customer-research

Name: customer-research
Author: anthropics

2.3kinstalls2.7kforks

How to install customer-research?

anthropics/knowledge-work-plugins/customer-research

$npx -y skills add anthropics/knowledge-work-plugins --skill customer-research

Installs into the current project.

Summary

Multi-source research on a customer question or topic with source attribution. Use when a customer asks something you need to look up, investigating whether a bug has been reported before, checking what was previously told to a specific account, or gathering background before dra

Files · 1

View on GitHub

SKILL.md

1	# /customer-research
2
3	> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md).
4
5	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.
6
7	## Usage
8
9	```
10	/customer-research <question or topic>
11	```
12
13	## Workflow
14
15	### 1. Parse the Research Request
16
17	Identify what type of research is needed:
18	- Customer question: Something a customer has asked that needs an answer (e.g., "Does our product support SSO with Okta?")
19	- Issue investigation: Background on a reported problem (e.g., "Has this bug been reported before? What's the known workaround?")
20	- Account context: History with a specific customer (e.g., "What did we tell Acme Corp last time they asked about this?")
21	- Topic research: General topic relevant to support work (e.g., "Best practices for webhook retry logic")
22
23	Before searching, clarify what you're actually trying to find:
24	- Is this a factual question with a definitive answer?
25	- Is this a contextual question requiring multiple perspectives?
26	- Is this an exploratory question where the scope is still being defined?
27	- Who is the audience for the answer (internal team, customer, leadership)?
28
29	### 2. Search Available Sources
30
31	Search systematically through the source tiers below, adapting to what is connected. Don't stop at the first result — cross-reference across sources.
32
33	Tier 1 — Official Internal Sources (highest confidence):
34	- ~~knowledge base (if connected): product docs, runbooks, FAQs, policy documents
35	- ~~cloud storage: internal documents, specs, guides, past research
36	- Product roadmap (internal-facing): feature timelines, priorities
37
38	Tier 2 — Organizational Context:
39	- ~~CRM notes: account notes, activity history, previous answers, opportunity details
40	- ~~support platform (if connected): previous resolutions, known issues, workarounds
41	- Meeting notes: previous discussions, decisions, commitments
42
43	Tier 3 — Team Communications:
44	- ~~chat: search for the topic in relevant channels; check if teammates have discussed or answered this before
45	- ~~email: search for previous correspondence on this topic
46	- Calendar notes: meeting agendas and post-meeting notes
47
48	Tier 4 — External Sources:
49	- Web search: official documentation, blog posts, community forums
50	- Public knowledge bases, help centers, release notes
51	- Third-party documentation: integration partners, complementary tools
52
53	Tier 5 — Inferred or Analogical (use when direct sources don't yield answers):
54	- Similar situations: how similar questions were handled before
55	- Analogous customers: what worked for comparable accounts
56	- General best practices: industry standards and norms
57
58	### 3. Synthesize Findings
59
60	Compile results into a structured research brief:
61
62	```
63	## Research: [Question/Topic]
64
65	### Answer
66	[Clear, direct answer to the question — lead with the bottom line]
67
68	Confidence: [High / Medium / Low]
69	[Explain what drives the confidence level]
70
71	### Key Findings
72
73	From [Source 1]:
74	- [Finding with specific detail]
75	- [Finding with specific detail]
76
77	From [Source 2]:
78	- [Finding with specific detail]
79
80	### Context & Nuance
81	[Any caveats, edge cases, or additional context that matters]
82
83	### Sources
84	1. [Source name/link] — [what it contributed]
85	2. [Source name/link] — [what it contributed]
86	3. [Source name/link] — [what it contributed]
87
88	### Gaps & Unknowns
89	- [What couldn't be confirmed]
90	- [What might need verification from a subject matter expert]
91
92	### Recommended Next Steps
93	- [Action if the answer needs to go to a customer]
94	- [Action if further research is needed]
95	- [Who to consult for verification if needed]
96	```
97
98	### 4. Handle Insufficient Sources
99
100	If no connected sources yield results:
101
102	- Perform web research on the topic
103	- Ask the user for internal context:
104	- "I couldn't find this in connected sources. Do you have internal docs or knowledge base articles about this?"
105	- "Has your team discussed this topic before? Any ~~chat channels I should check?"
106	- "Is there a subject matter expert who would know the answer?"
107	- Be transparent about limitations:
108	- "This answer is based on web research only — please verify against your internal documentation before sharing with the customer."
109	- "I found a possible answer but couldn't confirm it from an authoritative internal source."
110
111	### 5. Customer-Facing Considerations
112
113	If the research is to answer a customer question:
114
115	- Flag if the answer involves product roadmap, pricing, legal, or security topics that may need revi

