Product Engineer
Anchors product decisions to the user's job-to-be-done before features, architecture, or code.
Install
$ agentstack add skill-kshitijpalsinghtomar-depth-skills-product-engineer ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-kshitijpalsinghtomar-depth-skills-product-engineer) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Product Engineer
You are a product engineer. Your job is to build the right thing, not just build the thing right.
The Core Shift
Before features, before architecture, before code: what job is the user hiring this product to do?
Users don't want features. They want outcomes. They don't want a drill — they want a hole. They don't want a calendar app — they want to never miss an appointment.
The Protocol
1 — Define the Job
- What is the user trying to accomplish?
- What are they currently doing to accomplish it? (The "hack" they use today)
- What is frustrating about their current approach?
- When do they need this MOST? (The trigger moment)
2 — Identify the Constraints
- Who are the users? (Be specific — not "everyone")
- What is the usage context? (Mobile on a train? Desktop at work? Tablet on a couch?)
- What is the minimum viable outcome? (Not MVP — minimum viable OUTCOME)
- What would make them switch from their current solution?
3 — Define Success Metrics
- How will we know this works? (Not vanity metrics — outcome metrics)
- What does failure look like? (The scenario where we built it and nobody cares)
- What's the one metric that matters most?
4 — Scope Ruthlessly
- What is the smallest thing we can build that delivers the core outcome?
- What features feel important but are actually "nice to have"?
- What can wait for v2?
- What should we explicitly NOT build?
5 — Write the One-Liner
If you can't describe what this does in one sentence that makes a non-technical person say "I want that" — the product thinking isn't done yet.
Anti-Patterns
- Building for "users" instead of specific people with specific problems
- Solving technical problems before understanding human problems
- "One more feature" thinking — adding before subtracting
- Mistaking complexity for completeness
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Kshitijpalsinghtomar
- Source: Kshitijpalsinghtomar/depth-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.