customer-360
Skill36 starsChanged 15 days agoMITView on GitHub
Full 360-degree view of a specific customer — sessions, purchases, errors, support interactions, engagement history. Use when support needs context on a customer, sales wants to understand a prospect's behavior, or you need to investigate an escalated issue.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- intercom/claude-plugin-externaltheir own version, first seen Nov 1, 2026
- kyle-olmstead/cs-claude-enginetheir own version, first seen Oct 17, 2026
- composio-community/support-skillstheir own version, first seen Apr 10, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- composio-community/support-skills★ 18same name
- intercom/claude-plugin-external★ 3same name
- kyle-olmstead/cs-claude-engine★ 1same 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 repository45 other files it gives its agents.
- a11y-analyzerSkill
- annotation-opsSkill
- anomaly-detectorSkill
- api-monitorSkill
- benchmark-analyzerSkill
- campaign-trackerSkill
- changelog-detectiveSkill
- cohort-compassSkill
- comparisonsSkill
- dashboard-builderSkill
- deploy-radarSkill
- error-forensicsSkill
- experiment-analyzerSkill
- feature-adoptionSkill
- form-analyzerSkill
- frustration-hunterSkill
- funnel-doctorSkill
- general-analysisSkill
- heatmap-generatorSkill
- incident-responderSkill
- jira-bug-reporterSkill
- journey-builderSkill
- lifecycle-analyzerSkill
- metric-auditorSkill
- mobile-analyzerSkill
- nps-proxySkill
- onboarding-tutorSkill
- page-performanceSkill
- persona-builderSkill
- predictive-alertsSkill
- privacy-auditorSkill
- query-translatorSkill
- quick-statsSkill
- report-deckSkill
- retention-analyzerSkill
- revenue-impactSkill
- scroll-depth-analyzerSkill
- segment-wizardSkill
- session-playlistSkill
- session-reviewSkill
- session-searchSkill
- slack-reporterSkill
- user-journeySkill
- webhook-healthSkill
- weekly-digestSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
6
Distinctive
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
- Very specific: line 28
Use free fullstory:discover_groups and fullstory:get_opportunity_stats for live signals.
- Distinctive: line 34
Start with whatever identifier you have:
- Distinctive: line 40
If the lookup returns nothing, try alternative identifiers or ask the user for a more specific one.
- Distinctive: line 48
If many sessions, sample strategically:
- Very specific: line 55
Use session-context agent to scan each sampled session for:
- Distinctive: line 82
Churned: No sessions in 30+ days despite previous engagement
- Distinctive: line 125
If the user has 100+ sessions, don't read them all.
- Distinctive: line 128
If the customer has zero sessions, say so and suggest checking: "They may be using a different email, or they're a prospect who hasn't used …
“Common” is measured: kept by at least 6 in 10 of the 3 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
Customer 360
Complete view of a single customer — all their sessions, key actions, frustration events, purchases, and engagement history in one place.
When to Use
- "Show me everything about customer user@example.com"
- "What's the history of user 84721? Support escalated their ticket."
- "Sales wants to know if Acme Corp has been evaluating our product — check their sessions."
- "This enterprise customer is threatening to churn — what's their experience been?"
- "Onboard a new CSM — give them the full picture of this account."
Mental Model
A Customer 360 is a structured snapshot of one user across all dimensions available in Fullstory:
- Identity: Who they are (email, plan, role, account)
- Engagement: How often they use the product, what features
- Success: Did they achieve their goals (conversions, completions)?
- Friction: What frustrated them (errors, rage clicks, dead clicks)?
- Trajectory: Getting better or worse over time?
Use free fullstory:discover_groups and fullstory:get_opportunity_stats for live signals. Discovery accepts one scope at a time (page_id, domain, app_name, segment_id, or funnel_id); use a segment for device/user filters and the live schema for time ranges. Use computed metrics for exact custom windows.
Workflow
Step 1: Look up the customer
Start with whatever identifier you have:
fullstory:get_user_profile(userIdentifier="user@example.com")
→ returns user_id, display_name, email, plan, role, first_seen, last_seen, total_sessionsIf the lookup returns nothing, try alternative identifiers or ask the user for a more specific one.
Step 2: Get session history
fullstory:get_sessions(user_id, time_range="last_90_days", limit=50)If many sessions, sample strategically:
- First 5 sessions (onboarding experience)
- Last 5 sessions (current state)
- Any sessions with errors or high frustration signals
Step 3: Identify key events
Use session-context agent to scan each sampled session for:
- Conversions: purchases, signups, upgrades
- Friction: errors, rage clicks, dead clicks, form abandonment
- Feature usage: which features did they use? power user or casual?
- Support indicators: visited help pages, searched docs, contacted support
Step 4: Check for frustration patterns
fullstory:discover_groups → filter to this specific user's sessions
→ have they been experiencing recurring frustrations?Or build a user-specific metric:
fullstory:build_metric(
query="rage clicks and dead clicks by user 84721",
output_type="single_number"
)Step 5: Assess engagement trajectory
Compare early sessions vs recent sessions:
- Growing: More sessions, deeper feature usage, exploring advanced features
- Stable: Consistent usage, same patterns
- Declining: Fewer sessions, shallower engagement, visiting cancellation/pricing pages
- Churned: No sessions in 30+ days despite previous engagement
Step 6: Assemble the 360
## Customer 360 — user@example.com (User ID: 84721)
### Profile
- Plan: Enterprise | Role: Admin | Account: Acme Corp (50 seats)
- Customer since: March 2024 (17 months)
- Total sessions: 342 | Last active: Aug 3, 2026
### Engagement
- Last 30 days: 12 sessions (stable — matches their 6-month average)
- Primary features: Dashboard, Reports, User Management
- Power user: uses advanced filters, exports data weekly
### Success Events
- Last purchase: Jul 28 (order #4821, $1,200)
- 3 purchases in last 90 days ($3,800 total)
- No failed purchase attempts
### Friction Events
- 2 errors in last 90 days (both on /reports — likely a known bug, see JIRA-4521)
- 1 rage click event on "Export CSV" button (Jul 15 — button was slow to respond)
- No form abandonment, no dead clicks
### Trajectory: Stable ✅
Consistent enterprise user. No churn risk. One known bug affected them (JIRA-4521, fix in progress).
### Support Context
- Support ticket #2841 (Jul 15): "Export button not working" — resolved, caused by the JIRA-4521 bug
- No open tickets
### Recommended Actions
- Follow up when JIRA-4521 is deployed — this user was affected
- Good candidate for case study (long-term enterprise, high engagement)Guidelines
- The 360 is a synthesis, not a data dump. Curate — highlight what matters, skip the boring sessions.
- For enterprise/B2B customers, include account-level context if available (total seats, other users on the account).
- If the user has 100+ sessions, don't read them all. Sample: first 5, last 5, and any with errors.
- The trajectory assessment (growing/stable/declining/churned) is the most actionable insight for CS and sales.
- Privacy: don't expose PII in the output unless the user explicitly asked for it. Use masked identifiers in the report.
- If the customer has zero sessions, say so and suggest checking: "They may be using a different email, or they're a prospect who hasn't used the product yet."
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.

