agentleFS
Sign inStart free
NVIDIAKnown publisherNVIDIA/nemoclaw-community/examples/recipes/nvidia/agentic-ai-learning-path/agents/hermes/skills/slack-channel-summarizer/SKILL.md

slack-channel-summarizer

Skill142 starsChanged 3 months agoApache-2.0View on GitHub

Read and summarize Slack channel history from inside the NemoClaw sandbox.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to resolve a Slack channel and read its history.

    line 8
  2. Distinctive:

    Check what was discussed in a channel before answering a question

    line 14
  3. Distinctive:

    Only refer to helper scripts that actually exist in this sandbox image

    line 21
  4. Very specific:

    If the user gives a direct Slack mention like <#C0ALN454EH4>, use that ID directly.

    line 28
  5. Distinctive:

    If the request comes from a tagged Slack channel and the runtime context already gives you the current channel ID, treat that as the …

    line 31
  6. Distinctive:

    Use the existing channel-description helper with the resolved channel ID.

    line 39

≈ “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

slack-channel-summarizer

Use this skill to resolve a Slack channel and read its history.

When to use

  • Summarize recent activity in a channel
  • Review conversation history for a time range
  • Check what was discussed in a channel before answering a question

Instructions

  • The best way to access slack given the sandbox is through the provided python scripts.
  • Direct curl requests, or Python scripts, are unlikely to succeed
  • The SLACK_BOT_TOKEN contains a placeholder env var that is resolved by the sandbox on egress
  • Only refer to helper scripts that actually exist in this sandbox image

Procedure

1. Resolve the channel ID

If the user gives a direct Slack mention like <#C0ALN454EH4>, use that ID directly.

If the request comes from a tagged Slack channel and the runtime context already gives you the current channel ID, treat that as the resolved channel ID for phrases like "this channel".

Otherwise, use your slack channel finder skill.

2. Read channel history

Use the existing channel-description helper with the resolved channel ID. It includes recent human messages and channel metadata that are sufficient for a summary:

/usr/bin/python3 /sandbox/.hermes-data/skills/slack-channel-finder/scripts/describe_slack_channel.py \
  --channel-id CHANNEL_ID --history-limit 15

Useful variants:

/usr/bin/python3 /sandbox/.hermes-data/skills/slack-channel-finder/scripts/describe_slack_channel.py \
  --channel-id CHANNEL_ID --history-limit 30 --replies
/usr/bin/python3 /sandbox/.hermes-data/skills/slack-channel-finder/scripts/describe_slack_channel.py \
  --channel-id CHANNEL_ID --history-limit 15 --resolve-users

Interpret common failures explicitly:

  • not_in_channel The bot is not a member of that channel.
  • missing_scope with needed=channels:history The bot cannot read public-channel history.
  • missing_scope with needed=groups:history The bot cannot read private-channel history.
  • channel_not_found The ID is wrong or unavailable to the token.

3. Summarize

Summarize only what the user asked for. Good defaults are:

  • time range covered
  • main topics
  • active participants
  • decisions or action items

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