agentleFS
Sign inStart free
kyle-olmsteadkyle-olmstead/cs-claude-engine/skills/expansion-whitespace/SKILL.md

expansion-whitespace

Skill1 starsChanged 23 days agoApache-2.0View on GitHub

This skill should be used when the user says "where can we expand [account]", "whitespace at [account]", "is [account] ready for an upsell", "[account] is over their seat limit", "which of my accounts are expansion-ready", "size the expansion at [account]", "sales handoff for [account]", or when a book review flags PB-EXP-01 or PB-EXP-02. It checks expansion readiness (any red flag defers the play), enumerates evidence-backed plays (seats, tier, modules, business units, regions, usage commit), sizes each as indicative annualized list, names the sponsor and the objection to expect, decides the motion by segment (self-serve nudge vs sales-assist handoff), and drafts one approval-gated sponsor communication.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. anthropics/knowledge-work-plugins★ 35ksame name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Follow ${CLAUDE_PLUGIN_ROOT}/skills/customer-360/references/playbook-protocol.md with these specifics.

    line 19
  2. Distinctive:

    Never quote prices or terms to a customer.

    line 54
  3. Very specific:

    Never propose a play without at least one evidence_paths[] entry.

    line 55
  4. Distinctive:

    Never draft to procurement.

    line 56

≈ “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

Expansion whitespace (PB-EXP-01 / PB-EXP-02)

Follow ${CLAUDE_PLUGIN_ROOT}/skills/customer-360/references/playbook-protocol.md with these specifics.

When it applies

  • PB-EXP-01 (smb / digital): health.band != "red" and any of utilization ≥ 0.85, feature-gate hits ≥ 3 in 14d, PQL ≥ 70, DAU/MAU ≥ 0.35.
  • PB-EXP-02 (enterprise / mid_market): health.band == "green", utilization ≥ 0.80, renewal > 60 days, no open expansion opportunity, and whitespace present (unowned modules/BUs) or gate hits / over-deployment.

Readiness gate first: an open P1/P2, payment past due, contraction in 90d, champion departed, CSAT < 3.5, or a high-urgency negative sentiment signal in 30d → emit a deferral action naming the blocker and stop. Do not run expansion on an account with an open P0 retention action.

Inputs beyond the Customer 360

  • pricing_catalog_json: for sizing only, the user's price book from ~~crm product library or ~~documents (ask once; remember in the stack profile) → plugin default DEFAULT_PRICING_CATALOG. Say which was used; default prices are placeholders.
  • feature_audit_json: run feature-depth-audit as a sub-step first when gate hits or unowned modules are in play, and pass its feature_audit block; else {}.

Prompts

  1. (conditional) ${CLAUDE_PLUGIN_ROOT}/prompts/adoption/feature_depth_audit.prompt
  2. ${CLAUDE_PLUGIN_ROOT}/prompts/expansion/whitespace_expansion_finder.prompt: set playbook_id by segment; max four plays; sizing with the catalog formulas; do_not_say list for the AE.

For enterprise/mid-market, offer to continue into ebr-generator with variant = "expansion" so the play lands in an executive review rather than a cold ask.

Artifacts

  • PB-EXP-0x.whitespace_expansion_finder.action.json with the expansion_brief block
  • PB-EXP-0x.expansion_brief.md: readiness, ranked plays with sizing basis and confidence, sponsor, objection and response, sales handoff notes with do_not_say
  • PB-EXP-0x.whitespace_expansion_finder.comm_1.md: sponsor discovery email (approval required); for digital, the in-app nudge copy is in the action as a digital_nudge

Proposed writes

  • ~~crm: expansion_candidate = true on the account; an opportunity suggestion as a task or note ("Suggested opp: <name>, <band>, close within <window>"); the engine never creates opportunities or touches forecast stages.
  • ~~chat: handoff post to the expansion queue channel with qualifying facts and do_not_say.
  • ~~email: draft of comm_1.

Rules specific to this playbook

  • Never quote prices or terms to a customer; sizing is internal and marked indicative.
  • Never propose a play without at least one evidence_paths[] entry.
  • Never draft to procurement.
  • Respect the two-asks-per-14-days limit and any open expansion action.

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