customer-pulse
anthropics/knowledge-work-plugins
How to install customer-pulse
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill customer-pulseFull instructions (SKILL.md)
Source of truth, from anthropics/knowledge-work-plugins.
name: customer-pulse version: 0.2.0 description: > Aggregates PayPal disputes, HubSpot feedback and tickets, and email sentiment (plus pasted or exported Google/Yelp reviews) into a themes report with verbatim evidence and a "do these three things this week" list. Use when the user asks how customers are feeling, for review analysis, what people are saying, or about disputes.
Customer Pulse
Quick start
Ask: "How are customers feeling this month?"
Claude pulls disputes, tickets, email threads, and Intercom conversations for the last 30 days, groups them into 3–5 themes with verbatim evidence, and delivers a "do these 3 things this week" action list.
To include Google/Yelp reviews, paste them after triggering — or say "I have some reviews to add."
Workflow
-
Set the date window. Default: last 30 days. If the user specifies a range, use it.
-
Pull PayPal disputes. Fetch disputes opened in the window. If the PayPal API returns a rate-limit error, skip and add
PayPal: rate-limited — not includedto the Sources section. Do not retry; do not error. See reference/gotchas.md for the rate-limit pattern. -
Pull HubSpot tickets and feedback. Fetch open and recently closed tickets. If 0 tickets exist, record
HubSpot tickets: 0and continue — do not surface a warning. -
Pull Gmail threads. Search for threads in the window containing:
refund cancel unhappy issue problem disappointed frustrated broken late slow wrong missing. Extract subject lines and 1–2 sentence excerpts per thread. -
Pull Intercom conversations. Call
search_conversationsto fetch open and recently closed conversations. Then callget_conversationfor each conversation ID returned to access the fullconversation_parts. Extract parts whereauthor.type === 'user'— these are customer messages. Exclude parts whereauthor.typeisadminorbot. -
Accept pasted reviews (optional). If the user pastes Google or Yelp review text, include it in the source pool tagged as
[Review]. No connector required. -
Extract themes. Group all evidence into 3–5 recurring themes. Each theme must include:
- A one-sentence label (e.g., "Shipping delays causing repeat complaints")
- 2–3 verbatim quotes with source tags:
[PayPal],[HubSpot],[Gmail],[Intercom], or[Review] - A signal count (how many items touch this theme)
Verbatim quotes are non-negotiable — never paraphrase. See reference/gotchas.md for the verbatim anti-pattern.
-
Generate the "do these 3 things" list. Rank themes by signal count. Pick the top 3 and write one concrete, owner-actionable step per theme. Format as a numbered checklist.
-
Deliver the report. Structure the output with these sections in order:
- Header — H2 with "Customer Pulse" and the date range.
- Sources pulled — Bullet list with signal counts per source (PayPal disputes, HubSpot tickets, Gmail threads, Intercom conversations, pasted reviews). Note any source that was rate-limited and skipped.
- Themes — For each theme, show a bold numbered theme label with the signal count, followed by two verbatim quotes as blockquotes, each attributed to its source.
- Do these 3 things this week — Numbered list of three concrete, owner-actionable steps, each tied to one of the top themes.
For a complete worked example, see reference/examples/example-report.md.
Approval gates
This skill is read-only — it does not post, send, reply, or modify any records. No approval gate is required.
Reference
- reference/gotchas.md — PayPal rate limits, HubSpot empty state, verbatim quote requirement, Gmail keyword drift
- reference/examples/example-report.md — full worked example output
Related skills
More from anthropics/knowledge-work-plugins and the wider catalog.
data-visualization
Pick the right chart and generate publication-quality Python visualizations with built-in design and accessibility best practices.
code-review
Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a change for N+1 queries, injection risks, missing edge cases, or error handling gaps.
documentation
Write and maintain technical documentation. Trigger with "write docs for", "document this", "create a README", "write a runbook", "onboarding guide", or when the user needs help with any form of technical writing — API docs, architecture docs, or operational runbooks.
build-dashboard
Build an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring snapshot, or needing multiple charts with filters in one browser-openable file.
task-management
Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments.
memory-management
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.