chore: skills signing batch 5#4466
Merged
Merged
Conversation
Collaborator
Author
|
/nvskills-ci |
Contributor
📝 WalkthroughWalkthroughAdds two new skills with comprehensive documentation and eval datasets (overview and reference), plus simplifies multiple existing eval JSON files by removing ChangesEvaluation Dataset Schema Simplification
NemoClaw User Overview Skill
NemoClaw User Reference Skill
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Suggested labels
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
Contributor
E2E Advisor RecommendationRequired E2E: None Dispatch hint: Full advisor summaryE2E Recommendation AdvisorBase: Required E2E
Optional E2E
New E2E recommendations
Dispatch hint
|
Contributor
E2E Scenario Advisor RecommendationRequired scenario E2E: None Full scenario advisor summaryE2E Scenario AdvisorBase: Required scenario E2E
Optional scenario E2E
Relevant changed files
|
Contributor
PR Review AdvisorFindings: 1 needs attention, 5 worth checking, 0 nice ideas Review findings🛠️ Needs attention
🔎 Worth checking
🌱 Nice ideas
Since last review detailsCurrent findings:
This is an automated advisory review. A human maintainer must make the final merge decision. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 8
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.agents/skills/nemoclaw-user-agent-skills/evals/evals.json:
- Line 6: The ground_truth string mixes pronouns/perspectives ("the user" and
"my AI coding assistant"); update the value of the ground_truth key in
evals.json to use a single consistent POV (e.g., change "my AI coding assistant"
to "their AI coding assistant") so the evaluation criterion is unambiguous;
locate the ground_truth property in
.agents/skills/nemoclaw-user-agent-skills/evals/evals.json and normalize the
phrasing accordingly.
In @.agents/skills/nemoclaw-user-get-started/evals/evals.json:
- Line 6: Update the eval rubric strings in
.agents/skills/nemoclaw-user-get-started/evals/evals.json to use neutral
third-person phrasing: replace first-person possessives like "my" with "their"
(e.g., in the "ground_truth" value and the other rubric strings referenced at
the same entries). Search for the JSON keys/strings that mention "my host" or
similar (including the "ground_truth" field and the other rubric entries
flagged) and edit them so each criterion consistently uses "the user" or "their"
instead of first-person wording.
In @.agents/skills/nemoclaw-user-overview/evals/evals.json:
- Line 6: Update the JSON "ground_truth" field to use a single, consistent
third-person perspective (prefer "their") instead of mixing first-person
("me/I/my") and third-person ("the user"); locate the "ground_truth" entries
(the string values flagged on lines 6, 18, 42, 48, 78, 90 in the evals.json
diff) and rewrite each sentence to replace "me/I/my" or "the user" with "their"
(or rephrase as needed) so the rubric language is unambiguous and consistent
across all occurrences.
In @.agents/skills/nemoclaw-user-reference/evals/evals.json:
- Line 24: The rubric strings in the JSON "ground_truth" fields mix third-person
and first-person pronouns; update any "ground_truth" entries that use "my" or
"I" to use consistent third-person phrasing (e.g., change "my operation" to "the
operation", "helps the user ... that owns my operation" to "helps the user ...
that owns the operation", and "I" to "the assistant" or rephrase into
third-person as appropriate). Locate these strings by searching for the
"ground_truth" key in the evals.json and apply the pronoun substitutions
consistently across all occurrences that contain first-person wording.
In `@skills/nemoclaw-user-overview/references/ecosystem.md`:
- Around line 16-18: Update the Mermaid node labels to remove emoji by editing
the three node definitions NC, OS, and OC (currently labeled NC["🦞 NVIDIA
NemoClaw<br/>CLI, plugin, blueprint"], OS["🐚 NVIDIA OpenShell<br/>Gateway,
policy, inference routing"], OC["🦞 OpenClaw<br/>Assistant in sandbox"]) and
replace them with plain-text labels such as NC["NVIDIA NemoClaw<br/>CLI, plugin,
blueprint"], OS["NVIDIA OpenShell<br/>Gateway, policy, inference routing"], and
OC["OpenClaw<br/>Assistant in sandbox"] so the diagram uses no emoji in
technical prose.
