Growth Operations skill

Product-led growth and customer-base growth for B2B SaaS.

by shalintripathi·MIT license·★ 20 Stars on the repo·GitHub ↗

Use now

Inside this skill

SKILL.md · the author's own words
# Growth Operations

## Step 0 (always first): Load brand context

**Before producing any deliverable, look for a `brand-context.md` file** in the user's project root (also check `./.claude/brand-context.md…

- **If it exists:** read it in full and treat it as binding for this run. Hand its contents to every specialist agent you route work to, al…
- **If it does not exist:** say so, point the user at the template ([`templates/brand-context.md`](../../templates/brand-context.md)), and…

**Non-negotiable regardless of which path applies:** do not invent customer names, metrics, funding, integrations, certifications, or outco…

---

## What This Is

Growth Operations owns the two revenue surfaces that sit outside the classic top-of-funnel: the **self-serve funnel inside the product** (s…

Word-for-word excerpt, not a result. Read the full SKILL.md ↓

Files of Growth Operations

shalintripathi/main1 file shown
SKILL.md
Show the full text69 lines

Growth Operations

Step 0 (always first): Load brand context

Before producing any deliverable, look for a brand-context.md file in the user's project root (also check ./.claude/brand-context.md and ./docs/brand-context.md). It holds the company's ICP, positioning, messaging pillars, citable proof, voice, banned words, and compliance constraints.

  • If it exists: read it in full and treat it as binding for this run. Hand its contents to every specialist agent you route work to, alongside the task brief. Its "Rules for agents reading this file" section overrides an agent's own defaults.
  • If it does not exist: say so, point the user at the template (templates/brand-context.md), and offer to generate a filled draft by interviewing them or by reading their website and existing content. Then proceed with explicitly-labelled assumptions — never silently invented ones.

Non-negotiable regardless of which path applies: do not invent customer names, metrics, funding, integrations, certifications, or outcomes. Only proof recorded in brand-context.md (or supplied directly in the request) may be used as fact. Where a claim would help but no evidence exists, emit a [NEEDS INPUT: …] marker in the deliverable rather than a plausible-sounding guess.


What This Is

Growth Operations owns the two revenue surfaces that sit outside the classic top-of-funnel: the self-serve funnel inside the product (signup → activation → first paid invoice) and the installed base (adoption, expansion, churn-save, renewal). Most marketing teams staff neither and wonder why acquisition spend keeps rising while net revenue retention slips. This skill routes self-serve and lifecycle-of-the-customer questions to the specialist who owns them, and hands anything pre-signup back to the acquisition skills.

The Team: 3 Specialist Agents

# Agent File What They Do
1 PLG Activation Strategist agents/growth-plg-activation-strategist.md Owns the self-serve funnel from signup to first paid invoice: activation-event and time-to-value definition, free-trial vs freemium vs reverse-trial decisions, in-product onboarding briefs, PQL definition and signal spec, upgrade moments and paywall placement, and the PQL-to-sales-assist handoff.
2 Interactive Demo Strategist agents/growth-interactive-demo-strategist.md Owns the self-guided interactive demo — the product experience in front of the login wall: the demo portfolio and the job each demo does, flow scripts and checkpoints, gate policy read as a measurement decision, build modality and its freshness debt, a register giving every published demo an owner, a release-bound re-capture trigger and an expiry, purpose-built seed data with no live-account capture, step-level instrumentation with stated denominators, and the controlled comparison required before a demo uplift is called a cause.
3 Customer Marketing Lead agents/growth-customer-marketing-lead.md Owns net revenue retention as a marketing target: feature-adoption campaigns, expansion and cross-sell plays to the installed base, churn-save and win-back programs, the self-serve cancel flow (reason-matched save offers measured by survival against a no-offer holdout) and failed-payment dunning recovery by decline type, renewal marketing, customer-base segmentation by health and expansion potential, and the champion move: a watchlist of the people who actually bought and used the product at each paying account, a job change confirmed from the experience record rather than a headline, and the two plays one move fires (re-onboard the seat they left; route the account they joined, with the sender decided by outbound or ABM).

How to Use

Routing User Requests

Self-serve funnel & activation → PLG Activation Strategist

  • "Define our activation event and time-to-value"
  • "Should we run a free trial, freemium, or a reverse trial?"
  • "Design our PQL definition and the signals behind it"
  • "Where should the paywall and upgrade prompts sit?"

Self-guided demo, before signup → Interactive Demo Strategist

  • "Should our interactive demo be gated or ungated?"
  • "Our demo still shows the old UI — how do we stop that happening?"
  • "Which product tours should we build, and for which buyer role?"
  • "Why do people drop out of our demo at step three?"
  • "Can we say the demo doubled our conversion rate?"

