30 agent skills · MIT licence
Customer Success Skills for AI agents
Agent skills for churn risk, renewal forecasting, QBRs, expansion, escalations and board reporting — written to the bar a Chief Customer Officer would sign, and structured so an agent produces the same quality every time.
/plugin marketplace add gaintrace/customer-success-skills/plugin install customer-success@customer-success-skillsOr say what you mean — “is northwind going to churn”, “prep me for the acme call”. Skills fire on the prompt, not the command name.
The evidence standard
Most AI output in customer success fails the same three ways.
It invents a number to fill a gap, and someone repeats it to a customer. It silently omits what it could not check, so the reader assumes it was checked and clear. And it produces false precision — an “87% churn probability” from a rules-based score that has never been backtested against a single renewal.
| Mechanism | What it does |
|---|---|
| Provenance tags | Every number carries [system · field · date]. No tag, no number. |
| Three evidence tiers | Observed / Inferred / Unknown, never blurred. Inferences state their rule and what would falsify them. |
| The Coverage Ledger | Every analysis ends with all seven signal families printed — including the ones with no data — plus a coverage percentage and the confidence cap it forces. |
| Confidence with entry criteria | High / Medium / Low / Insufficient, each with stated conditions. Confidence can never exceed what coverage permits. |
| Override floors | Commercial decisions — auto-renew off, notice served, data export — set a risk floor no healthy-looking aggregate can wash out. |
| No certainty language | “100% accurate”, “guaranteed”, “will churn” are banned. Bands and confidence only. |
“Never misses anything” here means something checkable: a fixed checklist walked every time, non-findings printed rather than dropped, blind spots declared, and no number that is not either computed or marked UNKNOWN — requires X.
Shared vocabulary
The seven signal families.
Every skill reasons over the same seven. Fixed vocabulary is what lets a risk assessment, a QBR, a forecast and a board report agree with each other.
What it actually produces
Brief by default. Twenty lines, one recommendation, and the thing that would prove it wrong.
An excerpt from the worked example — a complete churn-risk run over a four-account renewal window. Read it for the mechanics, not the numbers.
Renewal window · $1.12M assessed · $410k at risk (37%) · 2 accounts escalating regardless of score 1. Delta Systems — High Risk. $310k. Decide in 5 days. A P1 has been open 19 days past SLA [Zendesk · #48211 · as-of 2026-08-26], seats were cut 25% in March [Salesforce · Asset.Quantity], and invoices have slipped from 4 to 22 days late [Stripe · 180d]. Three separate pressures, one direction. Do: Priya opens the exec call and names an engineering owner by 28 Aug. 2. Acme Corp — Critical. $148k. Decide in 6 days. Auto-renew was switched off on 2 Aug [Salesforce · Contract.AutoRenew__c] and the champion's email has hard-bounced since 11 Aug. The score is irrelevant — a decision has been made. Do: Marcus runs exec-to-exec outreach by 28 Aug, after verifying in 24h that the flag change was not our own re-papering. 3. Beta Industries — Watch band, escalating anyway. $620k. RevOps, who signed and hold the budget, went from 22 active users to 4 since May, while the account total rose 18% because Marketing grew [Amplitude · distinct_users_30d]. Aggregate health reads green; the buying team has left. Do: Jo meets Dana Osei (VP RevOps) by 10 Sept with RevOps' own numbers, not the account total. Confidence: high on Delta and Beta (7/7 families), high on Acme (6/7 — no VoC source). What would change this: RevOps back above 12 weekly actives; Delta's P1 closing with a committed date; confirmation that Acme's auto-renew change was ours.
Beta Industries scores 34.7/100 on the churn-risk scale — where higher is worse — with every aggregate metric healthy, and escalates anyway, because the team that holds the budget stopped using the product while the account total grew. The scoring is reproducible:python3 skills/churn-risk/scripts/risk_score.py …
The library
All 30 skills.
Each is a self-contained folder — SKILL.md plus its references, assets, scripts and evals. Take the whole library, or the two you want.
Foundation
01Run this first. Every other skill reads what it captures.Risk
03Early warning, intervention, and what the loss teaches.Seven-family risk sweep with override floors, compound-pattern detection, ARR-weighted ranking and an intervention plan.
save-playWar-room plan for a red account: root-cause diagnosis, the matching play, commitments, exec engagement, and the stop-loss decision.
churn-postmortemLoss review that finds the true root cause, the earliest detectable signal, and the systemic fix — then tunes the risk model.
Renewal
03Governed by the opt-out deadline, never the renewal date.The T-180 → close stage-gate runbook, governed by the opt-out deadline, with MEDDPICC-for-renewals and the paper process.
renewal-negotiationUplift justification, the concession ladder, procurement handling, and multi-year structuring.
renewal-forecastEvidence-based forecast categories, the ARR bridge, GRR/NRR with every edge case, scenarios and forecast accuracy.
