agentleFS
Sign inStart free
jtalk22jtalk22/slack-mcp-server/skills/slack-workflow-profiles/SKILL.md

slack-workflow-profiles

Skill33 starsChanged 39 days agoMITView on GitHub

Set up a saved Slack catch-up profile by choosing its workflow_kind, channels, priority people and cadence, so slack_catch_me_up returns evidence shaped for an incident room, a support inbox, an exec brief or a launch watch. Use when the user wants a repeatable catch-up or a handoff routine, or asks which channels and people to track.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask what the catch-up is for and who reads it, then pick the kind.

    line 30
  2. Very specific:

    Call slack_workflow_save with profile_name, workflow_kind and the fields above.

    line 43

≈ “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

Workflow profiles

A profile is a saved scope for slack_catch_me_up. It records which channels to read, whose messages count most, how far back to look, and which output keys the catch-up asks for. Profiles are stored on this machine in ~/.slack-mcp-workflows.json. Saving one sends nothing to Slack.

Choose the kind

The kind decides which keys slack_catch_me_up asks you to write.

workflow_kindUse it forKeys the catch-up asks for
incident_rooman incident channel, an on-call handoffincident_summary, timeline, open_risks, owner_gaps, next_actions
support_inboxcustomer or internal support queuesopen_threads, ack_lag, owner_gaps, escalations, next_actions
exec_briefa leadership digest across several channelssummary, decisions, risks, asks, action_items
product_launch_watcha launch, a release cycle, a feedback streamlaunch_signals, feedback_themes, blockers, metrics, next_actions
customanything elsesummary, highlights, open_questions, next_actions

Build it

  1. Ask what the catch-up is for and who reads it, then pick the kind.
  2. Channels: call slack_list_conversations and use channel IDs. Names also match when the catch-up runs, but IDs survive a rename. Without that tool, ask the user for the channel names. If you leave channels empty, every catch-up reads whatever is unread at that moment.
  3. Priority people: call slack_users_search with a name or email and put the user IDs in priority_people. Without that tool, ask the user for the IDs. Their messages and their mentions get their own lists in the catch-up.
  4. summary_cadence sets the default look-back: 24 hours for on_demand and daily_8am, 7 days for weekly_monday. It schedules nothing. Something still has to call slack_catch_me_up.
  5. retention_mode (ephemeral by default, or persistent) is recorded on the profile. This server does not act on it.
  6. Call slack_workflow_save with profile_name, workflow_kind and the fields above. Saving an existing profile_name replaces the profile, and a field you leave out returns to its default, so send every field to change one. Confirm with slack_workflows, then run slack_catch_me_up once so the user sees what the profile returns.

Start from a template

The package ships six templates, applied from a terminal rather than through a tool call:

npx -y @jtalk22/slack-mcp --apply-template oncall-handoff --channels C012345,C067890 --priority-people U0PRIME
TemplateKindCadence
incident-roomincident_roomon_demand
oncall-handoffincident_roomon_demand
support-triagesupport_inboxdaily_8am
exec-mondayexec_briefweekly_monday
customer-feedbackproduct_launch_watchdaily_8am
sprint-trackerproduct_launch_watchdaily_8am

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