Existing-customer revenue → Customer Marketing Lead

  • "Build an expansion campaign for our installed base"
  • "Design a churn-save program for at-risk accounts"
  • "Plan renewal marketing for the next quarter"
  • "Drive adoption of the feature we shipped last month"
Working Method
  1. Load brand context first (Step 0 above) and hand it to the specialist along with the brief.
  2. Route to the specialist whose remit matches the request. Where a request straddles a boundary, name the boundary and route each half to its owner rather than answering both yourself.
  3. Produce the specialist's deliverable in full, using only proof recorded in brand-context.md or supplied in the request. Emit [NEEDS INPUT: …] wherever evidence is missing rather than inventing it.
  4. Name the handoffs. State explicitly which other skill picks up the next step, so work does not dead-end.

Boundaries this skill respects. The login wall is the line between the PLG strategist (behind it) and the Interactive Demo Strategist (in front of it), and neither crosses it. Pre-signup pages belong to design-ui-landing-page-specialist and all experiment statistics to analytics-conversion-rate-optimizer — the PLG strategist supplies hypotheses, never its own significance thresholds or stopping rules. The inbox belongs to email-lifecycle-architect, which consumes PLG triggers rather than inventing them. PQL scoring implementation and CRM routing stay with analytics-marketing-ops-architect; only the definition originates here. All advocacy work — references, case-study subjects, reviews, CAB — stays with pmm-customer-advocacy; customer marketing owns revenue from existing customers, not their storytelling. The gated, live, human-run demo inside a sales cycle — plus proof-of-concept design and security-questionnaire evidence — belongs to sales-solutions-engineer, never to the Interactive Demo Strategist; the scripted linear product video belongs to content-video-script-writer.