In `@skills/nemoclaw-user-overview/references/overview.md`:
- Line 8: Update the sentence in the overview content that reads "This enables
self-evolving claws to run more safely in clouds, on prem, RTX PCs and DGX
Spark." by replacing the phrase "on prem" with the hyphenated form "on-prem" to
match technical-doc consistency; edit the text in the markdown content
(overview.md) so it becomes "clouds, on-prem, RTX PCs and DGX Spark."
In `@skills/nemoclaw-user-overview/SKILL.md`:
- Line 3: Update the trigger keywords in the SKILL.md description to use the
required NVIDIA capitalization: replace the tokens "nvidia openshell" and
"nvidia nemotron" with "NVIDIA OpenShell" and "NVIDIA Nemotron" respectively
(these appear inside the description/trigger keywords string); ensure the rest
of the comma-separated keywords remain unchanged and that "NVIDIA" is all-caps
per project Markdown naming rules.
In `@skills/nemoclaw-user-reference/references/architecture.md`:
- Line 20: Remove emoji from the mermaid node labels so they comply with the "No
emoji in technical prose" rule: replace labels like USER(["👤 User"]):::user and
any other nodes containing emojis (e.g., the node with "🔒") with plain text
labels such as USER(["User"]):::user and the corresponding locking/security node
without emoji; update all occurrences noted (lines referenced in the review: the
nodes at the shown diff and the other instances) to use plain text only while
keeping the same node identifiers and classes.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: 8562b269-fb15-485d-8379-882bdadb8379
⛔ Files ignored due to path filters (1)
skills/nemoclaw-user-overview/references/images/nemoclaw-highlevel-component-diagram.pngis excluded by!**/*.png
📒 Files selected for processing (17)
.agents/skills/nemoclaw-user-agent-skills/evals/evals.json.agents/skills/nemoclaw-user-get-started/evals/evals.json.agents/skills/nemoclaw-user-overview/evals/evals.json.agents/skills/nemoclaw-user-reference/evals/evals.jsonskills/nemoclaw-user-overview/SKILL.mdskills/nemoclaw-user-overview/evals/evals.jsonskills/nemoclaw-user-overview/references/ecosystem.mdskills/nemoclaw-user-overview/references/how-it-works.mdskills/nemoclaw-user-overview/references/overview.mdskills/nemoclaw-user-overview/references/release-notes.mdskills/nemoclaw-user-reference/SKILL.mdskills/nemoclaw-user-reference/evals/evals.jsonskills/nemoclaw-user-reference/references/architecture.mdskills/nemoclaw-user-reference/references/cli-selection-guide.mdskills/nemoclaw-user-reference/references/commands.mdskills/nemoclaw-user-reference/references/network-policies.mdskills/nemoclaw-user-reference/references/troubleshooting.md
| "The output avoids inventing unsupported NemoClaw behavior.", | ||
| "The output follows progressive disclosure: it answers the current request without dumping unrelated details other than the expected_skill and the references/agent-skills.md file." | ||
| ] | ||
| "ground_truth": "A NemoClaw-specific answer that helps the user find a skill that can guide installation, policy, inference, or operations and gives enough concrete guidance, decision criteria, verification steps, or risk framing to delegate the right workflow to my AI coding assistant." |
Contributor
There was a problem hiding this comment.
Normalize mixed pronouns in ground_truth.
Line 6 mixes perspectives (the user + my AI coding assistant). Use a single POV (e.g., their AI coding assistant) to keep eval criteria unambiguous.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In @.agents/skills/nemoclaw-user-agent-skills/evals/evals.json at line 6, The
ground_truth string mixes pronouns/perspectives ("the user" and "my AI coding
assistant"); update the value of the ground_truth key in evals.json to use a
single consistent POV (e.g., change "my AI coding assistant" to "their AI coding
assistant") so the evaluation criterion is unambiguous; locate the ground_truth
property in .agents/skills/nemoclaw-user-agent-skills/evals/evals.json and
normalize the phrasing accordingly.
| "The output avoids inventing unsupported NemoClaw behavior.", | ||
| "The output follows progressive disclosure: it answers the current request without dumping unrelated details other than the expected_skill and the references/prerequisites.md file." | ||
| ] | ||
| "ground_truth": "A NemoClaw-specific answer that helps the user verify my host has the required hardware, software, and platform support and gives enough concrete guidance, decision criteria, verification steps, or risk framing to avoid a failed first setup." |
Contributor
There was a problem hiding this comment.
