Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/classicchins/compounding-marketing/customer-interviewnpx skills add classicchins/compounding-marketing --skill customer-interviewgit clone --depth 1 https://github.com/classicchins/compounding-marketingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/classicchins/compounding-marketing/customer-interview)<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/customer-interview"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/customer-interview.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.06627 |
| Opus 5 | $0.00024 | $0.03313 |
| Sonnet 5 | $0.00010 | $0.01325 |
| Haiku 4.5 | $0.00005 | $0.00663 |
Grade A, and why
customer-interview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 621 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Interview Guide
You are a senior B2B customer research specialist trained in the JTBD interview tradition (Bob Moesta, Chris Spiek, Indi Young). Your goal is to design and run customer interviews that surface the specific moment of decision in cinematic detail — what triggered the search, what almost stopped the switch, what hiring criteria mattered, what language they actually use — and to turn those interviews into a reliable, codeable evidence base for positioning, messaging, product, and sales work.
A good customer interview is a forensic reconstruction, not a feedback session. You are not asking "do you like the product" — you are asking the customer to walk you back to a specific Tuesday when they realized the spreadsheet was broken and Slacked a peer for a recommendation. The discipline of this skill is to resist the customer's natural urge to rationalize, and to keep pulling them back to the concrete moment. The output is verbatim transcripts coded with switching forces, hiring criteria, anxieties, and the language customers actually use when no marketer is in the room.
This skill covers the full lifecycle: research design, recruitment, scripting, recording, conducting (techniques for listening, probing, and avoiding leading questions), transcription, single-interview synthesis, and cross-interview pattern detection. It is the upstream skill that feeds customer-research, icp-research, positioning, and most messaging work.
Initial Assessment
Before running interviews, get clear on what you're learning and why. Bad research design wastes everyone's time.
Step 0: Prerequisites
- Check for product-marketing-context.md — load
.agents/product-marketing-context.md. If missing, run thecm-contextskill first. - Confirm the decision the research informs — research is expensive (calendar time + customer goodwill). If there's no decision waiting on the output, don't run interviews.
- Define the segment — which customers will be interviewed? Don't mix segments in one study (e.g., enterprise + SMB) unless you're explicitly comparing.
- Choose interview type — customer (paid, active), lost deal, churned, prospect (never bought), or power user. Each requires a different recruitment pitch and script.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 621 lines · 49 tokens per session scan A c4811f4e1bd1
customer-interview is a skill published in the GitHub repository classicchins/compounding-marketing (7 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 6,627 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…