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 julianoczkowski/product-manager --skill pm-market-problemsgit clone --depth 1 https://github.com/julianoczkowski/product-managerWrote 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/julianoczkowski/product-manager/pm-market-problems)<a href="https://agentmods.dev/skills/julianoczkowski/product-manager/pm-market-problems"><img src="https://agentmods.dev/badge/skills/julianoczkowski/product-manager/pm-market-problems/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/julianoczkowski/product-manager/pm-market-problems"><img src="https://agentmods.dev/badge/skills/julianoczkowski/product-manager/pm-market-problems.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 | $0.00118 | $0.01496 |
| Opus 5 | $0.00059 | $0.00748 |
| Sonnet 5 | $0.00024 | $0.00299 |
| Haiku 4.5 | $0.00012 | $0.00150 |
Grade A, and why
pm-market-problems 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 12d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Market Problems — discovery & validation (Framework: Market → Market Problems)
Rule: The answers to most of your questions are not in the building. Discover,
collect, analyze and communicate problems found in the market, then validate they are
urgent, pervasive, and that the market is willing to pay to solve them. See
../pm-copilot/references/framework.md for the full map.
Who to listen to
The Noisy 20% vs. the Quiet 80%. The noisy 20% (your most excited/unhappy customers plus loud internal voices — an exec's advisory board, a big-client sales rep, support) give a limited, skewed view. The quiet 80% won't come to you; you must go find them (industry conferences — leave your booth; professional associations; LinkedIn; end-user training). Noisy customers don't represent the whole market.
The four market segments — each is "a person with a problem." Balance interviews across all four:
| Segment | Lens they speak through | The question to ask |
|---|---|---|
| Customers (bought yours) | your product | "What other problems should we be solving for you that we aren't solving today?" |
| Competitors' Customers | the competitor's product | "What other problems should we solve that your current product isn't solving?" |
| Evaluators (shopping now) | win/loss — don't disrupt the sale | "Why did we win (or lose) your business?" |
| Potentials (not shopping) | no lens — best for innovation | "What problems are you facing, and why are you not looking for a solution?" |
NIHITO — Nothing Interesting Happens In The Office. Recommend ~10 market visits per product manager per quarter. It feels like cold calling, but you aren't selling — state what's in it for them and expect many "no"s.
Discovery techniques
Observation — take thorough notes, look for patterns, minimize interruptions; if something catches your eye, ask. Answer: What do customers do / how / why? What's done manually that could be automated? What's multi-step that could be streamlined? How do they interact with your product? When do they use other systems, search for info, or need help?
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.
- 12d ago First seen · 124 lines · 118 tokens per session scan A 348b65007947
pm-market-problems is a skill published in the GitHub repository julianoczkowski/product-manager (32 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 1,496 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
persona-create
This skill should be used when the user asks to "create a persona", "add a new persona", "set up a new agent role", "add a woterclip persona", or runs the /persona-create command. Interactively creates a new WoterClip persona with SOUL.md, TOOLS.md, and config.yaml.
persona-import
This skill should be used when the user asks to "import a paperclip agent", "convert paperclip to woterclip", "migrate from paperclip", "import persona from paperclip", or wants to convert existing Paperclip agent directories into WoterClip persona format.
falsify
Adversarial falsification of sigint research findings. Generates disconfirming queries, executes web-only adversarial search, assigns ordinal verdicts (falsified | weakened | survived | inconclusive), and applies remediation (quarantine, confidence downgrade, follow-up queue). Invocable standalone via /sigint:falsify…
regulatory-review
This skill should be used when the user asks to "analyze regulations", "regulatory landscape", "compliance requirements", "legal considerations", "regulatory risk", "industry regulations", "compliance analysis", "regulatory trends", or needs guidance on understanding regulatory environments, compliance requirements…
report-writing
This skill should be used when the user asks to "write a report", "executive summary", "research report format", "report structure", "present findings", "business writing", "analysis documentation", or needs guidance on structuring research outputs, executive communication, or professional report formatting.
tech-assessment
This skill should be used when the user asks to "assess technology", "technology evaluation", "tech stack analysis", "technical feasibility", "technology trends", "build vs buy", "technology roadmap", "architecture assessment", or needs guidance on evaluating technologies, technical due diligence, or technology…