agentleFS
pradeep-sankaran-07pradeep-sankaran-07/team-os-gdrive-template/.claude/skills/account-review/SKILL.md

account-review

Skill0 starsChanged 2 months agoMITView on GitHub

Review one account end to end and produce the written view: how it is doing, what is at risk, and what the plan is. Use before a QBR or a renewal, when an account looks wobbly, or on a regular cadence for the accounts that matter. Triggers: "review the <account> account", "how is <account> doing", "prep for the <account> QBR", "is <account> at risk", "account review for <account>". NOT for the whole portfolio at once (use customer-dashboard). NOT for a prospect who has not bought (use solution-brief). NOT for writing up a single call (use customer-call-summary).

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Read the whole account folder, oldest to newest, so the direction of travel is visible rather than just the current state.

    line 26
  2. Distinctive:

    If the evidence is thin, say the confidence is low.

    line 42
  3. Distinctive:

    Expansion: - only where there is a real signal.

    line 52
  4. Very specific:

    Write to output_location, refresh accounts/<slug>/summary.md, append one line to _ops/log.md.

    line 57
  5. Distinctive:

    Every claim traces to a file in the account folder.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Account review

Step 1 - Gather

Read the whole account folder, oldest to newest, so the direction of travel is visible rather than just the current state. Note the date of the most recent call and the most recent email: an account with no contact in two months is a finding in itself.

Step 2 - Infer health, do not ask for it

Health is green, amber or red, and it is inferred from evidence, not hand-set. Say which evidence produced it.

Signal
greenusing what they bought, contact is current, no open escalation
amberadoption below plan, a blocker with no date, a champion who went quiet, a renewal inside 90 days with no conversation started
redan open escalation, a stated intent to leave, or a commercial term we cannot meet

If the evidence is thin, say the confidence is low. A confident amber and an uncertain amber are different things to the person reading it.

Step 3 - Write

  1. Health - the rating, and the two or three facts behind it.
  2. Usage - what they actually use, against what they bought.
  3. Results - what they have got out of it, in their words where possible.
  4. Risks - each with an owner and a next action. A risk with no action is a worry, not a risk.
  5. Expansion - only where there is a real signal. Leave it empty rather than inventing one.

Step 4 - Record

Write to output_location, refresh accounts/<slug>/summary.md, append one line to _ops/log.md.

Review before delivering (required)

  • Every claim traces to a file in the account folder.
  • The health rating and its evidence agree.
  • Risks have owners and dates.
  • A human has read it before it reaches the customer or leadership.

Things that have gone wrong before

  • Never carry a health rating forward unexamined. Why: a rating copied from last quarter's review looks like a fresh assessment and is trusted as one. If the evidence has not been re-read, the rating has not been made. (2026-09-16)

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.