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 magnus919/agent-skills --skill product-discoverygit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/product-discovery)<a href="https://agentmods.dev/skills/magnus919/agent-skills/product-discovery"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/product-discovery/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/magnus919/agent-skills/product-discovery"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/product-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.01477 |
| Opus 5 | $0.00034 | $0.00739 |
| Sonnet 5 | $0.00014 | $0.00295 |
| Haiku 4.5 | $0.00007 | $0.00148 |
Grade A, and why
product-discovery 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 9d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Discovery — Stakeholder Map
Pre-discovery work begins before any conversation. Load this reference first when planning discovery:
| Reference | Load when | File |
|---|---|---|
| Stakeholder Mapping & Sequencing | You need to decide who to interview and in what order | references/stakeholder-mapping.md |
| Interview Protocol Design | You're designing a question stack for a specific stakeholder type | references/question-patterns.md |
| Gap Detection Techniques | You're preparing to recognize what stakeholders don't say | references/gap-detection.md |
Pipeline: Phase 0 — Discovery
RAW NEED → [MAP] → [INTERVIEW] → [SYNTHESIZE] → [DISTILL] → [VALIDATE] → SPEC.md
| | | | |
Who to What to Resolve Convert to Stakeholder
talk to ask conflicts structured review
Load the reference for the phase you're entering.
Core principles
- Closed questions confirm what you already think; open questions discover what you didn't know to ask. If the answer can be "yes" or "no," you're validating, not discovering.
- Knowledge holders come first; authority holders validate — they don't originate. The person who knows the problem is not the same person who approves the budget.
- Conflicts are almost never about what they appear to be. Surface disagreements are proxies for unstated differences in assumptions, risk tolerance, or incentives.
- Every weasel word represents a gap. "Probably," "ideally," "eventually" — each is a known issue the stakeholder hasn't committed to addressing.
Quick Start — Where to Enter
| You have this | Start here |
|---|---|
| A vague idea or problem space | Load references/stakeholder-mapping.md — identify who to interview |
| An interview scheduled with no protocol | Load references/question-patterns.md and references/gap-detection.md — design your question stack |
| Raw interview notes from one or more sessions | Load references/transcript-to-spec.md — distill into structured spec components |
| A draft spec that needs stakeholder verification | Load references/transcript-to-spec.md (Interpretation Audit Trail section) — run the validation loop |
| Stakeholders who disagree on requirements | Load references/conflict-resolution.md — classify and resolve before spec |
| Limited time with a stakeholder | Load references/time-constrained-discovery.md — maximize signal in minimal time |
| An AI agent conducting interviews | Load references/ai-conducted-discovery.md — account for sycophancy and trust dynamics |
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 8.3 KB
- README.md 1.8 KB
- references/ai-conducted-discovery.md 3.5 KB
- references/conflict-resolution.md 3.8 KB
- references/gap-detection.md 6.4 KB
- references/power-dynamics.md 2.9 KB
- references/question-patterns.md 6.1 KB
- references/stakeholder-mapping.md 3.3 KB
- references/time-constrained-discovery.md 3.0 KB
- references/transcript-to-spec.md 4.6 KB
- templates/discovery-plan.md 1001 B
- templates/distillation-worksheet.md 1.7 KB
- templates/gap-register.md 966 B
- templates/interpretation-log.md 778 B
- templates/interview-guide.md 1.4 KB
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.
- 9d ago First seen · 108 lines · 68 tokens per session scan A e7a272e47a6b
product-discovery is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,477 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 2026-09-03.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…