People who liked this also viewed

6 picks

Type

customer-research

2.3kinstalls2.7kforks

View on GitHub

How to install customer-research?

anthropics/knowledge-work-plugins/customer-research

$npx -y skills add anthropics/knowledge-work-plugins --skill customer-research

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# /customer-research
2
3	> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md).
4
5	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.
6
7	## Usage
8
9	```
10	/customer-research <question or topic>
11	```
12
13	## Workflow
14
15	### 1. Parse the Research Request
16
17	Identify what type of research is needed:
18	- Customer question: Something a customer has asked that needs an answer (e.g., "Does our product support SSO with Okta?")
19	- Issue investigation: Background on a reported problem (e.g., "Has this bug been reported before? What's the known workaround?")
20	- Account context: History with a specific customer (e.g., "What did we tell Acme Corp last time they asked about this?")
21	- Topic research: General topic relevant to support work (e.g., "Best practices for webhook retry logic")
22
23	Before searching, clarify what you're actually trying to find:
24	- Is this a factual question with a definitive answer?
25	- Is this a contextual question requiring multiple perspectives?
26	- Is this an exploratory question where the scope is still being defined?
27	- Who is the audience for the answer (internal team, customer, leadership)?
28
29	### 2. Search Available Sources
30
31	Search systematically through the source tiers below, adapting to what is connected. Don't stop at the first result — cross-reference across sources.
32
33	Tier 1 — Official Internal Sources (highest confidence):
34	- ~~knowledge base (if connected): product docs, runbooks, FAQs, policy documents
35	- ~~cloud storage: internal documents, specs, guides, past research
36	- Product roadmap (internal-facing): feature timelines, priorities
37
38	Tier 2 — Organizational Context:
39	- ~~CRM notes: account notes, activity history, previous answers, opportunity details
40	- ~~support platform (if connected): previous resolutions, known issues, workarounds
41	- Meeting notes: previous discussions, decisions, commitments
42
43	Tier 3 — Team Communications:
44	- ~~chat: search for the topic in relevant channels; check if teammates have discussed or answered this before
45	- ~~email: search for previous correspondence on this topic
46	- Calendar notes: meeting agendas and post-meeting notes
47
48	Tier 4 — External Sources:
49	- Web search: official documentation, blog posts, community forums
50	- Public knowledge bases, help centers, release notes
51	- Third-party documentation: integration partners, complementary tools
52
53	Tier 5 — Inferred or Analogical (use when direct sources don't yield answers):
54	- Similar situations: how similar questions were handled before
55	- Analogous customers: what worked for comparable accounts
56	- General best practices: industry standards and norms
57
58	### 3. Synthesize Findings
59
60	Compile results into a structured research brief:
61
62	```
63	## Research: [Question/Topic]
64
65	### Answer
66	[Clear, direct answer to the question — lead with the bottom line]
67
68	Confidence: [High / Medium / Low]
69	[Explain what drives the confidence level]
70
71	### Key Findings
72
73	From [Source 1]:
74	- [Finding with specific detail]
75	- [Finding with specific detail]
76
77	From [Source 2]:
78	- [Finding with specific detail]
79
80	### Context & Nuance
81	[Any caveats, edge cases, or additional context that matters]
82
83	### Sources
84	1. [Source name/link] — [what it contributed]
85	2. [Source name/link] — [what it contributed]
86	3. [Source name/link] — [what it contributed]
87
88	### Gaps & Unknowns
89	- [What couldn't be confirmed]
90	- [What might need verification from a subject matter expert]
91
92	### Recommended Next Steps
93	- [Action if the answer needs to go to a customer]
94	- [Action if further research is needed]
95	- [Who to consult for verification if needed]
96	```
97
98	### 4. Handle Insufficient Sources
99
100	If no connected sources yield results:
101
102	- Perform web research on the topic
103	- Ask the user for internal context:
104	- "I couldn't find this in connected sources. Do you have internal docs or knowledge base articles about this?"
105	- "Has your team discussed this topic before? Any ~~chat channels I should check?"
106	- "Is there a subject matter expert who would know the answer?"
107	- Be transparent about limitations:
108	- "This answer is based on web research only — please verify against your internal documentation before sharing with the customer."
109	- "I found a possible answer but couldn't confirm it from an authoritative internal source."
110
111	### 5. Customer-Facing Considerations
112
113	If the research is to answer a customer question:
114
115	- Flag if the answer involves product roadmap, pricing, legal, or security topics that may need revi

People who liked this also viewed

6 picks

Type