nemoclaw-maintainer-verify-stale
Verifies whether stale NVIDIA/NemoClaw bug reports still reproduce on the latest tag.
Skill by YYC-Cube
Chalk Labs
Need help deploying nemoclaw-maintainer-verify-stale?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/yyc-cube-nemoclaw-maintainer-verify-stale
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/nemoclaw-maintainer-verify-stale
What's inside
- Skill name
nemoclaw-maintainer-verify-stale- Description
- Verifies whether stale NVIDIA/NemoClaw bug reports still reproduce on the latest tag. Use when maintainers ask to verify stale issues, reproduce old bugs on latest, drain the bug backlog, or apply fixed-on-latest, verify-inconclusive, or status: wont-fix. Runs candidate filtering, local/Brev reproduction, by-design detection, confidence scoring, redacted comments, and tag-only labeling; never auto-closes.
- License
- Apache-2.0
- Instructions
- 57 lines in SKILL.md · view on GitHub
Files (7)
- SKILL.md
- brev-provisioning.md · reference/
- by-design.md · reference/
- candidate-selection.md · reference/
- environment-and-reproducer.md · reference/
- reproduction-rubrics.md · reference/
- scoring-comments-and-logging.md · reference/
SKILL.md (first lines)
<!-- SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. --> <!-- SPDX-License-Identifier: Apache-2.0 --> # NemoClaw Maintainer — Verify Stale Issues Automates the maintainer loop: choose an old bug, verify whether it still reproduces on the latest NemoClaw tag, then post an evidence-backed comment and label. It is tag-only: never close issues automatically. ## Progress checklist Copy this checklist and update it as you work: ```text Verify-stale progress: - [ ] Select issue(s), latest tag, and reported version - [ ] Apply skip/idempotency/active-discussion filters - [ ] Classify environment, provider, and bug class - [ ] Extract or synthesize a reproducer - [ ] Verify preconditions and try local-first if eligible - [ ] If Brev is needed, get plan approval before provisioning - [ ] Validate the reproducer on baseline, then verify latest - [ ] Check by-design/static-analysis branch when behavior was removed - [ ] Score, redact, draft, and self-verify comment links - [ ] Re-check issue state, post comment/label, update tracker when required - [ ] Append activity log entry ``` ## Workflow 1. **Select candidates and versions.** Read [reference/candidate-selection.md](reference/candidate-selection.md). Use it for single-issue mode, batch mode, latest-tag detection, filters, idempotency, active-discussion handling, and reported-version parsing. 2. **Classify and prepare.** Read [reference/environment-and-reproducer.md](reference/environment-and-reproducer.md). Use it for CPU/GPU/provider/bug-class classification, safe API-key handling, reproducer extraction, dependency checks, Brev auth, label checks, and local-first verification. 3. **Stop for approval before cost.** In batch mode, present one issue's plan and wait for maintainer approval before provisioning Brev. 4. **Provision and install.** If local-first does not settle the issue, read [reference/brev-provisioning.md](reference/brev-provisioning.md). Use it for Brev reuse/provisioning, reset, baseline/latest installs, dependency bootstrap, and `brev exec` footguns. 5. **Run the verification rubric.** Read [reference/reproduction-rubrics.md](reference/reproduction-rubrics.md). Use it to validate baseline behavior, retry with a synthesized reproducer if needed, run latest, handle architectural drift, and branch for performance or rebuild-cycle bugs. 6. **Check intentional changes.** If the symptom targets removed/deprecated behavior, read [reference/by-design.md](reference/by-design.md). Use static evidence to apply `status: wont-fix` only when the by-design branch self-verifies. 7. **Score, comment, label, and log.** Read [reference/scoring-comments-and-logging.md](reference/scoring-comments-and-logging.md). Use it for confidence scoring, redaction, concise templates, issue-state race checks, Project 199 movement, infra failures, and activity logging. ## Non-negotiables - Never auto-close an issue. Apply labels and ask a maintainer/reporter to confirm. - Never put API keys on a command line. Use the file-based pattern in `environment-and-reproducer.md`. - Never post unredacted transcripts, issue excerpts, synthesized scripts, internal hostnames, email addresses, or tokens. - Never post a comment with broken markdown links or tag-drifting `file:line` citations. Re-run cited commands and link-check at least one rendered link per comment section. - Never use Brev for unsupported platforms or integration-token issues in v1. - Keep comments concise: default to 200–300 words for fixed/by-design, 100–200 for inconclusive, and 30–80 for still-reproduces. ## Reference map | Need | Read | |---|---| | Candidate query, filters, version parser | [reference/candidate-selection.md](reference/candidate-selection.md) | | Environment classification, credentials, reproducer, preconditions, local-first | [reference/environment-and-reproducer.md](reference/environment-and-reproducer.md) | | Brev box reuse/provision, reset, installs, dependency bootstrap | [reference/brev-provisioning.md](reference/brev-provisioning.md) | | Baseline/latest matching, synth-repro, drift, performance, rebuild-cycle | [reference/reproduction-rubrics.md](reference/reproduction-rubrics.md) | | Static by-design/wont-fix branch | [reference/by-design.md](reference/by-design.md) | | Score, redact, comment, label, tracker move, infra handling, log | [reference/scoring-comments-and-logging.md](reference/scoring-comments-and-logging.md) |
From YYC-Cube/YYC3-NemoClaw, Apache-2.0.
