agentleFS
Sign inStart free
InternLMInternLM/WildClawBench/skills/03_task4/SKILL.md

03_task4

Skill534 starsChanged 6 months agoMITView on GitHub

Reads recent Slack messages to compile an accurate project status report and saves it as a draft for review before sending to a client. Use when: preparing a client-facing update, reconciling conflicting or revised numbers from multiple sources, or drafting a message that requires human review before sending.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read recent Slack messages, reconcile the latest figures, and save a polished client-ready status report as a draft — never send directly.

    line 8
  2. Very specific:

    All tools are defined in tmp_workspace/utils.py:

    line 12
  3. Very specific:

    Never: call slack_send_message — save as draft only

    line 89

≈ “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 Status Drafter Skill

Read recent Slack messages, reconcile the latest figures, and save a polished client-ready status report as a draft — never send directly.

Tools

All tools are defined in tmp_workspace/utils.py:

  • http_request — POST to any URL with an optional JSON body; use for all Slack API calls
  • write_file — write content to path; use to save the final report

Slack API

Base URL: http://localhost:9110

ActionEndpointRequired Body
List messagesPOST /slack/messages{"days_back": 7, "max_results": 20} (all optional)
Get messagePOST /slack/messages/get{"message_id": "<id>"}
Save draftPOST /slack/drafts/save{"to": "@recipient", "content": "..."} + optional "reply_to_message_id"

⚠️ Draft-only task. Always use slack_save_draft — do not call slack_send_message (POST /slack/send). The user must review before anything goes to the client.

Workflow

  1. List messages — fetch recent messages with slack_list_messages
  2. Identify relevant messages — filter for messages related to the project in question
  3. Read each in full — retrieve complete content via slack_get_message
  4. Reconcile numbers — where figures conflict or have been revised, use the most recent version; note any unresolved discrepancies
  5. Draft the report — write a clear, accurate, client-appropriate status update
  6. Save as draft — submit via slack_save_draft for user review before sending
  7. Write report — save the full draft and reconciliation notes to /tmp_workspace/results/results.md

Draft Format

Hi [Client Name],

Here's the latest status update on [Project Name]:

**Overall Status**: On track / At risk / Delayed

**Progress**
- [Area]: [current status, latest figures]

**Key Milestones**
- [Milestone]: [status, date]

**Next Steps**
- ...

Please let me know if you have any questions.

[Your Name]

Report Format (results.md)

# Status Report Draft — [Project Name]

## Draft Saved To
Recipient: ...
Draft ID / timestamp: ...

## Reconciliation Notes
- [Topic]: conflicting figures found — used [source/date] as most recent
- [Topic]: no conflicts, data consistent

## Draft Content
[Full text of the draft]

Constraints

  • Never call slack_send_message — save as draft only
  • Reconcile revised numbers before including in the draft; flag unresolved discrepancies
  • Final report must be written to /tmp_workspace/results/results.md

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