source-etl-query
Skill142 starsChanged 3 months agoApache-2.0View on GitHub
Query the host-side source-etls REST mirror for GitHub discussions, historical GitHub mirror data, and NVIDIA forums research.
In this repository62 other files it gives its agents.
- examples/recipes/partners/hpe/retail-assistant/docker-compose/scripts/identity/AGENTS.mdAGENTS.md
- examples/recipes/partners/hpe/retail-assistant/helm/files/identity/AGENTS.mdAGENTS.md
- examples/recipes/partners/tavily/watchtower/prompts/AGENTS.mdAGENTS.md
- nemoclaw-community-contributor-examplesSkill
- nemoclaw-community-maintainer-policiesSkill
- coach-nemoclaw-hermesSkill
- coordinate-nemoclaw-blenderSkill
- blender-host-sandbox-boundarySkill
- blender-python-api-verificationSkill
- ovphysx-host-runtime-boundarySkill
- axe-a11ySkill
- deep-researchSkill
- cross-source-gap-analysisSkill
- github-readonly-liveSkill
- nemoclaw-autohealSkill
- nemoclaw-nvteamSkill
- outlook-email-searchSkill
- slack-channel-finderSkill
- slack-channel-summarizerSkill
- module-1Skill
- module-2Skill
- module-3Skill
- module-4Skill
- module-5Skill
- module-6Skill
- module-7Skill
- setup-workshop-nemoclaw-operatorSkill
- setup-workshop-nemoclawSkill
- workshopSkill
- cross-source-gap-analysisSkill
- github-readonly-liveSkill
- gitlab-readonly-liveSkill
- nemoclaw-autohealSkill
- nemoclaw-nvteamSkill
- outlook-email-searchSkill
- public-web-searchSkill
- slack-channel-finderSkill
- slack-channel-summarizerSkill
- source-etl-querySkill
- kubernetes-sreSkill
- openshift-llm-deploySkill
- inbound-judgingSkill
- memory-consolidationSkill
- memory-repairSkill
- memory-writingSkill
- obligation-reviewSkill
- preference-updateSkill
- nv-tech-assistantSkill
- payment-ops-playbookSkill
- payment-screeningSkill
- rail-boundary-testSkill
- release-packetSkill
- pr-reviewSkill
- pr-test-case-assistantSkill
- vss-videoSkill
- nemoclaw-hermes-swarmSkill
- blackwall-payment-gateSkill
- retail-apiSkill
- retail-apiSkill
- watchtowerSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use this skill to query the host-side REST bridge served by source-etls.
- Very specific: line 19
Use github-readonly-live instead when the user asks for current live GitHub issues, PRs, commits, branches, README, or repository contents …
- Distinctive: line 25
Use the helper script in this skill.
- Distinctive: line 26
Prefer the helper scripts over custom REST queries
- Very specific: line 39
Always run these commands via the terminal tool — do not invoke source-etl-query as a named skill tool.
- Distinctive: line 74
Run a broad unfiltered query first to show what IS in the database:
- Distinctive: line 96
Do not describe mirror data as live.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
source-etl-query
Use this skill to query the host-side REST bridge served by source-etls.
This is the mirror path, not the live GitHub REST path.
When to use
- Inspect mirrored GitHub issues or pull requests when the user explicitly asks for mirror data, historical mirror state, or ETL freshness checks
- Inspect mirrored GitHub discussions
- Inspect mirrored NVIDIA forum topics
- Build digests or comparisons that should use the hourly ETL mirror
Use github-readonly-live instead when the user asks for current live GitHub
issues, PRs, commits, branches, README, or repository contents from the single
repo allowed by $GITHUB_READONLY_REPO.
Access model
- Use the helper script in this skill.
- Prefer the helper scripts over custom REST queries
- The sandbox should treat this bridge as the default source for GitHub discussions and NVIDIA forum data in the NVIDIA setup path.
- The mirror and
$GITHUB_READONLY_REPOmay point at different repos. Keep mirror facts and live GitHub facts labeled separately.
Required Environment
SOURCE_ETL_API_URL, orSOURCE_ETL_API_HOSTplusSOURCE_ETL_API_PORT
Procedure
Always run these commands via the terminal tool — do not invoke source-etl-query
as a named skill tool.
1. Query the mirrored source through the REST bridge
/usr/bin/python3 /sandbox/.hermes-data/skills/source-etl-query/scripts/query_source_etl.py github-discussions --limit 20
/usr/bin/python3 /sandbox/.hermes-data/skills/source-etl-query/scripts/query_source_etl.py forum-topics --limit 20
# Historical mirror checks only; use github-readonly-live for current issues/PRs.
/usr/bin/python3 /sandbox/.hermes-data/skills/source-etl-query/scripts/query_source_etl.py github-issues --limit 20
/usr/bin/python3 /sandbox/.hermes-data/skills/source-etl-query/scripts/query_source_etl.py github-prs --limit 202. Narrow the result set when needed
/usr/bin/python3 /sandbox/.hermes-data/skills/source-etl-query/scripts/query_source_etl.py github-discussions --search <keyword> --limit 10
/usr/bin/python3 /sandbox/.hermes-data/skills/source-etl-query/scripts/query_source_etl.py forum-topics --search <keyword> --limit 103. Interpret the results and handle empty or mismatched data
The ETL is configured to mirror a specific GitHub repo and forum tag — these are set by whoever deployed this sandbox, and may differ from what the user is asking about.
If the query returns zero rows:
- The database may be empty because the ETL has not completed its first sync yet (it runs on an interval, typically hourly). Tell the user: "The mirror appears empty — the ETL may not have completed its first sync yet. Try again in a few minutes."
- Alternatively the ETL target repo or forum tag may not match what the user is asking about (see below).
If results exist but are not relevant to the user's question:
- Run a broad unfiltered query first to show what IS in the database:
/usr/bin/python3 /sandbox/.hermes-data/skills/source-etl-query/scripts/query_source_etl.py github-discussions --limit 5 /usr/bin/python3 /sandbox/.hermes-data/skills/source-etl-query/scripts/query_source_etl.py forum-topics --limit 5 - Then tell the user what repo/topics the mirror actually contains, e.g.:
"The ETL mirror contains discussions from
NVIDIA/NemoClawand forum topics taggednemoclaw. If you need mirror data from a different repo or topic, the ETL target would need to be reconfigured."
Do not fall back to live NVIDIA forum requests — the sandbox has no egress
to forum HTML. For GitHub, switch to github-readonly-live only when the user
needs current live data from $GITHUB_READONLY_REPO; otherwise explain the ETL
mirror scope or freshness limitation.
Pitfalls
- The mirror is refreshed hourly, so it is not guaranteed to match the live source instantly.
- The ETL scope is configured per-deployment — forum topics follow the configured tag, and GitHub mirror rows follow the configured repo. Neither covers the whole of GitHub or the entire forums site.
- Do not describe mirror data as live. If combining it with live GitHub REST data, say which facts came from the mirror and which came from live REST.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

