$ ~/registry/skill/anthropics-customer-support-skills-customer-research

SKILL

customer-research

Name: customer-research
Author: anthropics

Research customer questions across sources with citations to support accurate responses.

Stars

★ 22,528

Source

GitHub

Updated

2026-07-11

// securityCaution

Prompt only, no code
Open source

Summary

The material indicates this is an open-source, prompt-only research workflow with no declared secrets, remote endpoints, or local execution capability, so overall risk is low. Caution is still warranted because its intended use spans multiple data sources, and actual connected tools may introduce normal organizational data access and egress exposure.

CredentialsLow risk

The material explicitly states that no keys or environment variables are required; as a prompt-only skill, it does not itself handle credentials, and there is no sign of credential harvesting or export instructions.

Network egressCaution

No fixed remote endpoint is declared, and the skill itself does not directly perform networking; however, the README explicitly instructs searching connected internal systems, chat, email, and external web sources, so in real deployments user queries and retrieved content may be sent out through those existing tools as normal egress.

Code executionLow risk

Based on the material and the system checks, this is a prompt-only skill with no indication that it starts local processes, runs scripts, or invokes system commands.

Data accessCaution

The README targets CRM, support platforms, cloud storage, chat, email, meeting notes, and account history, indicating it may drive access to broad organizational and customer-context data; while this is normal for a research skill, access should remain bounded by connector permissions and least privilege to avoid over-broad retrieval of sensitive records.

Supply chainLow risk

The source is an open-source GitHub repository, anthropics/knowledge-work-plugins, which makes the content auditable and materially reduces supply-chain opacity; limitations include no declared license, 0 stars, and unknown maintenance status, but these alone do not constitute a high-risk red flag.

Recommendations

Enable it only in a controlled environment and verify that connected CRM, email, and chat tools use least-privilege permissions.
For research involving customer accounts, email, or meeting notes, classify data first and avoid retrieving unnecessary sensitive content.
If compliance review is required, verify the repository license and maintenance status before adopting it in production workflows.
Keep source attribution and access audit logs for research outputs so reviewers can verify whether inappropriate data sources were used.

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

// download

Download SKILL.mdInstall manifest ↗

// examples

Check whether an issue was reported before

Prompt

Please research whether this customer-reported issue has been reported before. Search tickets, internal docs, release notes, and bug records. Summarize similar cases, first occurrence, current status, and cite the source link for each conclusion.

Expected

A cited research summary showing prior reports, related cases, and the current handling status.

Review what was previously communicated to an account

Prompt

Please find what we previously told this customer. Compile key commitments, explanations, and timelines from emails, CRM notes, ticket replies, and meeting notes, and list sources in chronological order.

Expected

A chronological summary of past customer communications with key statements and supporting sources.

Gather background before drafting a response

Prompt

Before I reply to the customer, research the background on this topic. Combine product docs, help center articles, past cases, and team notes. Extract key facts, known limitations, actionable recommendations, and include citations.

Expected

A response-ready background brief with facts, limitations, recommendations, and citations.

// docs

/customer-research

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Multi-source research on a customer question, product topic, or account-related inquiry. Synthesizes findings from all available sources with clear attribution and confidence scoring.

Usage

/customer-research <question or topic>

Workflow

1. Parse the Research Request

Identify what type of research is needed:

Customer question: Something a customer has asked that needs an answer (e.g., "Does our product support SSO with Okta?")
Issue investigation: Background on a reported problem (e.g., "Has this bug been reported before? What's the known workaround?")
Account context: History with a specific customer (e.g., "What did we tell Acme Corp last time they asked about this?")
Topic research: General topic relevant to support work (e.g., "Best practices for webhook retry logic")

Before searching, clarify what you're actually trying to find:

Is this a factual question with a definitive answer?
Is this a contextual question requiring multiple perspectives?
Is this an exploratory question where the scope is still being defined?
Who is the audience for the answer (internal team, customer, leadership)?

2. Search Available Sources

Search systematically through the source tiers below, adapting to what is connected. Don't stop at the first result — cross-reference across sources.

Tier 1 — Official Internal Sources (highest confidence):

~~knowledge base (if connected): product docs, runbooks, FAQs, policy documents
~~cloud storage: internal documents, specs, guides, past research
Product roadmap (internal-facing): feature timelines, priorities

Tier 2 — Organizational Context:

~~CRM notes: account notes, activity history, previous answers, opportunity details
~~support platform (if connected): previous resolutions, known issues, workarounds
Meeting notes: previous discussions, decisions, commitments

Tier 3 — Team Communications:

~~chat: search for the topic in relevant channels; check if teammates have discussed or answered this before
~~email: search for previous correspondence on this topic
Calendar notes: meeting agendas and post-meeting notes

Tier 4 — External Sources:

Web search: official documentation, blog posts, community forums
Public knowledge bases, help centers, release notes
Third-party documentation: integration partners, complementary tools

Tier 5 — Inferred or Analogical (use when direct sources don't yield answers):

Similar situations: how similar questions were handled before
Analogous customers: what worked for comparable accounts
General best practices: industry standards and norms

3. Synthesize Findings

Compile results into a structured research brief:

## Research: [Question/Topic]

### Answer
[Clear, direct answer to the question — lead with the bottom line]

**Confidence:** [High / Medium / Low]
[Explain what drives the confidence level]

### Key Findings

**From [Source 1]:**
- [Finding with specific detail]
- [Finding with specific detail]

**From [Source 2]:**
- [Finding with specific detail]

### Context & Nuance
[Any caveats, edge cases, or additional context that matters]

### Sources
1. [Source name/link] — [what it contributed]
2. [Source name/link] — [what it contributed]
3. [Source name/link] — [what it contributed]

### Gaps & Unknowns
- [What couldn't be confirmed]
- [What might need verification from a subject matter expert]

### Recommended Next Steps
- [Action if the answer needs to go to a customer]
- [Action if further research is needed]
- [Who to consult for verification if needed]