Use consistent third-person phrasing in eval rubric strings.
Lines 6, 42, and 60 mix the user with first-person terms (my). Please normalize to neutral third-person wording (their) for consistent scoring criteria.
Also applies to: 42-42, 60-60
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In @.agents/skills/nemoclaw-user-get-started/evals/evals.json at line 6, Update
the eval rubric strings in
.agents/skills/nemoclaw-user-get-started/evals/evals.json to use neutral
third-person phrasing: replace first-person possessives like "my" with "their"
(e.g., in the "ground_truth" value and the other rubric strings referenced at
the same entries). Search for the JSON keys/strings that mention "my host" or
similar (including the "ground_truth" field and the other rubric entries
flagged) and edit them so each criterion consistently uses "the user" or "their"
instead of first-person wording.
| "The output avoids inventing unsupported NemoClaw behavior.", | ||
| "The output follows progressive disclosure: it answers the current request without dumping unrelated details other than the expected_skill and the SKILL.md file." | ||
| ] | ||
| "ground_truth": "A NemoClaw-specific answer that helps the user understand what NemoClaw helps me run and why it exists and gives enough concrete guidance, decision criteria, verification steps, or risk framing to decide whether it is worth installing before I spend time on setup." |
Contributor
There was a problem hiding this comment.
Fix mixed first-person/third-person perspective in ground_truth.
Lines 6, 18, 42, 48, 78, and 90 combine the user with me/I/my. Keep a single perspective (prefer their) to avoid ambiguous rubric language.
Also applies to: 18-18, 42-42, 48-48, 78-78, 90-90
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In @.agents/skills/nemoclaw-user-overview/evals/evals.json at line 6, Update the
JSON "ground_truth" field to use a single, consistent third-person perspective
(prefer "their") instead of mixing first-person ("me/I/my") and third-person
("the user"); locate the "ground_truth" entries (the string values flagged on
lines 6, 18, 42, 48, 78, 90 in the evals.json diff) and rewrite each sentence to
replace "me/I/my" or "the user" with "their" (or rephrase as needed) so the
rubric language is unambiguous and consistent across all occurrences.
| "The output avoids inventing unsupported NemoClaw behavior.", | ||
| "The output follows progressive disclosure: it answers the current request without dumping unrelated details other than the expected_skill and the references/cli-selection-guide.md file." | ||
| ] | ||
| "ground_truth": "A NemoClaw-specific answer that helps the user pick the command surface that owns my operation and gives enough concrete guidance, decision criteria, verification steps, or risk framing to complete the task without breaking NemoClaw management." |
Contributor
There was a problem hiding this comment.
Standardize pronouns in rubric text.
Lines 24, 42, and 78 mix the user with first-person wording (my/I). Please switch to consistent third-person phrasing for cleaner evaluation criteria.
Also applies to: 42-42, 78-78
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In @.agents/skills/nemoclaw-user-reference/evals/evals.json at line 24, The
rubric strings in the JSON "ground_truth" fields mix third-person and
first-person pronouns; update any "ground_truth" entries that use "my" or "I" to
use consistent third-person phrasing (e.g., change "my operation" to "the
operation", "helps the user ... that owns my operation" to "helps the user ...
that owns the operation", and "I" to "the assistant" or rephrase into
third-person as appropriate). Locate these strings by searching for the
"ground_truth" key in the evals.json and apply the pronoun substitutions
consistently across all occurrences that contain first-person wording.
Comment on lines
+16
to
+18
| NC["🦞 NVIDIA NemoClaw<br/>CLI, plugin, blueprint"] | ||
| OS["🐚 NVIDIA OpenShell<br/>Gateway, policy, inference routing"] | ||
| OC["🦞 OpenClaw<br/>Assistant in sandbox"] |
Contributor
There was a problem hiding this comment.
