Success Story Miner

Success Story Miner

Prerequisites

This skill needs the iGPT MCP at https://mcp.igpt.ai/.

If the MCP tools aren't available or return an auth error, tell the user to install the iGPT plugin (/plugin marketplace add igptai/skills) or add https://mcp.igpt.ai/ as a connector, then complete OAuth and say "ready". Retry once after they confirm. Never invent tokens or OAuth URLs. For deeper troubleshooting: https://raw.githubusercontent.com/igptai/skills/main/shared/mcp-guard.md

---

What This Skill Does

Scans all customer email threads for moments of genuine satisfaction — customers sharing positive results, expressing appreciation, reporting outcomes achieved, and making statements that could be used as testimonials or case study material.

---

Workflow

1. Before calling any tool, collect these values from the user. Offer the

defaults and let the user override them; do not invent values they did not give.

• [time_range] — what window of email to scan. The user may give this

in any form ("last 12 months", "the last year", "May 2024", "since launch"). Default: the last 12 months. Keep the user's natural phrasing for use in the ask input; convert to ISO dates separately for the search call.

• [account_scope] — either "all" (default) or the name of a specific

customer account to focus on.

• [accountclause] — derived. When [accountscope] is not "all", set

to " for account [accountscope]". When [accountscope] is "all", set to empty string.

1. Call search with:

• query: thank you great results love excellent working well impressed

achieved solved helped outcome success (if [account_scope] is not "all", append the account name to the query)

• datefrom: ISO start date derived from [timerange]
• dateto: ISO end date derived from [timerange] (or today if open-ended)

1. Call ask with:

• input: Review all customer email threads from [timerange][accountclause]. Find every moment where a customer expressed genuine satisfaction, reported a positive outcome or result, praised the product or team, or said something that could be used as a testimonial or case study quote. For each success moment note the customer, what they said, the context of the win, and the potential value as a proof point or case study.
• output_format:

{ "strict": true, "schema": { "type": "object", "description": "Customer success story and testimonial report mined from email history", "additionalProperties": false, "properties": { "asof": { "type": "string", "description": "ISO8601 date when this report was generated" }, "successmoments": { "type": "array", "description": "List of every customer success moment found in email", "items": { "type": "object", "description": "A single customer success moment with testimonial potential", "additionalProperties": false, "properties": { "customer": { "type": "string", "description": "Name of the customer company" }, "contact": { "type": "string", "description": "Name or role of the customer contact who expressed this success" }, "date": { "type": "string", "description": "ISO8601 date when this success moment appeared in email" }, "successtype": { "type": "string", "description": "Category of success moment", "enum": [ "quantifiedresult", "problemsolved", "teampraise", "productpraise", "recommendationoffer", "renewalenthusiasm", "expansioninterest", "generalsatisfaction" ] }, "quoteorsummary": { "type": "string", "description": "Direct quote or close paraphrase of what the customer said" }, "businesscontext": { "type": "string", "description": "Brief description of the business situation that led to this success" }, "testimonialpotential": { "type": "string", "description": "How strong this moment is as testimonial or case study material", "enum": ["excellent", "good", "moderate", "low"] }, "casestudyangle": { "type": "string", "description": "The story angle this success moment could support in a case study" } }, "required": [ "customer", "contact", "date", "successtype", "quoteorsummary", "businesscontext", "testimonialpotential", "casestudyangle" ] } }, "excellentcount": { "type": "number", "description": "Number of success moments rated as excellent testimonial material" }, "topcandidates": { "type": "array", "description": "The top three customers most suitable for case study or testimonial outreach", "items": { "type": "string", "description": "Name of a customer who is a strong case study candidate" } }, "summary": { "type": "string", "description": "One or two sentence summary of success moments found and top case study candidates" } }, "required": [ "asof", "successmoments", "excellentcount", "topcandidates", "summary" ] } }

1. Present excellent and good testimonial moments first, ordered by potential.

Lead with top candidates and excellent count.

1. Ask: "Would you like me to draft a case study request or testimonial ask

for any of these customers?"

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: igptai
• Source: igptai/skills
• License: MIT
• Homepage: https://www.igpt.ai

Install and usage instructions live in the source repository linked above.