasf:1.0.0:domains:technology/internet_of_things", "oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:images_computer_vision/object_detection"], "updatedAt":"2026-06-18T02:13:11Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareiaqdxe4oat2wkyh7jvro46hmub7goakc5zcp26sxm5bv3huf6flpu", "displayName":"deepstream-dev", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"description":"NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.", "license":"CC-BY-4.0 AND Apache-2.0", "name":"deepstream-dev", "version":"v1.0.0"}}, "version":"v1.0.0", "description":"NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.", "tags":["oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T02:13:04Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareib7vhl5hom4mtoedgmd7dxtbpi33tsljmjq2e2uehztkwn4seqsfe", "displayName":"data-designer", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"description":"Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.", "frontmatter_metadata":{"owner":"DataDesigner"}, "license":"Apache-2.0", "name":"data-designer", "version":"v1.0.0"}}, "version":"v1.0.0", "description":"Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.", "tags":["oasf:1.0.0:domains:technology/data_science", "oasf:1.0.0:skills:natural_language_processing/ethical_interaction"], "updatedAt":"2026-06-18T02:12:55Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareih3wqgvvpqtwpitbsosrurppb35qilg4hpnselyfnni6wnbnvgifi", "displayName":"dali-dynamic-mode", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"description":"DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.", "frontmatter_metadata":{"- dali":"", "- data-loading":"", "- data-processing":"", "- dynamic-mode":"", "- gpu-processing":"", "- ndd":"", "- python":"", "author":"DALI Team <dali-team@nvidia.com>", "domain":"deep-learning", "languages":"", "tags":"", "team":"dali"}, "license":"Apache-2.0", "name":"dali-dynamic-mode", "version":"v1.0.0"}}, "version":"v1.0.0", "description":"DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.", "tags":["oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T02:12:46Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareifzbglcaebjd57du6jcuuvfv6azmjuem6w5l3ykt5zps4k6oeu7qa", "displayName":"cupynumeric-parallel-data-load", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"compatibility":["linux-x86_64, linux-aarch64, darwin-aarch64, wsl-x86_64"], "description":"Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants. Use when no single-call loader fits, including when per-shard row counts differ across files. Prefer cupynumeric.load or legate.io.hdf5.from_file when they apply.", "frontmatter_metadata":{"- cupynumeric":"", "- data-loading":"", "- distributed":"", "- gpu":"", "- io":"", "- legate":"", "- parallel":"", "- sharded-data":"", "author":"NVIDIA Corporation <legate@nvidia.com>", "docs":"https://docs.nvidia.com/cupynumeric/latest/", "tags":"", "upstream":"https://github.com/nv-legate/cupynumeric", "version":"1.0.0"}, "license":"CC-BY-4.0 OR Apache-2.0", "name":"cupynumeric-parallel-data-load", "version":"1.0.0"}}, "version":"1.0.0", "description":"Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants. Use when no single-call loader fits, including when per-shard row counts differ across files. Prefer cupynumeric.load or legate.io.hdf5.from_file when they apply.", "tags":["oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T02:12:37Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareic5rv2i2exba2bfzcjyaewqbloqdcjusyx2skigwnbtarnai7tf54", "displayName":"cupynumeric-migration-readiness", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"compatibility":["Knowledge-driven assessment; no cuPyNumeric install required. Runtime claims target Linux x86_64/aarch64 with NVIDIA compute capability >= 7.0 and CUDA 12.x/13.x. Runtime validation is delegated to cuPyNumeric Doctor."], "description":"Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.", "frontmatter_metadata":{"- cupynumeric":"", "- distributed-computing":"", "- gpu":"", "- legate":"", "- numpy":"", "author":"NVIDIA Corporation <legate@nvidia.com>", "docs":"https://docs.nvidia.com/cupynumeric/latest/", "tags":"", "upstream":"https://github.com/nv-legate/cupynumeric", "version":"2.0.0"}, "license":"CC-BY-4.0 OR