agentleFS
youdcodeyoudcode/open-company/.agents/skills/follow-ups/SKILL.md

follow-ups

Skill2 starsChanged 54 days agoMITView on GitHub

Lists the follow-ups due today and drafts them for approval. Use when the human types "followups", or at the start of a session when follow-ups are due.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 0

    Distinctive

    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. Very specific:

    After follow-up 2: set next_action="close the loop".

    line 14
  2. Very specific:

    Update next_action and next_action_date (suggest 4 to 7 working days) with tools/leads.mjs update.

    line 17

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “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

Follow-ups

Role: sales.

  1. node tools/leads.mjs list --due.
  2. For each lead, by status:
    • approved or contacted with no answer: draft follow-up 1 or 2 with node tools/drafts.mjs new <id> --followup ... (shorter, adds something new, no guilt). After follow-up 2: set next_action="close the loop".
    • replied: do not write. Summarize the reply for the human if it is in the workspace, ask what to do.
    • meeting: ask the consultant for a meeting brief in workspace/departments/consulting/.
  3. Update next_action and next_action_date (suggest 4 to 7 working days) with tools/leads.mjs update.
  4. Report in 5 lines.

The human sets status=contacted (or asks you to) once a message is really sent.

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.