NVIDIA/nemoclaw-community

geometry-fidelity-policy

Mandatory acceptance policy for source-referenced CAD reconstruction; separates geometric fidelity from structural and persistence checks.

Langue du texte source : anglais

kubernetes-sre

Inspect Kubernetes or OpenShift resources and perform only the mutations exposed by the chart-managed SRE API proxy.

Langue du texte source : anglais

openshift-llm-deploy

Use when inspecting GPU/model capacity, live GPU utilization, GPU memory, power or temperature telemetry, model serving metrics such as queue depth, KV-cache usage or request latency, Prometheus/Thanos metric queries, model Routes or NodePorts, OpenShell…

Langue du texte source : anglais

memory-consolidation

Keep the memory inside its size limits by compacting rather than truncating, so it stays readable as it ages.

Langue du texte source : anglais

memory-repair

Check the memory against its schema and fix what can be fixed, so the store degrades visibly rather than silently.

Langue du texte source : anglais

memory-writing

Create and update the memory pages that the ranking job gates its top tier on, from evidence the selector collected.

Langue du texte source : anglais

preference-update

Update a bounded preference policy from the user's repeated corrections, without ever overwriting the user's own choices.

Langue du texte source : anglais

outlook-email-search

Search the Outlook mailbox via Microsoft Graph to find and read emails that help answer user questions.

Langue du texte source : anglais

setup-workshop-nemoclaw-operator

Operator/host side of running the NVIDIA "Build an Agent" DevX workshop inside an OpenShell/NemoClaw sandbox. In the NemoClaw community repo this is the PRIMARY workshop-setup entry point: use it for "set up / run the Build-an-Agent workshop" requests when…

Langue du texte source : anglais

setup-workshop-nemoclaw

Set up the NVIDIA "Build an Agent" DevX workshop as a working JupyterLab environment from INSIDE a locked-down OpenShell/NemoClaw sandbox, and hand the user the token URL + access commands. This is the PRIMARY workshop-setup path in the NemoClaw community…

Langue du texte source : anglais

nemoclaw-nvteam

Route product, program, engineering, data and ML, quality, SRE, security, and developer-community work through the eight local role lenses packaged with the developer-community-chief-of-staff recipe in nemoclaw-community. Use for explicit NVTeam or persona…

Langue du texte source : anglais

outlook-email-search

Search the Outlook mailbox via Microsoft Graph to find and read emails that help answer user questions.

Langue du texte source : anglais

vss-video

Use when a question is about what happens in a video file or clip. Puts the clip in front of NVIDIA RT-VLM and reports timestamped, grounded findings.

Langue du texte source : anglais

nemoclaw-hermes-swarm

Use when deploying Hermes bots in NemoClaw sandboxes. Bring up, extend, verify, and debug a sandboxed bot swarm with ./swarm.

Langue du texte source : anglais

nemoclaw-community-contributor-examples

Guide NemoClaw Community contributors through classifying, naming, adding, moving, renaming, and reviewing repository examples. Use when work affects examples, recipes, partner contributions, field demos, developer tools, catalog collections, category…

Langue du texte source : anglais

nemoclaw-community-maintainer-policies

Provide read-only NemoClaw Community maintainer policy for Issue Type, labels, title conventions, triage, and example publication metadata.

Langue du texte source : anglais

module-6

This skill should be used when a learner is working through Module 6 ("Agent Safety") of the Build-an-Agent workshop and wants help understanding the concepts, the code, or the NemoClaw stack — e.g. "/module-6 why isn't HITL or a container enough?",…

Langue du texte source : anglais

pr-test-case-assistant

Read public GitHub pull requests, produce a short triage brief, and draft feature test cases grounded in the pull request description and diff. Use when a Slack user provides a public GitHub repository or pull request.

Langue du texte source : anglais

cross-source-gap-analysis

Compare findings across Slack, GitHub, NVIDIA forums, and Outlook to identify alignment gaps, missing coverage, and follow-ups.

Langue du texte source : anglais

github-readonly-live

Read the configured live GitHub repository through authenticated, policy-scoped GitHub REST GET requests.

