data-consumer-discovery SKILL.md skillA
data-consumer-discovery from hollandkevint/data-product-operator is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add hollandkevint/data-product-operator/data-consumer-discovery@v0.1.0Pins v0.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- hollandkevint/data-product-operator
- Path
skills/data-consumer-discovery/SKILL.md- Versions recorded
- 2
- Latest version
- v0.1.0, committed Nov 3, 2026
- First version recorded
- Feb 20, 2026
- Size
- 4,378 bytes
- Repository stars
- 5
- License
- MIT
Discover what internal data consumers actually need. Adapted Mom Test and JTBD for data teams. Use when conducting user research, interviewing stakeholders, gathering consumer requirements, running discovery sessions, or when someone asks "what do they need?" or "how do I figure out what to build?".
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
## Five Discovery Questions Ask these in order. Each builds on the prior answer: 1. **"What decision are you trying to make?"** Not "what data do you need?" Data requests are solutions. Decisions are the actual problem. If they say "I need a dashboard," ask what decision the dashboard enables. 2. **"Walk me through the last time you made this decision."** Concrete past behavior beats hypothetical future needs. Listen for: where the data came from, how long it took, what they trusted, what they second-guessed. 3. **"Where did the data come from? How much did you trust it?"** Trust is the adoption barrier for data products. A perfect pipeline that nobody trusts is useless. Map their trust signals: source familiarity, recency, whether they cross-checked. 4. **"What did you end up doing?"** The action reveals the real need. "I exported to Excel and manually combined three reports" tells you more than any requirements document. 5. **"If you could get this answer in under a minute, what changes?"** Gauges impact. If the answer is "nothing much," the problem isn't painful enough to build for. If it's "we could catch billing errors before they go out," you have a validated need. …
Read the whole file at its exact version.
How to install
mdr add hollandkevint/data-product-operator/data-consumer-discovery@sha256:b9cb8bd7dd7644bbThe line at the top of this page pins the label v0.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_g5svzqx7bybkyyin)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Feb 20, 2026 and Nov 3, 2026, about one every 256 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.1.0 latest | 2026-11-03 | 2939ae2 | 4,378 B | A | view · diff |
| v0.1.0 | 2026-02-20 | b2b7f45 | 4,385 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4378 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
hollandkevint/data-product-operator · 5 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_g5svzqx7bybkyyin GET https://markdownregistry.com/api/v1/resolve?ref=hollandkevint/data-product-operator/data-consumer-discovery GET https://markdownregistry.com/api/v1/blob/b9cb8bd7dd7644bb88db08ec3419bf34865a35b84d1c26aac0d6ce788f948e6a
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.