Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
DeepSeek
Muse+22 moreClaude CodeCursorCodex CLIDeepSeekMuse
Dots
Manus
Grok
Grok Bot+18 agentsVoice of Customer Intelligence OS
Turn interviews, reviews, calls, and support conversations into evidence-traced messaging and offer decisions.
$6
Voice of Customer Intelligence OS
Example session with this skill installed
Analyze this six-source sample for a project-management SaaS:
S1 interview: "I spend Monday morning rebuilding the same status report."
S2 support ticket: "Our executives won't log in; I need a PDF."
S3 sales call: "Can it prove where every number came from?"
S4 interview: "Setup took too long, so the team went back to spreadsheets."
S5 review: "The dashboard is clean, but client exports are too basic."
S6 sales call: "We need SSO before procurement will approve it."
Build a VOC insight pack without treating this small sample as market prevalence.
- Read your context and instructions
- Compiled the voice of customer
Voice of Customer insight pack
Sample boundary: This analysis covers six qualitative sources. It identifies signals and hypotheses; it does not estimate market prevalence or statistical demand.
| Theme | Evidence | Source diversity | Confidence |
|---|---|---|---|
| Executive/client-ready reporting | S2 needs a PDF; S5 says exports are too basic | Support + review | Medium |
| Repetitive status work | S1 rebuilds the same report every Monday | One interview | Low |
| Traceability of numbers | S3 asks where every number came from | One sales call | Low |
| Adoption friction | S4 returned to spreadsheets after slow setup | One interview | Low |
| Enterprise procurement | S6 requires SSO for approval | One sales call | Low |
Buyer-language bank
- “I spend Monday morning rebuilding the same status report.” — repeated-work pain, S1.
- “Our executives won't log in; I need a PDF.” — stakeholder-access constraint, S2.
- “Can it prove where every number came from?” — trust and auditability requirement, S3.
- “Setup took too long” — time-to-value objection, S4.
- “Client exports are too basic.” — external-deliverable gap, S5.
- “We need SSO before procurement will approve it.” — enterprise gate, S6.
Messaging hypotheses
Primary: Client-ready reports with traceable numbers, without rebuilding updates by hand. Support: S1, S2, S3, S5. Confidence: Medium.
2.
Adoption: Reach the first useful report before the team falls back to spreadsheets. Support: S4. Confidence: Low.
3. Enterprise: Reporting workflows that are ready for procurement requirements. Support: S6. Confidence: Low.
Objection and proof map
| Objection | Proof needed | Current evidence gap |
|---|---|---|
| Setup may take too long | Time-to-first-report demonstration | Only one setup-friction source |
| Exports may not satisfy clients | Sample executive PDF and configurable export | No detail on required export fields |
| Numbers may be hard to trust | Visible source lineage for every metric | No usability evidence for audit trails |
| Procurement may block adoption | Clear SSO/security documentation | Procurement context appears once |
Offer opportunities
Executive Reporting Sprint: a guided setup that produces a traceable executive PDF quickly. Validate with S1, S2, S3, and S5-type buyers before packaging.
Migration Confidence Review: map setup steps, likely delays, and spreadsheet fallback risks. Validate with at least five recent evaluators.
Contradictions and unknowns
No direct contradictions appear in this small sample. Unknowns include company size, role, buying stage, export requirements, acceptable setup time, and whether SSO is common outside enterprise deals.
Validation backlog
Interview 8–10 buyers across agency, mid-market, and enterprise contexts. Ask for the last status report they created, who consumed it, how long it took, what proof was challenged, what blocked setup, and which procurement controls were mandatory. Keep every new claim linked to a source ID.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Strategists often rely on gut feel or generic personas because manual analysis of raw customer transcripts, reviews, and survey data is slow and prone to bias. It is difficult to transform hundreds of scattered data points into actionable messaging without losing the original buyer's voice.
What it does
- Synthesizes transcripts, reviews, and survey data into evidence-traced buyer language and segments.
- Extracts atomic units of evidence including triggers, pain points, objections, and desired outcomes.
- Maps the buyer journey from initial trigger through to retention signals based on real qualitative data.
- Generates a language bank and objection taxonomy using direct quotes and specific buyer phrasing.
- Identifies contradictions and unanswered questions to prevent overconfidence in narrow data sets.
Why this beats prompting it yourself
General prompts often hallucinate personas or fabricate market demand when data is thin. This skill enforces a strict evidence-ledger methodology that distinguishes between direct quotes and analyst interpretation, ensuring every recommendation cites specific source IDs and maintains a clear audit trail.
Use cases
- Synthesizing dozens of sales call transcripts into a high-converting message architecture.
- Auditing product reviews to identify specific workarounds and unmet feature needs.
- Building evidence-based segment cards for product marketing teams.
- Developing sales talk tracks and proof hierarchies grounded in actual customer objections.
Known limitations
Does not perform quantitative market sizing or statistical prevalence analysis. Requires raw qualitative data inputs to function; it will not fabricate insights from zero data.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Marketing & SEO.
Requires qualitative source data; cannot perform statistical population modeling. Does not support PII extraction or automated CRM syncing.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Permissions
No special permissions declared or detected