Langue du texte source : anglais

nemoclaw-autoheal

Guide users through Hermes availability checks and the optional host-side auto-heal setup without crossing the sandbox-to-host boundary.

Langue du texte source : anglais

nemoclaw-nvteam

Route product, program, engineering, data and ML, quality, SRE, security, and developer-community work through the eight local role lenses packaged with the developer-community-chief-of-staff recipe in nemoclaw-community. Use for explicit NVTeam or persona…

Langue du texte source : anglais

slack-channel-finder

Discover Slack channels by topic, team, or domain and determine the channel ID.

Langue du texte source : anglais

slack-channel-summarizer

Read and summarize Slack channel history from inside the NemoClaw sandbox.

Langue du texte source : anglais

source-etl-query

Query the host-side source-etls REST mirror for GitHub discussions, historical GitHub mirror data, and NVIDIA forums research.

Langue du texte source : anglais

module-1

This skill should be used when a learner is working through Module 1 ("Build an Agent") of the Build-an-Agent workshop and wants help understanding the concepts, notebooks, or code — e.g. "/module-1 what are agents?", "/module-1 explain the ReAct pattern",…

Langue du texte source : anglais

module-2

This skill should be used when a learner is working through Module 2 ("Agentic RAG") of the Build-an-Agent workshop and wants help understanding the concepts, code, or how to run it — e.g. "/module-2 what is agentic RAG?", "/module-2 explain chunking and…

Langue du texte source : anglais

module-3

This skill should be used when a learner is working through Module 3 ("Agent Evaluation") of the Build-an-Agent workshop and wants help understanding the concepts, the code, or interpreting their results — e.g. "/module-3 what is faithfulness?", "/module-3…

Langue du texte source : anglais

module-4

This skill should be used when a learner is working through Module 4 ("Agent Customization") of the Build-an-Agent workshop and wants help understanding the concepts, the code, training, or GPU issues — e.g. "/module-4 should I train my agent or just prompt…

Langue du texte source : anglais

module-5

This skill should be used when a learner is working through Module 5 ("Deep Agents") of the Build-an-Agent workshop and wants help understanding the concepts, the code, or sandboxing — e.g. "/module-5 what are deep agents?", "/module-5 explain the four…

Langue du texte source : anglais

module-7

This skill should be used when a learner is working through Module 7 ("Agent Harnesses & Skills") of the Build-an-Agent workshop and wants help understanding the concepts, the harness landscape, the lab code, or portable/GPU skills — e.g. "/module-7 what is a…

Langue du texte source : anglais

workshop

This skill should be used when a learner wants to navigate or understand the Build-an-Agent workshop as a whole — e.g. "/workshop where do I start?", "what order should I do the modules in?", "what does Module 3 need before I start?", "which module covers RAG…

Langue du texte source : anglais

axe-a11y

Automated web accessibility scanning (axe-core) driven by patchright + real Google Chrome — audits sites behind bot walls and behind auth

Langue du texte source : anglais

inbound-judging

Decide which newly-arrived email and Slack messages create an obligation for the user, and craft the row that represents each one.

Langue du texte source : anglais

obligation-review

Re-judge open obligations against their current state in the world and re-rank them, on a schedule that does not depend on new mail arriving.

Langue du texte source : anglais

gitlab-readonly-live

Read one of the configured GitLab projects through authenticated, policy-scoped REST GET requests.

Langue du texte source : anglais

public-web-search

Search the current public web through the recipe's optional, policy-scoped Tavily integration and return cited titles, URLs, snippets, and search metadata. Use for current public information that is not available from the configured Slack, Outlook, GitHub, or…

Langue du texte source : anglais

cross-source-gap-analysis

Compare findings across Slack, GitHub, NVIDIA forums, and Outlook to identify alignment gaps, missing coverage, and follow-ups.

Langue du texte source : anglais

github-readonly-live

Read an allowed live GitHub repository through authenticated, policy-scoped GitHub REST GET requests.

Langue du texte source : anglais

source-etl-query

Query the host-side source-etls REST mirror for GitHub discussions, historical GitHub mirror data, and NVIDIA forums research.

Langue du texte source : anglais