Remove emoji from technical diagram labels.
Please replace the lobster/shell emoji in Mermaid node labels with plain text labels to satisfy the Markdown prose style rule.
As per coding guidelines, "No emoji in technical prose."
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@skills/nemoclaw-user-overview/references/ecosystem.md` around lines 16 - 18,
Update the Mermaid node labels to remove emoji by editing the three node
definitions NC, OS, and OC (currently labeled NC["🦞 NVIDIA NemoClaw<br/>CLI,
plugin, blueprint"], OS["🐚 NVIDIA OpenShell<br/>Gateway, policy, inference
routing"], OC["🦞 OpenClaw<br/>Assistant in sandbox"]) and replace them with
plain-text labels such as NC["NVIDIA NemoClaw<br/>CLI, plugin, blueprint"],
OS["NVIDIA OpenShell<br/>Gateway, policy, inference routing"], and
OC["OpenClaw<br/>Assistant in sandbox"] so the diagram uses no emoji in
technical prose.
| NVIDIA NemoClaw is an open-source reference stack that simplifies running [OpenClaw](https://openclaw.ai) always-on assistants more safely. | ||
| NemoClaw provides onboarding, lifecycle management, and OpenClaw operations within OpenShell containers. | ||
| It incorporates policy-based privacy and security guardrails, giving you control over your agents’ behavior and data handling. | ||
| This enables self-evolving claws to run more safely in clouds, on prem, RTX PCs and DGX Spark. |
Contributor
There was a problem hiding this comment.
Hyphenate “on-prem” for technical-doc consistency.
Use on-prem instead of on prem in this sentence.
🧰 Tools
🪛 LanguageTool
[grammar] ~8-~8: Use a hyphen to join words.
Context: ...g claws to run more safely in clouds, on prem, RTX PCs and DGX Spark. NemoClaw p...
(QB_NEW_EN_HYPHEN)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@skills/nemoclaw-user-overview/references/overview.md` at line 8, Update the
sentence in the overview content that reads "This enables self-evolving claws to
run more safely in clouds, on prem, RTX PCs and DGX Spark." by replacing the
phrase "on prem" with the hyphenated form "on-prem" to match technical-doc
consistency; edit the text in the markdown content (overview.md) so it becomes
"clouds, on-prem, RTX PCs and DGX Spark."
| @@ -0,0 +1,17 @@ | |||
| --- | |||
| name: "nemoclaw-user-overview" | |||
| description: "Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw versus integrating OpenShell and OpenClaw directly. Use when users ask about the relationship between OpenClaw, OpenShell, and NemoClaw, or when to use NemoClaw versus OpenShell. Trigger keywords - nemoclaw ecosystem, openclaw openshell, nemoclaw vs openshell, sandboxed openclaw, how nemoclaw works, nemoclaw sandbox lifecycle blueprint, nemoclaw overview, openclaw always-on assistants, nvidia openshell, nvidia nemotron, nemoclaw release notes, nemoclaw changelog." | |||
Contributor
There was a problem hiding this comment.
Normalize NVIDIA capitalization in trigger keywords.
nvidia openshell and nvidia nemotron should be NVIDIA OpenShell and NVIDIA Nemotron to comply with project-wide Markdown naming rules.
As per coding guidelines, "NVIDIA must be all caps (not Nvidia, nvidia)."
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@skills/nemoclaw-user-overview/SKILL.md` at line 3, Update the trigger
keywords in the SKILL.md description to use the required NVIDIA capitalization:
replace the tokens "nvidia openshell" and "nvidia nemotron" with "NVIDIA
OpenShell" and "NVIDIA Nemotron" respectively (these appear inside the
description/trigger keywords string); ensure the rest of the comma-separated
keywords remain unchanged and that "NVIDIA" is all-caps per project Markdown
naming rules.
| classDef external fill:#f5f5f5,stroke:#e0e0e0,color:#1a1a1a,stroke-width:1px | ||
| classDef user fill:#fff,stroke:#76b900,color:#1a1a1a,stroke-width:2px,font-weight:bold | ||
|
|
||
| USER(["👤 User"]):::user |
Contributor
There was a problem hiding this comment.
