crm
Skill1 starsChanged 18 days agoMITView on GitHub
Customer relationship management and event-driven marketing flow engine: audience segmentation, RFM scoring, welcome and activation onboarding drips, cart and checkout recovery flows, lead nurture journeys, churn winback sequences, bulk deliverability infrastructure (SPF, DKIM, DMARC, BIMI, warming curves), and transactional SMS triggers — routed through eight modes. Use when managing client customer databases, building automated email/SMS flows in Klaviyo, Customer.io, Resend, or Postmark, rescuing abandoned carts, setting up DNS deliverability records, or segmenting user cohorts. Not for writing standalone editorial blog content (content) or agency-to-client retention QBRs (retain).
We split this skill into the rules it gives an agent
8 rules. 0 are common, 5 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 38
Every invocation resolves to exactly one mode.
- Distinctive: line 51
Only the resolved mode's reference is loaded — the rest stay on disk, saving tokens on every run.
- Very specific: line 82
Context Discovery: Read .agents/brand/voice.md for tone, .agents/brand/messaging.md for core claims, and .agents/context/accounts.md for …
- Very specific: line 83
Architecture & Deliverability (
deliverability): Verify domain DNS records (dig TXT on SPF, DKIM, DMARC) and ensure purpose-split … - Distinctive: line 87
Verification & Launch: Test webhooks with synthetic payloads, verify mobile rendering across email clients, and confirm unsubscribe …
- Very specific: line 93
Mixing Transactional and Marketing Mail: Never send bulk marketing emails from the primary root domain without a dedicated sending …
- Distinctive: line 95
Ignoring TCPA / GDPR Consent: Never trigger SMS or promotional emails without explicit, verifiable opt-in consent and one-click opt-out.
- Distinctive: line 96
Vague, Multi-Action Messages: Every email in an automated flow must have exactly ONE job.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
📬 crm — Customer Relationship & Event-Driven Marketing Flows
One unified department for client customer management and automated behavioral flows. Unifies the customer database (contacts, properties, RFM tiers, segments) with automated event-driven journeys (welcome onboarding, abandoned cart rescue, educational nurture, churn win-back, DNS deliverability infrastructure, and SMS notifications). Governed jointly by Sol (event triggers, webhook payloads, deliverability DNS) and Jasper (journey pacing, sequence psychology, high-converting copy).
Modes
Every invocation resolves to exactly one mode. Match the request, then load only the matched reference:
| Mode | Trigger phrases | Behavior | Reference |
| onboard | "welcome flow", "onboarding drip", "signup sequence", "activation flow" | Welcome sequence, product activation milestones, and new user onboarding drips | references/onboard.md |
| abandon | "abandoned cart", "browse abandonment", "checkout rescue", "trial expiry flow" | High-urgency cart recovery, browse abandonment, and expiring trial checkout rescue | references/abandon.md |
| nurture | "nurture sequence", "lead magnet drip", "educational sequence", "value drip" | Multi-part educational nurture campaigns and product-led value delivery | references/nurture.md |
| winback | "winback flow", "re-engagement", "churn recovery", "sunset unengaged" | Behavioral churn prevention, dormant re-engagement offers, and sunset cleanups | references/winback.md |
| deliverability | "deliverability audit", "spf dkim setup", "dmarc policy", "domain warming", "spam score" | Bulk sender DNS authentication, IP/domain warming curves, and bounce webhooks | references/deliverability.md |
| sms | "sms marketing", "whatsapp notifications", "sms triggers", "text broadcast" | Transactional order alerts and high-conversion broadcast SMS/WhatsApp campaigns | references/sms.md |
| contacts | "customer segments", "rfm scoring", "custom properties", "list hygiene" | Audience segmentation, RFM customer tiers, custom properties, and list cleaning | references/contacts.md |
audit | "CRM audit", "deliverability audit", "audit contact data" | Authentication-first deliverability pass (SPF/DKIM/DMARC) + list hygiene, decay, and lifecycle flows. | references/audit.md |
Only the resolved mode's reference is loaded — the rest stay on disk, saving tokens on every run.
When to Use
- Building automated email or SMS flows in Klaviyo, Resend, Customer.io, Postmark, or HubSpot.
- Setting up abandoned cart, browse abandonment, and checkout recovery funnels.
- Configuring SPF, DKIM, DMARC, and BIMI DNS records to guarantee inbox placement.
