agentleFS
agiea-brainagiea-brain/agency-skills/skills/bailey-darling/client-activation-checkin/SKILL.md

client-activation-checkin

Skill1 starsChanged 16 days agoMITView on GitHub

Use this skill before a check-in with a client who has signed but whose work is not yet live with the people it was built for, when the call is about to become another status update. Produces a prep card: the one milestone this call exists to move, where they actually are against it, what is blocking it, and the agenda to send. Also use for "prep my check-in with [client]", "they signed but nothing's happening", "client call prep", "onboarding call".

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    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:

    Not blocked, just not prioritised: the real finding.

    line 29
  2. Very specific:

    Write the agenda the client gets beforehand.

    line 30
  3. Distinctive:

    MUST name one milestone and hold it across check-ins until reached.

    line 44
  4. Distinctive:

    MUST distinguish delivered from in use, and report the second.

    line 45
  5. Distinctive:

    MUST read the shared working channel before the call, not just the record.

    line 46
  6. Distinctive:

    MUST send an agenda in advance.

    line 47
  7. Distinctive:

    MUST end with a dated commitment from both sides.

    line 48
  8. Distinctive:

    MUST raise a client-side blocker they have not acknowledged in the first ten minutes.

    line 49
  9. Distinctive:

    NEVER let a check-in become a status update.

    line 50
  10. Distinctive:

    NEVER count internal sign-off as activation.

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Applies between signing and the work being in live use. Produces a one-page prep card built around a single milestone, and a short agenda the client sees before the call.

The play

  1. Name the one milestone this engagement is working toward, in the client's terms, and keep it the same across every check-in until it is reached. One milestone, not a list. A check-in with three goals is a status update, and status updates are how an engagement drifts for a quarter.
  2. Separate delivered from in use. These are two different states and conflating them is the most expensive mistake in client work: a thing can be finished, signed off, invoiced, and used by nobody. The two-stage model and how to tell which stage a client is in are in references/activation-stages.md.
  3. Pull the context from where the work actually happens before opening any system of record. A shared channel with the client holds more signal than a CRM field, because it is written by the people doing the work. What to look for is in references/prep-card.md.
  4. Establish the gap: what is true today against what the milestone requires. One sentence. If it cannot be written, the milestone is too vague to drive a call.
  5. Identify the blocker and who owns it. Branch by who:
    • Blocked on the firm: the check-in is an apology and a date. Fix it before the call if the fix is hours.
    • Blocked on the client, and they know: the call is about removing the obstacle, not about restating the deadline.
    • Blocked on the client, and they do not know they are blocking: the hardest case. Name it plainly and early in the call, not at minute fifty.
    • Blocked on a third party: the firm chases it, not the client. This is service, and it is cheap to provide.
    • Not blocked, just not prioritised: the real finding. Something changed in their world, and the call is about whether this still matters.
  6. Write the agenda the client gets beforehand. Three lines, one of them the milestone. The patterns are in references/prep-card.md. An agenda sent in advance changes who prepares for the call.
  7. End with one commitment from each side, each with a name and a date. A check-in that ends with only the firm owing something has not moved the client at all.
  8. Record what happened and the new gap, so the next card starts from it rather than from memory.

What good looks like

  • First thing I check that most people skip: whether anyone outside the client's own team has touched the work yet. Internal approval feels like progress and is not; the work is not real until the people it was built for are using it.
  • The mediocre version: a call that opens with "how's everything going", receives "good, we've been slammed", and ends with the firm promising to follow up. It is pleasant, it costs an hour, and the engagement is in exactly the same place.
  • I know the prep is right when the first question of the call references something specific they said or did since last time.
  • Second test: the client leaves owing something. If only the firm has a task, nothing will have changed by the next call.
  • Red flag: three check-ins with the same blocker. The blocker is not a blocker, it is a priority, and that is a different and more honest conversation.

Rules

  • MUST name one milestone and hold it across check-ins until reached.
  • MUST distinguish delivered from in use, and report the second.
  • MUST read the shared working channel before the call, not just the record.
  • MUST send an agenda in advance.
  • MUST end with a dated commitment from both sides.
  • MUST raise a client-side blocker they have not acknowledged in the first ten minutes.
  • NEVER let a check-in become a status update. If there is nothing to move, shorten or cancel it.
  • NEVER count internal sign-off as activation.

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.