Skills

Nemoclaw Maintainer Analyze PR Value Stream

Analyze one NemoClaw PR lifetime to identify contributor, review, and automation delays...

Install

npx skills add NVIDIA/NemoClaw --skill nemoclaw-maintainer-analyze-pr-value-stream -g -a claude-code -y
Repository
NVIDIA/NemoClaw22.9k
Category
Git and review
Updated
3d ago
License
Apache-2.0
Context cost
Lightabout 1,063 tokens
Runs scripts
No, instructions only

What it does

Analyze one NemoClaw PR lifetime to identify contributor, review, and automation delays or compare it with a latency target.

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

Analyze a Pull Request Value Stream

Run the deterministic read-only analyzer once for one pull request. Every invocation collects the complete observable retained lifetime. It writes a Perfetto-compatible trace, summary, and manifest under .nemoclaw-maintainer/pr-value-stream/pr-<number>/ and emits the summary as bounded JSON on stdout.

Do not run a reduced or latest-revision-only analysis. The latest-revision waterfall remains one derived part of the complete lifetime result.

Prerequisites

  • Run from a NemoClaw checkout with authenticated gh access.
  • Use Node.js 22.19 or later with type stripping enabled.
  • Retained Vitest artifact timing is conditional: install this checkout's dependencies so node_modules/vitest/vitest.mjs is available, and install zipinfo and unzip. Optional artifact failures appear in caveats and do not become test-timing evidence.

Run the analysis

node --no-warnings \
  .agents/skills/nemoclaw-maintainer-analyze-pr-value-stream/scripts/analyze-pr-value-stream.mts \
  --workdir "$PWD" \
  --number <pull-request-number>

The default repository is NVIDIA/NemoClaw. Use --repository OWNER/REPO only when the user requests another repository. The ten-minute target defaults to 10; use --target-minutes only when the user requests another target.

The analyzer owns completeness and safety bounds. Do not use legacy pagination or truncation options to reduce the standard analysis. If required retained history exceeds a bound, the command fails rather than calling a partial trace complete.

Outputs

A successful invocation writes:

Read the whole SKILL.md on GitHub

More in Git and review