Meetings & relationship
06Before the call, after the call, and the map of who matters.The one-pager that makes you the best-prepared person in the room, built around a single walk-out commitment.
qbr-builderQBR/EBR anchored on the customer's objectives, with quantified value realisation and SMART goals for next quarter.
post-call-followupCustomer recap, internal notes, CRM updates and downstream triggers — with a hard wall between internal and external.
proactive-outreachTrigger-based outreach that gets replies, with a full trigger catalogue and a message library.
stakeholder-mapWho matters, how strong each relationship is, where the single points of failure are, and the plan to close them.
exec-escalation-commsThe note that goes in writing to a customer executive when something breaks or slips — written to be forwarded, unedited, to people you have never met.
Growth & value
03Expansion gated on health, and the value story that earns it.Ranked, sized expansion pipeline from existing data — gated on health so trust is never spent for a quota.
value-caseProves, measures and defends what a customer actually got for their money — impact hypothesis, baseline, KPIs, the arithmetic, and the one-page value case.
customer-advocacyWho is safe to ask to speak publicly, privately, or to a prospect — what to ask them for, how to word it, and how not to burn them.
Lifecycle
03From handover to steady state, against real capacity.Onboarding plan built backwards from time-to-value, with the activation event as the finish line.
success-planMutual success plan with SMART goals, baselines, joint owners and a review cadence that survives contact with reality.
book-of-business-triageMonday-morning prioritisation of a whole portfolio against real capacity.
Leadership
04The numbers that survive a board meeting.The monthly report leadership reads: ARR bridge, retention metrics, health migration matrix, drivers and decisions requested.
exec-retention-reviewThe board and exec-staff narrative — what happened, what it means, what we are doing, what we need.
voice-of-customerSynthesises NPS, CSAT, tickets, transcripts and churn reasons into themes with ARR attached.
coverage-and-capacitySegmentation, coverage model, CSM capacity and the headcount case.
CS Ops
03The instruments: scores, data, playbooks.Designs, calibrates, backtests and audits a health score people will actually trust.
cs-data-auditInstrumentation and data-quality audit with a prioritised remediation plan.
cs-playbook-designerTurns plays into triggered, measurable automations — and kills the ones that do not work.
Forward-deployed engineering
04The technical account work FDEs and solutions architects own.Technical account plan: architecture as deployed, deployment risk, custom work, and the path back to product.
fde-scopingScope and statement of work for a deployment or services engagement — in and out of scope, milestones with acceptance criteria, dependencies, estimate and change control.
integration-healthWhether the integrations wired into an account are actually working — per connector, per error class, including the failures that raise no alert.
custom-vs-productBuild bespoke, generalise, work around, or say no — priced on the carrying cost, not the build cost.
How they fit together
The common chains.
Skills hand off to each other on a shared schema, so the output of one is a legitimate input to the next. cs-context runs first and every other skill reads it.
Install
One command in Claude Code. A clone anywhere else.
Works with Claude Code, Claude, Codex, Cursor, Windsurf, Gemini CLI, Copilot and anything supporting the Agent Skills standard.
/plugin marketplace add gaintrace/customer-success-skills/plugin install customer-success@customer-success-skillsSkills are namespaced — /customer-success:churn-risk — though you rarely type them.
claude plugin marketplace add gaintrace/customer-success-skillsclaude plugin install customer-success@customer-success-skillsgit clone https://github.com/gaintrace/customer-success-skills.gitcp -r customer-success-skills/skills/* ~/.claude/skills/Or point your agent's skills directory at skills/.
First run
Start with cs-context. It writes.agents/cs-context.md, and every other skill reads it. Skip it and the skills will tell you the output is generic rather than guess your commercial model.
Set up customer success context for my companyWhich of my renewals in the next 90 days are at risk, and why?Prep me for the Acme call tomorrowWhere's my expansion revenue hiding?What went wrong with the accounts we lost last quarter?From skills to always-on
These skills do the thinking. They do not do the watching.
An agent session ends and the sweep goes stale the moment you close it. The signals that decide a renewal arrive between reviews — a champion's email starts hard-bouncing on a Tuesday, an auto-renew flag flips on a Friday, a P1 ages past its SLA over a weekend. Run the seven-family sweep by hand on Monday and it is accurate on Monday.
That gap is a job for a platform, not a prompt. Every skill closes with an Automate This note naming the manual cost it just incurred, so you can decide what is worth wiring up — with whatever tooling you already run.
GainTrace, a contributor to this library, builds one such platform — the column on the right is what it automates. The library is MIT and vendor-neutral: nothing here requires it.
| The skills, manually | What a platform automates |
|---|---|
| You reconcile CRM, billing, support, product analytics and email by hand, per account | Pre-built connectors resolved into one live account timeline |
| You score risk once, in a session that ends | Continuous scoring that ranks who needs attention today |
| You explain the score by hand so people trust it | Signal-by-signal reasoning shown, never an opaque number |
| You find risk when you happen to look | Risk flagged ahead of the renewal call rather than at it |
| You write the play and then chase it | Playbooks that fire when risk signals cross a threshold |