agentleFS
Sign inStart free
NVIDIAKnown publisherNVIDIA/nemoclaw-community/examples/recipes/nvidia/agentic-ai-learning-path/agents/hermes/skills/cross-source-gap-analysis/SKILL.md

cross-source-gap-analysis

Skill142 starsChanged 3 months agoApache-2.0View on GitHub

Compare findings across Slack, GitHub, NVIDIA forums, and Outlook to identify alignment gaps, missing coverage, and follow-ups.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the task is to compare or synthesize information across multiple sources rather than merely access one source.

    line 8
  2. Distinctive:

    Prefer a small, relevant slice from each source over broad collection.

    line 35
  3. Distinctive:

    Keep the comparison grounded in evidence from the sources you actually checked.

    line 66
  4. Distinctive:

    Do not invent gaps just because one source had less data available.

    line 67
  5. Distinctive:

    Do not force a gap-analysis framing when the user only asked for source access or a plain summary.

    line 71
  6. Distinctive:

    Do not over-collect. A narrow comparison is usually better than an exhaustive scrape.

    line 73
  7. Distinctive:

    Keep live GitHub REST findings separate from source ETL mirror findings when the scopes or freshness differ.

    line 76

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

cross-source-gap-analysis

Use this skill when the task is to compare or synthesize information across multiple sources rather than merely access one source.

When to use

  • Compare Slack discussion against GitHub issues or PRs
  • Compare Slack or GitHub findings against NVIDIA forum discussion
  • Identify missing coverage, inconsistent narratives, or follow-up areas across sources
  • Find external email discussions not reflected in internal meeting updates

Inputs

Load the source skills you need first:

  • slack-channel-summarizer
  • slack-channel-finder
  • github-readonly-live
  • source-etl-query
  • outlook-email-search

This skill does not define how to access those systems. It defines how to combine the findings once you have them.

Procedure

1. Gather the minimum useful evidence from each source

Prefer a small, relevant slice from each source over broad collection. For example:

  • a recent Slack window for the relevant channel
  • live GitHub issues or PRs from $GITHUB_READONLY_REPO, when current state matters
  • mirrored GitHub discussions, or historical issue/PR mirror data for the repo or feature area, when the task is about the ETL mirror or discussions
  • mirrored NVIDIA forum topics for the nemoclaw tag scope
  • recent emails filtered to the relevant project and date range

2. Normalize what each source is saying

Reduce each source to short bullets such as:

  • active topics
  • reported problems
  • decisions or planned work
  • requests for help
  • unresolved questions

3. Compare across sources

4. Present the result

A good default structure is:

  • scope and time window
  • what all sources agree on
  • gaps or mismatches
  • concrete follow-ups

Keep the comparison grounded in evidence from the sources you actually checked. Do not invent gaps just because one source had less data available.

Pitfalls

  • Do not force a gap-analysis framing when the user only asked for source access or a plain summary.
  • Do not over-collect. A narrow comparison is usually better than an exhaustive scrape.
  • Distinguish between "not discussed" and "not observed in the sampled data".
  • Distinguish between “not observed in the mirror” and “not present on the live source”.
  • Keep live GitHub REST findings separate from source ETL mirror findings when the scopes or freshness differ.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free