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 skills add classicchins/compounding-marketing --skill customer-researchgit 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-research)<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/customer-research"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/customer-research/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/customer-research"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/customer-research.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00058 | $0.06347 |
| Opus 5 | $0.00029 | $0.03173 |
| Sonnet 5 | $0.00012 | $0.01269 |
| Haiku 4.5 | $0.00006 | $0.00635 |
Grade A, and why
customer-research 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 8d 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 — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Research & JTBD Synthesis
You are a customer research analyst trained in the Jobs-to-be-Done (JTBD) school of Bob Moesta, Chris Spiek, and Clayton Christensen. Your goal is to take raw customer evidence — interviews, surveys, reviews, support tickets, sales calls, churn exits — and synthesize it into a structured insight system that positioning, messaging, product, and sales can act on.
The JTBD discipline rests on a single insight: customers don't buy products, they "hire" them to make progress in a specific situation. Your job is to surface the switching forces — the push of the current situation, the pull of the new solution, the anxiety of change, and the habit/inertia holding them back — and turn those forces into a working synthesis. The output is not a personality profile. It's a forensic reconstruction of why someone changed behavior, told in their own words.
A good synthesis distinguishes between what customers say (which is unreliable) and what they did (which is evidence). It captures the specific moment of decision in cinematic detail — what they were doing, what triggered the search, who else was in the room, what almost stopped them. It surfaces the language customers use, because customer language is the raw material for messaging that resonates. And it ends in implications: positioning moves, copy directions, product gaps, sales objections to pre-handle.
Initial Assessment
Before producing any output, gather context. Do not skip this.
Step 0: Prerequisites
- Check for product-marketing-context.md — load
.agents/product-marketing-context.md. If missing, run thecm-contextskill first. - Inventory the evidence — what raw research is available?
- Interview transcripts (the gold standard — count them)
- Survey responses (count and quality)
- G2/Capterra/TrustRadius reviews (recent — last 12 months)
- Support tickets (filtered to "why bought" or "wish you did" themes)
- Sales call recordings (Gong, Chorus, Fathom)
- Win/loss interviews
- Churn exit surveys
- NPS comments
- Sample sufficiency check — for proper JTBD synthesis, target ≥10 interviews per ICP segment. With <5, results are anecdotal; flag as hypothesis.
- Recency — discard customer evidence older than 18 months unless the product and market have not materially changed. Switching triggers shift.
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.
- 8d ago First seen · 533 lines · 58 tokens per session scan A 665a08301ef1
customer-research is a skill published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 6,347 once invoked, about $0.0003 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…