agentleFS
jackchukajackchuka/skills/p-activity-digest/SKILL.md

p-activity-digest

Skill15 starsChanged 9 days agoMITView on GitHub

Summarize recent communication activity from Slack and meeting recordings. Use when the user wants to know what happened on Slack, review meeting action items, find mentions, or get a communication summary. Triggers on "summarize Slack", "meeting action items", "what was discussed", "activity summary", "search my mentions", "highlight of the day", "/activity-digest".

The file

Show its rules and text

We split this skill into the rules it gives an agent

17 rules. About 0 are common, 12 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user if not clear:

    line 36
  2. Distinctive:

    Focus: all activity, mentions only, action items only, specific channels/topics

    line 40
  3. Distinctive:

    Use the Slack MCP tools in this order:

    line 52
  4. Very specific:

    Identify user: Call slack_read_user_profile() (no args) to get the current user's ID.

    line 54
  5. Very specific:

    Search for mentions: Call slack_search_public_and_private with query "from:me" and date-scoped query for the target period to find the …

    line 56
  6. Very specific:

    Search for mentions of user: Call slack_search_public_and_private with the user's name or handle to find where others mentioned them

    line 57
  7. Distinctive:

    If Fireflies is available and in scope:

    line 64
  8. Very specific:

    Search meetings: Call fireflies_get_transcripts with date filters for the target period

    line 66
  9. Distinctive:

    If Fireflies is unavailable, proceed with Slack data only and note the omission in the output.

    line 71
  10. Distinctive:

    Deduplicate: Before synthesis, deduplicate across sources — the same discussion may appear in both Slack threads and Fireflies meeting …

    line 75
  11. Distinctive:

    If only Slack: omit Meeting Highlights section

    line 110
  12. Distinctive:

    If only Fireflies: omit Slack Activity section

    line 111
  13. Distinctive:

    If action-items-only: show only the Action Items section

    line 112
  14. Distinctive:

    If the user specifies a file path, write to that file

    line 116
  15. Distinctive:

    If the user is composing a daily report, provide the content for insertion

    line 117
  16. Very specific:

    When searching Slack, use date qualifiers in the query: "after:2026-02-16 before:2026-02-17"

    line 122
  17. Distinctive:

    If Slack search returns too many results, narrow by channel or conversation type

    line 124

≈ “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

Activity Digest

Aggregate and summarize recent communication activity from Slack messages and meeting recordings (Fireflies). Produces a structured summary with action items, mentions, and key decisions.

When to Use

  • User asks for Slack activity summary
  • User wants meeting highlights or action items
  • User asks "what was discussed" or "what happened on Slack"
  • User wants to find messages where they were mentioned
  • Producing communication portions of a daily/weekly report

Prerequisites

  • Slack MCP server configured and authenticated
  • Fireflies MCP server configured (optional, for meeting transcripts)

Workflow

Step 1: Determine Scope

Ask the user if not clear:

  • Time range: today, yesterday, past N days, specific date
  • Sources: Slack only, Fireflies only, or both
  • Focus: all activity, mentions only, action items only, specific channels/topics

Shared context (resolved before dispatch):

  • DATE_START: start date (YYYY-MM-DD)
  • DATE_END: end date (YYYY-MM-DD)
  • SOURCES: which sources to query
  • FOCUS: filter mode

Steps 2 and 3 are independent data sources. Dispatch both concurrently (parallelize if possible). If your platform supports parallel subagents, launch one per source. Otherwise, query each sequentially.

Step 2: Gather Slack Activity (parallelize if possible)

Use the Slack MCP tools in this order:

  1. Identify user: Call slack_read_user_profile() (no args) to get the current user's ID.
  2. Dispatch all Slack searches in parallel.
  3. Search for mentions: Call slack_search_public_and_private with query "from:me" and date-scoped query for the target period to find the user's own messages
  4. Search for mentions of user: Call slack_search_public_and_private with the user's name or handle to find where others mentioned them
  5. Channel context (optional): If a specific channel is requested, use slack_read_channel on that channel for the time period

Combine results and deduplicate.

Step 3: Gather Meeting Activity

If Fireflies is available and in scope:

  1. Search meetings: Call fireflies_get_transcripts with date filters for the target period
  2. For each meeting returned, call fireflies_get_summary in parallel (parallelize if possible) — each call is independent.
  3. Get summaries: For each relevant meeting, call fireflies_get_summary to retrieve action items, keywords, and overview
  4. Deep dive (optional): If the user asks about a specific meeting, call fireflies_get_transcript for full conversation content

If Fireflies is unavailable, proceed with Slack data only and note the omission in the output.

SYNC: After all data sources return, merge results into a unified collection before synthesis. If a source was unavailable, proceed with available data.

Deduplicate: Before synthesis, deduplicate across sources — the same discussion may appear in both Slack threads and Fireflies meeting notes. Use thread timestamps and meeting IDs as primary keys to merge overlapping records.

Step 4: Synthesize and Format

Produce a structured summary organized by priority:

## Activity Digest - [Date Range]

### Action Items

- [action item from meeting or Slack thread]
- [action item with @assignee if identifiable]

### Key Decisions

- [decision made in meeting or Slack discussion]

### Mentions & Requests

- [someone asked/mentioned you about X in #channel]

### Meeting Highlights

- **[Meeting Title]** — [1-2 sentence summary]
  - Key topics: [topic1], [topic2]

### Slack Activity Summary

- Participated in N threads across [channels]
- [Notable thread summary]

Adapt the format:

  • If only Slack: omit Meeting Highlights section
  • If only Fireflies: omit Slack Activity section
  • If action-items-only: show only the Action Items section

Step 5: Output

  • If the user specifies a file path, write to that file
  • If the user is composing a daily report, provide the content for insertion
  • Otherwise, display directly in the conversation

Tips

  • When searching Slack, use date qualifiers in the query: "after:2026-02-16 before:2026-02-17"
  • For meeting summaries, the fireflies_get_summary tool is much faster than fireflies_get_transcript — use summary first, transcript only when needed
  • If Slack search returns too many results, narrow by channel or conversation type
  • Deduplicate between Slack and meeting notes — the same discussion may appear in both

Examples

Example 1: Yesterday's activity

User: "summarize my Slack activity yesterday"
Action: Search Slack messages for yesterday, find mentions, format as digest

Example 2: Meeting action items

User: "what are action items from today's meetings?"
Action: Query Fireflies for today, get summaries, extract action items

Example 3: Full digest for daily report

User: "give me activity digest for today to add to my daily report"
Action: Query both Slack and Fireflies, produce combined summary, write to daily report file

Example 4: Specific mention search

User: "search Slack for messages about me this week"
Action: Search with user's name/handle for past 7 days, summarize findings

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.