Apache-2.0", "name":"cupynumeric-migration-readiness", "version":"2.0.0"}}, "version":"2.0.0", "description":"Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.", "tags":["oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T02:12:29Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareiftjrwjrtmrvfh2jmweccuo5xgw2r2wnvmibqvq26dnvjn23dbi4e", "displayName":"cupynumeric-install", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"compatibility":["linux-x86_64, linux-aarch64, darwin-aarch64, wsl-x86_64"], "description":"Install and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.", "frontmatter_metadata":{"- conda":"", "- cupynumeric":"", "- distributed-computing":"", "- gpu":"", "- installation":"", "- legate":"", "- numpy":"", "author":"NVIDIA Corporation <legate@nvidia.com>", "docs":"https://docs.nvidia.com/cupynumeric/latest/installation.html", "tags":"", "upstream":"https://github.com/nv-legate/cupynumeric", "version":"2.0.0"}, "license":"CC-BY-4.0 OR Apache-2.0", "name":"cupynumeric-install", "version":"2.0.0"}}, "version":"2.0.0", "description":"Install and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.", "tags":["oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:natural_language_processing/information_retrieval_synthesis"], "updatedAt":"2026-06-18T02:12:21Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareihcpvmywosw5sts2jrsutrfjpgwgrs32rgqnuof3ycl5s3qinp5oi", "displayName":"cupynumeric-hdf5", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"compatibility":[">-"], "description":">-", "frontmatter_metadata":{"- cupynumeric":"", "- data-io":"", "- gpudirect-storage":"", "- h5py":"", "- hdf5":"", "- legate":"", "- parallel-io":"", "- scientific-data":"", "author":"NVIDIA Corporation <legate@nvidia.com>", "docs":"https://docs.nvidia.com/legate/latest/api/python/io/index.html", "tags":"", "upstream":"https://github.com/nv-legate/cupynumeric", "version":"2.0.0"}, "license":"CC-BY-4.0 OR Apache-2.0", "name":"cupynumeric-hdf5", "version":"2.0.0"}}, "version":"2.0.0", "description":">-", "tags":["oasf:1.0.0:domains:technology/cloud_computing", "oasf:1.0.0:domains:technology/internet_of_things", "oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:natural_language_processing/natural_language_generation"], "updatedAt":"2026-06-18T02:12:14Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareic75l6vjanudj6fegqsloirsxhtdcim5xmybgaeoagmfbel6dyrye", "displayName":"cuopt-user-rules", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"description":"Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuopt-developer for those.", "frontmatter_metadata":{"- cuopt":"", "- guidelines":"", "- user-rules":"", "author":"NVIDIA cuOpt Team", "tags":""}, "license":"Apache-2.0", "name":"cuopt-user-rules", "version":"v1.0.0"}}, "version":"v1.0.0", "description":"Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuopt-developer for those.", "tags":["oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T02:12:05Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareia2ikeywgldwwioqg332pbfuuuxylx4x3gtdf6hz2e5my3dafhjxu", "displayName":"cuopt-skill-evolution", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"description":"After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.", "frontmatter_metadata":{"- cuopt-skill-evolution":"", "- meta":"", "- workflow":"", "author":"NVIDIA cuOpt Team", "tags":""}, "license":"Apache-2.0", "name":"cuopt-skill-evolution", "version":"v1.0.0"}}, "version":"v1.0.0", "description":"After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.", "tags":["oasf:1.0.0:domains:technology/cloud_computing", "oasf:1.0.0:domains:technology/internet_of_things", "oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T02:11:59Z", "metadata":{}}, {"identifier":"urn:ai:org.agntcy:cid:baeareieocqnbpu7l2gccf3l46wybuh7ezbsjmej362uk6yzflhxf44l4fm", "displayName":"cuopt-server-common", "mediaType":"application/agentskill+md", "data":{"skill_file":"SKILL.md", "skill_manifest":{"description":"cuOpt REST server — what it does and how requests flow. Domain concepts; no deploy or client code.", "frontmatter_metadata":{"- concepts":"", "- cuopt":"", "- rest-api":"", "- server":"", "author":"NVIDIA cuOpt Team", "tags":""}, "license":"Apache-2.0", "name":"cuopt-server-common", "version":"v1.0.0"}}, "version":"v1.0.0", "description":"cuOpt REST server — what it does and how requests flow. Domain concepts; no deploy or client code.", "tags":["oasf:1.0.0:domains:technology/software_engineering", "oasf:1.0.0:skills:retrieval_augmented_generation/retrieval_of_information"], "updatedAt":"2026-06-18T02:11:52Z", "metadata":{}}], "nextPageToken":"MTA0MA"}