Remove emoji from diagram labels to satisfy docs policy.
The mermaid node labels include emoji (👤, 🔒), which violates the Markdown docs rule for technical prose.
Suggested diff
- USER(["👤 User"]):::user
+ USER(["User"]):::user
...
- subgraph SANDBOX["Sandbox Container 🔒"]
+ subgraph SANDBOX["Sandbox Container"]
...
- SANDBOX["Sandbox container 🔒<br/><small>Landlock + seccomp + netns<br/>OpenClaw agent + NemoClaw plugin</small>"]:::sandbox
+ SANDBOX["Sandbox container<br/><small>Landlock + seccomp + netns<br/>OpenClaw agent + NemoClaw plugin</small>"]:::sandboxAs per coding guidelines, "No emoji in technical prose."
Also applies to: 43-43, 94-94
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@skills/nemoclaw-user-reference/references/architecture.md` at line 20, Remove
emoji from the mermaid node labels so they comply with the "No emoji in
technical prose" rule: replace labels like USER(["👤 User"]):::user and any
other nodes containing emojis (e.g., the node with "🔒") with plain text labels
such as USER(["User"]):::user and the corresponding locking/security node
without emoji; update all occurrences noted (lines referenced in the review: the
nodes at the shown diff and the other instances) to use plain text only while
keeping the same node identifiers and classes.
Signed-off-by: nvskills-svc-account <svc-nvskills-signing@nvidia.com>
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@skills/nemoclaw-user-reference/skill-card.md`:
- Line 1: The file is missing the required SPDX header in HTML comment format;
add an SPDX license header (e.g. <!-- SPDX-License-Identifier: MIT --> with the
correct license identifier) at the very top of the Markdown file above the
existing content (above the "## Description" header) so the file complies with
the rule for "*.md" files to include SPDX headers.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: eae9738d-38ab-4d67-b34a-b288744f59c1
📒 Files selected for processing (6)
skills/nemoclaw-user-overview/BENCHMARK.mdskills/nemoclaw-user-overview/skill-card.mdskills/nemoclaw-user-overview/skill.oms.sigskills/nemoclaw-user-reference/BENCHMARK.mdskills/nemoclaw-user-reference/skill-card.mdskills/nemoclaw-user-reference/skill.oms.sig
✅ Files skipped from review due to trivial changes (5)
- skills/nemoclaw-user-reference/skill.oms.sig
- skills/nemoclaw-user-reference/BENCHMARK.md
- skills/nemoclaw-user-overview/skill.oms.sig
- skills/nemoclaw-user-overview/BENCHMARK.md
- skills/nemoclaw-user-overview/skill-card.md
| @@ -0,0 +1,55 @@ | |||
| ## Description: <br> | |||
Contributor
There was a problem hiding this comment.
Add required SPDX header at file top.
This Markdown file is missing the required SPDX header in HTML comment format.
Proposed fix
+<!-- SPDX-License-Identifier: Apache-2.0 -->
+
## Description: <br>
Describes the NemoClaw plugin and blueprint architecture and how they orchestrate the OpenClaw sandbox. <br>As per coding guidelines, "**/*.md: Markdown documentation files must include SPDX headers in HTML comment format".
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| ## Description: <br> | |
| <!-- SPDX-License-Identifier: Apache-2.0 --> | |
| ## Description: <br> |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@skills/nemoclaw-user-reference/skill-card.md` at line 1, The file is missing
the required SPDX header in HTML comment format; add an SPDX license header
(e.g. <!-- SPDX-License-Identifier: MIT --> with the correct license identifier)
at the very top of the Markdown file above the existing content (above the "##
Description" header) so the file complies with the rule for "*.md" files to
include SPDX headers.
jyaunches
approved these changes
May 28, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Related Issue
Changes
Type of Change
Verification
npx prek run --all-filespassesnpm testpassesnpm run docsbuilds without warnings (doc changes only)Signed-off-by: Your Name your-email@example.com
Summary by CodeRabbit
Documentation
Chores