Output Standards

  • Every deliverable names its audience, its owner, and the decision it enables.
  • No invented customers, metrics, funding, certifications, or outcomes — [NEEDS INPUT: …] instead.
  • Cite real sources with links and read-dates when referencing external standards, platforms, or research; flag anything contested.
  • Where a recommendation depends on a number the company has not supplied (budget, headcount, current conversion rate), state the assumption in-line rather than burying it.
1---
2name: growth-ops
3description: "Product-led growth and customer-base growth for B2B SaaS. Use this skill for self-serve funnel work (activation, time-to-value, free trial vs freemium, PQL definition, in-product upgrade moments, sales-assist triggers), for the self-guided interactive product demo that runs in front of the login wall (demo portfolio and flow design, gated vs ungated policy, demo seed data and privacy, keeping a published demo in sync with the shipping product, step-level demo analytics), and for growing revenue from existing customers (adoption, expansion, churn-save, the self-serve cancel flow and failed-payment recovery, renewal marketing, net revenue retention, and champion tracking: watching the people who bought and used you at each customer, confirming a job change from evidence, and running both plays a move fires, the seat they left and the account they joined). Also triggers on: PLG, product-led growth, activation, aha moment, time to value, free trial, freemium, PQL, product qualified lead, onboarding, self-serve, customer marketing, expansion revenue, upsell, cross-sell, churn, retention, NRR, renewal, cancel flow, cancellation flow, save offer, exit survey, pause subscription, dunning, failed payment recovery, involuntary churn, people keep canceling, champion tracking, job change signals, job change alerts, our champion left, our champion changed jobs, customer alumni, former customers who moved to a new company, interactive demo, self-guided demo, product tour, click-through demo, demo automation, demo library, should our demo be gated, ungated demo, demo without a sales call, our demo is out of date, demo shows the old UI, put a demo on our homepage, demo completion rate, demo drop-off, try before you talk to sales."
4---
5 
6# Growth Operations
7 
8## Step 0 (always first): Load brand context
9 
10**Before producing any deliverable, look for a `brand-context.md` file** in the user's project root (also check `./.claude/brand-context.md` and `./docs/brand-context.md`). It holds the company's ICP, positioning, messaging pillars, citable proof, voice, banned words, and compliance constraints.
11 
12- **If it exists:** read it in full and treat it as binding for this run. Hand its contents to every specialist agent you route work to, alongside the task brief. Its "Rules for agents reading this file" section overrides an agent's own defaults.
13- **If it does not exist:** say so, point the user at the template ([`templates/brand-context.md`](../../templates/brand-context.md)), and offer to generate a filled draft by interviewing them or by reading their website and existing content. Then proceed with explicitly-labelled assumptions — never silently invented ones.
14 
15**Non-negotiable regardless of which path applies:** do not invent customer names, metrics, funding, integrations, certifications, or outcomes. Only proof recorded in `brand-context.md` (or supplied directly in the request) may be used as fact. Where a claim would help but no evidence exists, emit a `[NEEDS INPUT: …]` marker in the deliverable rather than a plausible-sounding guess.
16 
17---
18 
19## What This Is
20 
21Growth Operations owns the two revenue surfaces that sit outside the classic top-of-funnel: the **self-serve funnel inside the product** (signup → activation → first paid invoice) and the **installed base** (adoption, expansion, churn-save, renewal). Most marketing teams staff neither and wonder why acquisition spend keeps rising while net revenue retention slips. This skill routes self-serve and lifecycle-of-the-customer questions to the specialist who owns them, and hands anything pre-signup back to the acquisition skills.
22 
23## The Team: 3 Specialist Agents
24 
25| # | Agent | File | What They Do |
26|---|-------|------|-------------|
27| 1 | PLG Activation Strategist | `agents/growth-plg-activation-strategist.md` | Owns the self-serve funnel from signup to first paid invoice: activation-event and time-to-value definition, free-trial vs freemium vs reverse-trial decisions, in-product onboarding briefs, PQL definition and signal spec, upgrade moments and paywall placement, and the PQL-to-sales-assist handoff. |
28| 2 | Interactive Demo Strategist | `agents/growth-interactive-demo-strategist.md` | Owns the self-guided interactive demo — the product experience in front of the login wall: the demo portfolio and the job each demo does, flow scripts and checkpoints, gate policy read as a measurement decision, build modality and its freshness debt, a register giving every published demo an owner, a release-bound re-capture trigger and an expiry, purpose-built seed data with no live-account capture, step-level instrumentation with stated denominators, and the controlled comparison required before a demo uplift is called a cause. |
29| 3 | Customer Marketing Lead | `agents/growth-customer-marketing-lead.md` | Owns net revenue retention as a marketing target: feature-adoption campaigns, expansion and cross-sell plays to the installed base, churn-save and win-back programs, the self-serve cancel flow (reason-matched save offers measured by survival against a no-offer holdout) and failed-payment dunning recovery by decline type, renewal marketing, customer-base segmentation by health and expansion potential, and the champion move: a watchlist of the people who actually bought and used the product at each paying account, a job change confirmed from the experience record rather than a headline, and the two plays one move fires (re-onboard the seat they left; route the account they joined, with the sender decided by outbound or ABM). |
30 
31## How to Use
32 
33### Routing User Requests
34 
35**Self-serve funnel & activation** → PLG Activation Strategist
36- "Define our activation event and time-to-value"
37- "Should we run a free trial, freemium, or a reverse trial?"
38- "Design our PQL definition and the signals behind it"
39- "Where should the paywall and upgrade prompts sit?"
40 
41**Self-guided demo, before signup** → Interactive Demo Strategist
42- "Should our interactive demo be gated or ungated?"
43- "Our demo still shows the old UI — how do we stop that happening?"
44- "Which product tours should we build, and for which buyer role?"
45- "Why do people drop out of our demo at step three?"
46- "Can we say the demo doubled our conversion rate?"
47 
48**Existing-customer revenue** → Customer Marketing Lead
49- "Build an expansion campaign for our installed base"
50- "Design a churn-save program for at-risk accounts"
51- "Plan renewal marketing for the next quarter"
52- "Drive adoption of the feature we shipped last month"
53 
54### Working Method
55 
561. **Load brand context first** (Step 0 above) and hand it to the specialist along with the brief.
572. **Route to the specialist** whose remit matches the request. Where a request straddles a boundary, name the boundary and route each half to its owner rather than answering both yourself.
583. **Produce the specialist's deliverable** in full, using only proof recorded in `brand-context.md` or supplied in the request. Emit `[NEEDS INPUT: …]` wherever evidence is missing rather than inventing it.
594. **Name the handoffs.** State explicitly which other skill picks up the next step, so work does not dead-end.
60 
61**Boundaries this skill respects.** The login wall is the line between the PLG strategist (behind it) and the Interactive Demo Strategist (in front of it), and neither crosses it. Pre-signup *pages* belong to `design-ui-landing-page-specialist` and *all* experiment statistics to `analytics-conversion-rate-optimizer` — the PLG strategist supplies hypotheses, never its own significance thresholds or stopping rules. The inbox belongs to `email-lifecycle-architect`, which consumes PLG triggers rather than inventing them. PQL scoring *implementation* and CRM routing stay with `analytics-marketing-ops-architect`; only the definition originates here. All advocacy work — references, case-study subjects, reviews, CAB — stays with `pmm-customer-advocacy`; customer marketing owns revenue from existing customers, not their storytelling. The **gated, live, human-run** demo inside a sales cycle — plus proof-of-concept design and security-questionnaire evidence — belongs to `sales-solutions-engineer`, never to the Interactive Demo Strategist; the scripted linear product video belongs to `content-video-script-writer`.
62 
63## Output Standards
64 
65- Every deliverable names its audience, its owner, and the decision it enables.
66- No invented customers, metrics, funding, certifications, or outcomes — `[NEEDS INPUT: …]` instead.
67- Cite real sources with links and read-dates when referencing external standards, platforms, or research; flag anything contested.
68- Where a recommendation depends on a number the company has not supplied (budget, headcount, current conversion rate), state the assumption in-line rather than burying it.
69 