- Creating onboarding and product activation drip sequences.
- Segmenting customers into high-value VIPs, recent buyers, and at-risk churn cohorts.
- Implementing behavioral webhook events between the application database and ESP.
Quick Reference
| Mode | Primary Input | Primary Output | Gate / SLA |
onboard | Signup event, activation milestones | 5–7 send onboarding sequence w/ triggers & CTAs | 1 action per send |
abandon | Cart/Checkout abandonment event | 3-part recovery sequence (1h, 24h, 48h) w/ incentives | Zero fake discounts |
nurture | Lead magnet opt-in, trial start | 5-part educational value journey (String of Pearls) | 100% evidentiary |
winback | Inactivity trigger (30d/60d/90d) | 3-touch re-engagement offer + sunset clean rule | Unsub honored instant |
deliverability | Sending domain, DNS host, ESP | DNS records (SPF, DKIM, DMARC) + warming schedule | dig TXT verified |
sms | Opt-in consent, transactional trigger | SMS message body, compliance footer, webhook hook | TCPA compliant |
contacts | Customer database export, purchase logs | Segment criteria, RFM matrix, custom properties | Zero plain PII leak |
Procedure
- Context Discovery: Read
.agents/brand/voice.mdfor tone,.agents/brand/messaging.mdfor core claims, and.agents/context/accounts.mdfor ESP delegation access IDs. - Architecture & Deliverability (
deliverability): Verify domain DNS records (dig TXTon SPF, DKIM, DMARC) and ensure purpose-split subdomains (t.for transactional,m.for marketing). - Segmentation & RFM Modeling (
contacts): Define dynamic customer cohorts based on Recency, Frequency, and Monetary metrics before drafting messages. - Flow Trigger Engineering: Map entry triggers, conditional delay intervals, filter criteria, and exit conditions.
- Message Copycraft: Shape each send around one single clear action, 18-token standalone quotable value points, and anti-puffery standards.
- Verification & Launch: Test webhooks with synthetic payloads, verify mobile rendering across email clients, and confirm unsubscribe compliance.
Pitfalls
- Mixing Transactional and Marketing Mail: Never send bulk marketing emails from the primary root domain without a dedicated sending subdomain (
m.domain.com). - Missing Domain DNS Authentication: Sending without SPF, DKIM, and DMARC will cause Gmail, Yahoo, and Microsoft to reject or junk messages.
- Ignoring TCPA / GDPR Consent: Never trigger SMS or promotional emails without explicit, verifiable opt-in consent and one-click opt-out.
- Vague, Multi-Action Messages: Every email in an automated flow must have exactly ONE job. Multiple competing buttons destroy conversion rates.
Verification
- All 7 mode reference files exist and are syntactically valid in
references/. - Frontmatter conforms to Hermes, OpenClaw, and RFC specifications with valid argument-hint and priority.
- Deliverability mode confirms SPF, DKIM, DMARC, and RFC 8058 one-click unsubscribe compliance.
- RFM segmentation and customer database traits conform to strict data-privacy standards with zero plaintext credential leak.
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- getnao/sylph★ 195same name
- magnus919/agent-skills★ 162same name
- ShawhinT/non-coding-skills★ 40same name
- GTMify/aigtm★ 25same name
- liangdabiao/monica-crm-claude-skill★ 13same name
- MagneticStudio/claw-crm★ 0same 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 repository49 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- llms.txtllms.txt
- accountsSkill
- analyticsSkill
- automationSkill
- brandSkill
- client-commsSkill
- contentSkill
- databaseSkill
- designSkill
- devopsSkill
- growthSkill
- gtmSkill
- incident-responseSkill
- mobileSkill
- opsSkill
- paidadsSkill
- qa-launchSkill
- researchSkill
- retainSkill
- sales-enablementSkill
- seoSkill
- smmSkill
- telegramSkill
- webdevSkill
- context-anchorSkill
- coupling-routerSkill
- evidence-ledgerSkill
- relaySkill
- secretarySkill
- gitSkill
- new-projectSkill
- updateagentsSkill
- updatedocsSkill
- animateSkill
- designscopeSkill
- refactorSkill
- auditSkill
- code-reviewSkill
- dead-letterSkill
- gauntlet-loopSkill
- humanizeSkill
- muse-securitySkill
- puaSkill
- clean-system-cacheSkill
- coachSkill
- periodic-retreatSkill
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
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.