More screenshots
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 agentsCustomer Interview Evidence Synthesizer
Synthesize customer interview evidence from transcripts, notes, and research files the user supplies or is authorized to share.
$1
Customer Interview Evidence Synthesizer
Example session with this skill installed
Synthesize these 5 discovery transcripts and this PM hypothesis doc. Identify themes around onboarding friction. Do not access external systems.
- Read your context and instructions
- Compiled the customer interview evidence
Decision: THEMES FOUND WITH MODERATE SUPPORT.
Theme: Setup Ambiguity (Strong) - 4/5 interviews mention 'unclear first steps'.
Contradiction: PM hypothesis assumes price is the blocker, but transcripts emphasize migration risk.
Confidence: Moderate. Need churned user data to validate.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Customer discovery notes and interview transcripts often sit in silos, resulting in fragmented insights and roadmap decisions based on founder gut-feel rather than evidence. Teams struggle to distinguish between one-off requests and genuine market themes, leading to wasted engineering effort.
What it does
- Extracts and groups evidence from transcripts, sales notes, and support summaries into traceable themes.
- Maps customer pains, jobs-to-be-done, buying triggers, and switching objections.
- Identifies contradictions between founder hypotheses, sales notes, and actual customer wording.
- Assigns confidence levels to insights based on source count and segment consistency.
- Generates quote banks and follow-up research checklists to close evidence gaps.
Why this beats prompting it yourself
Generic prompts often hallucinate consensus or ignore conflicting data points to provide a clean answer. This skill enforces strict traceability rules, explicitly flagging bias and separating team interpretation from verbatim customer language to ensure decisions are defensible.
Use cases
- Synthesizing churn interviews to identify the root cause of lost renewals versus reported price objections.
- Analyzing discovery calls to map onboarding friction points for a product redesign.
- Evaluating win/loss notes to refine sales messaging and objection handling.
- Identifying segment-specific patterns across messy, multi-source research spreadsheets.
Known limitations
Requires user-supplied text or files. Cannot access live CRM, analytics, or call-recording platforms directly.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Requires user-supplied text or files. No direct access to live CRM, billing, or call-recording platforms. Results are drafts requiring human validation.
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 3 months ago
Permissions
Permissions are limited to the active local workspace and are used to inspect user-supplied or local workspace files. The skill package does not require bundled credentials, unrestricted external network access, or automatic production changes.