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 Uxcel-Lab/product-skills --skill discoverygit clone --depth 1 https://github.com/Uxcel-Lab/product-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/uxcel-lab/product-skills/discovery)<a href="https://agentmods.dev/skills/uxcel-lab/product-skills/discovery"><img src="https://agentmods.dev/badge/skills/uxcel-lab/product-skills/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/uxcel-lab/product-skills/discovery"><img src="https://agentmods.dev/badge/skills/uxcel-lab/product-skills/discovery.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 | $0.00147 | $0.03126 |
| Opus 5 | $0.00073 | $0.01563 |
| Sonnet 5 | $0.00029 | $0.00625 |
| Haiku 4.5 | $0.00015 | $0.00313 |
Grade A, and why
pm-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 10d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Discovery Skill
How this skill behaves (read first)
This is a generative skill, and "do some discovery" hides several default traps. The instinctive moves are: treat discovery as a one-time research phase before building (then never revisit it), jump straight to solutions and features, run a generic "interview a few users + send a survey" plan without matching the rigor to what's actually at stake, measure success by what shipped rather than what changed, and ask users "would you use this?" (everyone says yes). The result is a feature factory that's busy but not learning. Good discovery is continuous, problem-first, outcome-oriented, and evidence-matched-to-risk. So this skill gates:
- Establish which risk you're de-risking and how much certainty the decision needs — value, usability, feasibility, or business-viability risk; a cheap reversible call needs far less evidence than an expensive irreversible bet.
- Apply the always-true core — continuous cadence, outcomes over output, problem before solution, past behavior over hypotheticals, evidence matched to risk, solutions from validated problems, ethical research.
- Surface the context-dependent decisions (problem vs. solution research, qual vs. quant, lightweight vs. deep, DIY vs. specialist, how much certainty before committing) with trade-offs.
Then it hands off to pm-assumption-rigor-audit, pm-okr-metric-validity-audit, and pm-prioritization-rigor-audit for validation. The actual test/experiment design for a specific assumption belongs to the generative pm-assumption-testing skill — discovery decides what to learn and how much it matters; assumption-testing designs the test.
Step 0 — Establish context before planning discovery
Ask if not known; state the assumption if proceeding without an answer:
- Which of the four risks is most uncertain? Value (will anyone want it?), usability (can they use it?), feasibility (can we build it?), business viability (does it fit the business?). Discovery exists to retire whichever risk is highest — name it before choosing activities.
- Are you in the problem space or the solution space? "Does anyone care about this problem?" is a different question, with different methods, from "does this solution work?" Don't skip to solution discovery before the problem is validated.
- How reversible and expensive is the decision this informs? This sets how much certainty to buy. Over-researching a one-way-door reversible tweak wastes the quarter; under-researching an irreversible, costly bet is how teams ship the wrong thing.
- Who's involved, and at what cadence? The product trio (PM + designer + engineer) plus cross-functional partners; is this a continuous habit or a one-off study? Default toward continuous.
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.
- 10d ago First seen · 106 lines · 147 tokens per session scan A 36702e477ff1
pm-discovery is a skill published in the GitHub repository Uxcel-Lab/product-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 147 tokens to every session and 3,126 once invoked, about $0.0007 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
pm-brainstorm
A guided brainstorming workflow for exploring a new product idea before detailed research or requirements work. It collects basic information about the product, users, and problem through staged questions.
pm-priority
A Chinese-language procedure for ranking several product requests when time or resources are limited. It supports scoring or grouping methods such as RICE, KANO, and MoSCoW to decide what should be done first.
start-super-pm
Use when starting any product management task - automatically detects task type and invokes appropriate PM skill using intelligent routing.
pm-change
A requirements-change workflow for recording a proposed change, assessing its effects, and deciding whether to approve it.
pm-risk
A structured process for identifying, rating, responding to, and monitoring project risks before important delivery points or launch.
pm-user-story
A workflow for turning product requirements into user stories: short statements of what a user wants and why, with acceptance criteria for checking the result.