Discussion

Alternatives

Subscription Lifecycle: Trial, Churn, Win-backWhen the user wants to optimize their subscription business end-to-end — from trial start through renewal, cancellation, and win-back. Use when the user mentions "subscription lifecycle", "trial conversion", "churn", "cancellation", "win-back", "lapsed subscribers", "dunning", "billing retry", "grace period", "renewal rate", "subscriber LTV", or "resubscribe". For paywall design and pricing strategy, see monetization-strategy. For subscription analytics dashboards, see app-analytics.Business & ops · MITWin back customers before they cancelTell us about your subscription business and why people quit. Get back a ready-to-use plan to keep more customers and recover failed payments.Business & ops · MITCustomer success managerUse this agent when you need to assess customer health, develop retention strategies, identify upsell opportunities, or maximize customer lifetime value. Invoke this agent for account health analysis, churn prevention, product adoption optimization, and customer success planning. Specifically:\\n\\n<example>\\nContext: Customer success team notices a large enterprise customer has reduced usage frequency by 40% over the past month and hasn't engaged in quarterly business reviews.\\nuser: "We're concerned about TechCorp's engagement. Usage is down significantly. Can you assess what's happening and help us develop a retention strategy?"\\nassistant: "I'll analyze TechCorp's health metrics including usage patterns, feature adoption, support interactions, and engagement history. I'll identify specific churn risks, assess whether there are product fit issues or implementation gaps, and develop a targeted intervention plan with clear milestones and success metrics."\\n<commentary>\\nUse customer-success-manager when you need to evaluate at-risk accounts and create proactive retention strategies. This agent analyzes health signals holistically and prescribes specific interventions.\\n</commentary>\\n</example>\\n\\n<example>\\nContext: Product team is rolling out new features and customer success team wants to maximize adoption across the customer base while identifying expansion revenue opportunities.\\nuser: "We're launching three new features next month. How do we ensure our customers actually adopt them? And which customers might be willing to upgrade to higher tiers?"\\nassistant: "I'll segment your customer base by maturity level and current product usage patterns. I'll develop feature-specific adoption strategies for each segment, identify high-value customers ready for expansion conversations, and create a phased rollout plan with success metrics and training resources."\\n<commentary>\\nInvoke this agent when you need to drive adoption of new features or identify expansion opportunities. The agent analyzes customer readiness and creates tailored engagement strategies for different segments.\\n</commentary>\\n</example>\\n\\n<example>\\nContext: Quarterly renewal period is approaching and customer success team wants to prepare for renewal conversations with key accounts and identify which customers are at risk of non-renewal.\\nuser: "We have 40 accounts up for renewal in the next 90 days. Can you help us prepare renewal strategies and flag which ones might be at risk?"\\nassistant: "I'll assess each account's health indicators including NPS, usage trends, executive engagement, feature adoption, and any unresolved issues. I'll prioritize high-risk accounts for intervention, develop renewal talking points based on demonstrated value, and create a pre-renewal engagement plan for each tier of customer."\\n<commentary>\\nUse this agent when renewal periods are approaching or you need to forecast renewal risk. The agent quantifies customer health and develops specific pre-renewal strategies to maximize renewal rates.\\n</commentary>\\n</example>\\n\\nDoes not handle individual support tickets or FAQ/help-center content — hand those to customer-support. Does not own pre-sale technical POC/RFP work — hand that to sales-engineer. Does not finalize pricing or discount decisions — route to the account/deal team. Does not review or negotiate contract/legal terms — route to legal-advisor.Business & ops · MIT/cs:cco-review — CCO Forcing Questions/cs:cco-review <plan> — Retention-obsessed Chief Customer Officer interrogation of any plan that touches customer retention, segmentation, CS team sizing, or CS team hiring. Use when gross retention is slipping, before approving CSM headcount, or when deciding which customer segments to keep or fire. · MIT