$ ~/registry/skill/anthropics-small-business-skills-customer-pulse-check

SKILL

customer-pulse-check

Name: customer-pulse-check
Author: anthropics

Identify top fixable customer issues and draft response templates from support data.

Stars

★ 22,528

Source

GitHub

Updated

2026-07-11

// securityCaution

Prompt only, no code
Open source

Summary

This skill appears to be an open-source, prompt-only workflow with no declared secrets, remote endpoints, or local code execution, so the overall risk is low. It does target customer feedback from PayPal, HubSpot, and review exports, so it may handle customer data when such sources are connected in the host platform, but the materials show no clear red flags such as excessive permissions or suspicious exfiltration.

CredentialsLow risk

The materials explicitly state that no keys or environment variables are required. The skill itself does not ask the user for tokens and does not describe any credential storage, forwarding, or reuse logic. If the host platform already connects PayPal or HubSpot, that is a platform-side credential context rather than a new credential risk introduced by this README.

Network egressLow risk

No remote endpoints are declared, and the system checks label it as prompt-only. The README only describes pulling data from connected sources and generating summaries, with no indication that user data is sent to unknown or unrelated third-party services.

Code executionLow risk

As a prompt-only skill, the materials do not describe starting local processes, running scripts, installing dependencies, or invoking system commands. No execution privileges beyond normal text analysis and synthesis are indicated.

Data accessCaution

The workflow is intended to read PayPal disputes, HubSpot tickets/conversation notes, and optional review export files, then synthesize themes; this means it may handle complaint content and some personal data when connected. The access scope is broadly consistent with the stated function, and the README even instructs avoiding PII in summaries, but users should still minimize connected sources and uploaded file scope.

Supply chainLow risk

The source is an open-source GitHub repository, which makes it auditable; the system checks also mark it as open-source, substantially reducing opaque supply-chain risk. There are some caveats—no declared license, low star count, and unknown maintenance status—but the provided materials show no closed-source distribution, malicious install chain, or obvious injection indicators.

Recommendations

Only connect PayPal, HubSpot, or upload review exports when needed, and prefer the minimum necessary time window (for example via the since argument).
Verify the host platform’s data-masking practices before use so summaries and drafts do not expose unnecessary personal information.
Review the actual repository contents and recent commit history; if used in production, validate behavior in a restricted test environment first.
If future versions add external endpoints, automatic sending, or write-back actions to third-party systems, reassess the skill.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "customer-pulse-check" skill from askskill:
1. Download https://raw.githubusercontent.com/anthropics/knowledge-work-plugins/main/small-business/skills/customer-pulse-check/SKILL.md
2. Save it as ~/.claude/skills/customer-pulse-check/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Review recent customer pain points

Prompt

Please analyze PayPal disputes, HubSpot tickets, and review export data since 2024-01-01. Identify recurring customer feedback themes and output the top 3 issues worth fixing first. For each issue, include frequency, representative examples, likely causes, and a customer support response template.

Expected

A prioritized list of three fixable issues with root-cause analysis, sample feedback, and support reply templates.

Create review response templates

Prompt

Using tickets, disputes, and user reviews from the past month, identify the 3 most common types of negative feedback and draft both public review replies and private follow-up templates for each, using a professional, reassuring, and actionable tone.

Expected

Three common negative feedback categories with matching public and private response templates ready for support and operations teams.

Turn feedback into product fixes

Prompt

Please analyze all PayPal disputes, HubSpot tickets, and review exports to find the top three fixable issues affecting customer experience. Provide improvement suggestions across product, process, and communication, then format the result as a brief for the product team.

Expected

A product-team brief with the top issues, impact summary, improvement recommendations, and reusable customer communication templates.

// docs

Run the customer voice synthesis. Pull feedback signals from all connected sources, identify the themes that are actually fixable, and produce drafted responses the owner can review and send.

Parse arguments:

--since (default: last 30 days) — start date YYYY-MM-DD for the lookback window

Step 1 — Gather feedback signals

Using the customer-pulse skill workflow:

Pull PayPal disputes and chargebacks for the period: reason codes, amounts, resolution status.
Pull HubSpot support tickets and conversation notes for the period.
If review export files are available (Google Reviews CSV, Yelp export, etc.) in Files: read and parse them.
Count total signals per source.

Step 2 — Theme extraction

Cluster all signals into recurring themes. For each theme:

Count how many signals mention it
Classify: Product quality / Delivery / Billing / Communication / Expectation mismatch / Other
Rate impact: 🔴 High (revenue risk, churn) / 🟡 Medium / 🟢 Low

Step 3 — Top-3 fixable issues

Using the ticket-deflector skill workflow:

Select the top 3 themes by: frequency × impact rating. For each:

State the issue in one sentence
Explain the root cause (where evident)
Suggest a specific operational fix
Draft a customer response template

Response template format:

Subject: Re: {issue topic}

Hi {first name},

Thank you for reaching out. {Acknowledgment of their experience in 1-2 sentences}.

{What we're doing about it / what happened / resolution offered}.

{Next step or offer}.

{Sign-off}

Step 4 — Summary table

Format the output as:

Customer Voice — {date range}
Total signals: {n} ({PayPal disputes: n} | {HubSpot tickets: n} | {Reviews: n})

TOP 3 FIXABLE ISSUES
1. {Issue} ({frequency}) — {impact} — Fix: {one-line fix}
2. {Issue} ({frequency}) — {impact} — Fix: {one-line fix}
3. {Issue} ({frequency}) — {impact} — Fix: {one-line fix}

Connector failures

Run with whatever sources are connected — this command degrades gracefully. If PayPal is missing, skip dispute data and note "PayPal not connected — dispute data skipped." If HubSpot is missing, skip ticket data and note it. If no sources are connected at all, stop and tell the owner: "No feedback sources connected. Connect at least one of PayPal, HubSpot, or upload a review export CSV."

Approval gates

Never send response emails automatically. Present drafts for owner review only.
Never close HubSpot tickets or resolve PayPal disputes without explicit owner confirmation.
Never include customer PII in the summary — use first name + last initial only.

Output

Present the summary table, then each response template. Ask the owner which templates they'd like to send, then wait for explicit approval before drafting the send.