agentleFS
kyle-olmsteadkyle-olmstead/cs-claude-engine/skills/ttv-acceleration/SKILL.md

ttv-acceleration

Skill1 starsChanged 23 days agoApache-2.0View on GitHub

This skill should be used when the user says "[account] is stuck in onboarding", "[account] hasn't gone live", "time to value on [account]", "unblock [account]'s implementation", "onboarding is stalled at [account]", "why hasn't [account] reached first value", "TTV acceleration", or when a book review flags PB-ADP-01. It diagnoses the blocker for an onboarding account that has passed its segment's p75 time-to-value without a value milestone, assigns owners on both sides, sets a milestone target date, and drafts one approval-gated check-in.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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. Very specific:

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

    line 17
  2. Distinctive:

    Do not propose a kickoff for an account that already had one.

    line 46
  3. Distinctive:

    Do not assign an action to a customer contact who has been silent 45+ days without a re-engagement step first.

    line 47
  4. Distinctive:

    Do not recommend paid services.

    line 48

≈ “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

TTV acceleration (PB-ADP-01)

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

When it applies

lifecycle.stage == "onboarding", lifecycle.value_milestones_reached == [], and lifecycle.days_since_term_start > benchmarks.ttv_p75_days. If a milestone has been reached, say so and offer feature-depth-audit instead. If the account is simply early (under p50), say that too: the engine does not chase week-one accounts.

Inputs beyond the Customer 360

  • value_milestone_definitions_json: from ~~product analytics milestone definitions when the connector exposes them, else the plugin default DEFAULT_VALUE_MILESTONES in ${CLAUDE_PLUGIN_ROOT}/src/orchestrator.py. Tell the user which was used.
  • Onboarding history: lifecycle.onboarding_steps[], lifecycle.kickoff_notes, sessions from ~~calendar, onboarding-tagged tickets from ~~support desk, and integration/onboarding themes from transcript signals. Pull these into the document before running if they are empty.

Prompt

${CLAUDE_PLUGIN_ROOT}/prompts/adoption/ttv_acceleration.prompt. Classify the blocker from the taxonomy in the prompt; the blocker is the earliest unmet prerequisite of the nearest milestone unless evidence shows motion stopped for another reason.

Artifacts

  • PB-ADP-01.ttv_acceleration.action.json with the onboarding_plan block
  • PB-ADP-01.ttv_acceleration.comm_1.md: check-in to the customer-side owner (approval required)
  • PB-ADP-01.unblock_plan.md: the plan as a one-pager: blocker, owners, three to five dated actions, milestone target date, first-win statement

Proposed writes

  • ~~crm: onboarding_risk_tier (watch / at_risk / stalled) on the account; a task to the implementation owner for each vendor-side action.
  • ~~support desk: when the blocker is technical_integration or vendor_delay, a ticket draft tagged onboarding-blocker with the prerequisite named; created only on approval.
  • ~~calendar: a proposed configuration/training session on the date the plan names.

Rules specific to this playbook

  • Do not propose a kickoff for an account that already had one.
  • Do not assign an action to a customer contact who has been silent 45+ days without a re-engagement step first.
  • Do not recommend paid services; you may note the blocker is of the kind professional services typically clears.

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.