Skip to content
cccskills
FreePublished on GitHub

nemoclaw-contributor-onboard

Prepare a local NemoClaw development environment, repair setup problems, or check readiness. It also handles explicitly requested command-line access, runtime onboarding, and launching the coding agent pinned by the project.

OriginalShow the original description

Set up, repair, or check a NemoClaw contributor checkout. Also handles requested development CLI exposure, runtime onboarding, and pinned-agent launch.

See how to install

Good for

  • Setting up a local NemoClaw development environment
  • Checking readiness before starting development
  • Repairing local dependency, build, or hook problems
  • Enabling CLI access or runtime onboarding with approval

Files included (3)

  • SKILL.md5.7 KB
  • agents/openai.yaml385 B
  • evals/evals.json3.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

<!-- SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. --> <!-- SPDX-License-Identifier: Apache-2.0 -->

Onboard a NemoClaw Contributor

Use the repository setup script as the executable source of truth. Do not duplicate its dependency, build, hook, CLI-exposure, or readiness logic in agent commands.

Establish Trust First

  1. Read the root AGENTS.md and CONTRIBUTING.md completely.
  2. Inspect the worktree and current branch without discarding or overwriting existing changes.
  3. Refresh the trusted origin/main reference, then compare the entire checkout/worktree diff against that up-to-date base before executing any checkout-local code. Include staged, unstaged, and untracked files; review lockfiles and all transitively executed source, not only the entry script or package manifests.
  4. If an execution surface differs from trusted origin/main, review the diff before running it. Existing implementation authorization covers in-scope repository-local validation. Isolate candidate code from host credentials and host mutations. This includes setup scripts and installed hooks. Stop before execution if that isolation cannot be established. Ask only for exposure or side effects outside that authorization.

Route by Intent

  • Readiness only: run ./scripts/dev-setup.sh --doctor and never run setup, repair, CLI exposure, runtime onboarding, or the pinned agent. Use ./scripts/dev-setup.sh --doctor --json when a machine-readable report helps.
  • Initial checkout setup: run ./scripts/dev-setup.sh from the repository root.
  • Explicit repository repair: run ./scripts/dev-setup.sh --repair only when the user asks to repair or retry repository-local setup.
  • CLI exposure: after explicit approval, run ./scripts/dev-setup.sh --expose-cli.
  • Runtime onboarding: after explicit approval, run ./scripts/dev-setup.sh --with-runtime.

The default and repair modes may update repository-local dependencies, builds, hooks, and the root Python environment. They must not create a gateway or sandbox or expose a host-visible nemoclaw command. CLI exposure is an explicit opt-in that may use an npm link or a user-local shim.

Handle User-Controlled Changes

Require explicit authorization before installing or changing host packages, starting or replacing a container runtime, accepting a license, generating or registering a signing key, changing GitHub state, or changing global Git configuration. Use authorization already supplied for that action and scope; ask only when it is missing.

  • Ask for contributor name and email only when the doctor reports that identity is missing.
  • Prefer repository-local Git identity changes when the user approves them.
  • Use gh auth login -h github.com for missing GitHub authentication and pause for browser or device authentication.
  • Let the user choose and register a Git-supported commit-signing key.
  • Follow ../_shared/git-github-hard-stop.md for authentication, authorization, SSH, remote-access, or push failures.
  • Never print tokens, credential values, private keys, or command output that may contain them.
  • Never place secrets in command arguments, generated reports, or tracked files.

After an approved host, account, identity, or signing remediation, rerun npm run dev:doctor or ./scripts/dev-setup.sh --doctor instead of rerunning setup. Reserve setup and --repair for repository-local dependency, build, or hook repair.

Decide on Runtime Onboarding

Determine whether the intended issue requires a live gateway or sandbox from its validation boundary. Ask only if that need or the authorization for it is unresolved. Documentation work and isolated unit tests normally do not require runtime onboarding.

If runtime validation is required and the user approves it, run:

./scripts/dev-setup.sh --with-runtime

This delegates to interactive nemoclaw onboard and also opts into development CLI exposure as part of that approved flow. Do not preselect third-party software acceptance, inference provider or model, credentials, sandbox name or resources, messaging integrations, or network policy unless the user already supplied those decisions.

Launch the Pinned Agent Only on Request

When the user specifically asks to use the repository-pinned coding agent, run the doctor first. If readiness fails, report the remediation and obtain authorization for the matching setup or repair mode rather than mutating the checkout automatically. When readiness passes, run:

npm run agent

Pass user-supplied Pi arguments after --. Do not install or invoke a global Pi binary.

Hand Off to the Contributor Lifecycle

This workflow ends after the doctor reports that every contributor-readiness check passes and every approved CLI-exposure, runtime-onboarding, or pinned-agent step is complete. Name the workflow that owns the next stage instead of restating its rules:

  • nemoclaw-contributor-plan-issue refines an issue into capability slices.
  • nemoclaw-contributor-implement-issue implements a slice and owns its tests.
  • nemoclaw-contributor-create-pr publishes the change and owns the branch-state, commit-verification, DCO, template, and review follow-up requirements.

Do not create a branch, commit, push, or PR unless the user's request includes that action.

Report the Result

Summarize repository-local setup performed, doctor status, user-controlled remediations still needed, whether CLI exposure or runtime onboarding ran, and the next safe contributor action.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Publish or update a NemoClaw pull request and track automated checks and reviews through completion. It preserves the requested scope, coordinates repairs for valid findings, and reports the latest commit’s results and remaining blockers.

  • Publishing implemented changes as a pull request
  • Updating an open pull request after review feedback
  • Tracking automated checks and reviews on the latest commit
NVIDIA/NemoClaw22.8KUpdated Oct 22, 2026

Implement an accepted NemoClaw issue or repair a classified pull request finding. Keep changes within the agreed scope, run focused checks for affected behavior, and review the final changes before handing evidence to an authorized publication workflow.

  • Implement an accepted issue within its agreed scope
  • Repair a classified pull request finding
  • Validate failure, recovery, and cleanup behavior
NVIDIA/NemoClaw22.8KUpdated Oct 22, 2026

Turn a named NemoClaw issue into an implementation plan with clear ownership, scope, completion criteria, and validation evidence. For larger changes, define independently useful steps, their dependencies, and delivery order.

  • Plan implementation for a named issue
  • Divide a large change into useful steps
  • Define acceptance criteria and test evidence
NVIDIA/NemoClaw22.8KUpdated Oct 22, 2026

Audit and upgrade NemoClaw dependencies, including Hermes and base images. Trace upstream changes to affected code, implement required migrations, and verify tests, distributed artifacts, and the versions actually selected for use.

  • Assess the impact of a dependency upgrade
  • Plan migrations for a Hermes upgrade
  • Verify base images and selected artifacts
NVIDIA/NemoClaw22.8KUpdated Oct 22, 2026

Update NemoClaw documentation after merged changes or audit it for outdated guidance. Verify current behavior against source and tests, edit the pages responsible for that guidance, and check affected links and generated variants.

  • Catch up documentation after merged changes
  • Audit documentation for outdated guidance
  • Update guides for changed user behavior
NVIDIA/NemoClaw22.8KUpdated Oct 22, 2026

Analyze saved NemoClaw CI timings to rank consistently slow command-line tests and compare base-image publication with reuse. Read-only analyzers report execution times, runner queues, and sample coverage as bounded JSON output.

  • Finding consistently slow command-line tests
  • Ranking test files by execution time
  • Comparing base-image publication with reuse
NVIDIA/NemoClaw22.8KUpdated Oct 22, 2026

See all skills by NVIDIA

Report a problem with this skill