More from YYC-Cube/YYC3-NemoClaw
- 0.468score
nemoclaw-user-get-started
YYC-Cube
Installs NemoClaw, launches a sandbox, and runs the first agent prompt.
SkillCFreshness: C★ 1Claude Code +9 - 0.468score
nemoclaw-maintainer-pr-comparator
YYC-Cube
Compares competing PRs that target the same issue and recommends which one to merge.
SkillCFreshness: C★ 1Claude Code +9 - 0.468score
nemoclaw-maintainer-triage
YYC-Cube
AI-assisted label triage for NVIDIA/NemoClaw issues and PRs.
SkillCFreshness: C★ 1Claude Code +9 - 0.468score
nemoclaw-user-configure-inference
YYC-Cube
Connects NemoClaw to a local inference server.
SkillCFreshness: C★ 1Claude Code +9 - 0.468score
nemoclaw-user-deploy-remote
YYC-Cube
Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow.
SkillCFreshness: C★ 1Claude Code +9 - 0.468score
nemoclaw-maintainer-cross-issue-sweep
YYC-Cube
Scans other open issues to find ones a given PR may also fix or accidentally break.
SkillCFreshness: C★ 1Claude Code +9 - 0.463score
nemoclaw-contributor-update-docs
YYC-Cube
Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages and refresh generated user…
SkillCFreshness: C★ 1Claude Code +9 - 0.463score
nemoclaw-contributor-create-pr
YYC-Cube
Create GitHub pull requests that follow the NemoClaw PR template.
SkillCFreshness: C★ 1Claude Code +9 - 0.463score
nemoclaw-maintainer-cut-release-tag
YYC-Cube
Creates deterministic NemoClaw semver release tags on origin/main and drafts release notes.
SkillCFreshness: C★ 1Claude Code +9 - 0.463score
nemoclaw-user-agent-skills
YYC-Cube
Describes the agent skills shipped with NemoClaw and how to access them by cloning the repository.
SkillCFreshness: C★ 1Claude Code +9 - 0.463score
nemoclaw-maintainer-release-notes
YYC-Cube
Drafts NemoClaw release notes from live GitHub tag and compare data.
SkillCFreshness: C★ 1Claude Code +9 - 0.463score
nemoclaw-maintainer-morning
YYC-Cube
Runs the morning maintainer standup for NemoClaw.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 4, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/YYC-Cube/YYC3-NemoClaw
- Website
- claw.yyc3.vip/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from YYC-Cube
- 0.549score
yyc3-ai-family-coding
YYC-Cube
YYC³ AI Family 编程体系 8-Agent 协同闭环开发。以「言启·千行、语枢·万物、预见·先知、千里·伯乐、元启·天枢、智云·守护、格物·宗师、创想·灵韵」8 位 AI 家人的角色分工与协同闭环,执行编程、架构设计、代码审查、技术选型、文档编写等软件开发任务。当用户提及任一成员名号、YYC³ AI…
SkillAFreshness: A★ 1Claude Code +9 - 0.536score
PPT内容生成
YYC-Cube
当用户需要撰写PPT演讲稿、生成演示大纲、组织演讲逻辑或丰富PPT内容时自动激活
SkillAFreshness: A★ 2Claude Code +9 - 0.534score
mcp-builder
YYC-Cube
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
SkillAFreshness: A★ 2Claude Code +9 - 0.534score
pdf
YYC-Cube
Use this skill whenever the user wants to do anything with PDF files.
SkillAFreshness: A★ 2Claude Code +9 - 0.529score
doc-coauthoring
YYC-Cube
Guide users through a structured workflow for co-authoring documentation.
SkillAFreshness: A★ 2Claude Code +9 - 0.529score
find-skills
YYC-Cube
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
SkillAFreshness: A★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get nemoclaw-maintainer-verify-stale running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
nemoclaw-maintainer-verify-stale skill. Agent Mart. https://agentmart.dev/skills/yyc-cube-nemoclaw-maintainer-verify-stale (last updated 2026-10-24)