phuryn/pm-skills is a marketplace of reusable skills, commands, and plugins that guide AI assistants through product-management work such as discovery, strategy, planning, metrics, launches, and growth. It is for product managers and teams using Claude Code, Cowork, or compatible assistants. The catalogue entries are the project's own workflows and extensions.
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.
git clone --depth 1 https://github.com/phuryn/pm-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/commands/phuryn/pm-skills/research-users)<a href="https://agentmods.dev/commands/phuryn/pm-skills/research-users"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/research-users/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/commands/phuryn/pm-skills/research-users"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/research-users.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 | $0.00019 | $0.00936 |
| Opus 5.5 | $0.00008 | $0.00374 |
| Sonnet 5.5 | $0.00004 | $0.00187 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
research-users 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 2mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- research-users — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/research-users -- User Research Synthesis
Turn raw research data into actionable user personas, behavioral segments, and customer journey maps. Accepts survey data, interview notes, feedback, analytics, or a product description for exploratory research.
Invocation
/research-users [upload survey results, interview notes, or feedback data]
/research-users B2B project management tool for agencies — help me understand our users
/research-users [paste user feedback or support ticket data]
Workflow
Step 1: Accept Research Inputs
Accept from any combination:
- Survey responses (CSV, spreadsheet, pasted)
- Interview notes or transcripts
- Support tickets or feature requests
- Product analytics / behavioral data
- NPS or satisfaction data
- Product description (for exploratory research without data)
Ask:
- What research do you have? What format?
- What do you want to understand? (who are our users, how do they differ, where's the friction)
- What decisions will this inform? (roadmap, positioning, pricing, onboarding)
Step 2: Build Personas
Apply the user-personas skill:
- Identify 3-4 distinct personas from the data
- For each persona: name, role, goals (JTBD), pains, gains, behavioral patterns
- Include unexpected insights — things that surprised you in the data
- Note persona prevalence (what % of your base each represents, if data allows)
Step 3: Segment Users
Apply the user-segmentation and market-segments skills:
- Create behavioral segments (not just demographics)
- For each segment: size, JTBD, product fit, willingness to pay, engagement level
- Identify the highest-value segment and the highest-growth segment
- Map segments to personas (how they overlap)
Step 4: Map the Customer Journey
Apply the customer-journey-map skill:
- Map the end-to-end journey: Awareness → Consideration → Onboarding → Active Use → Expansion → Advocacy
- For each stage: touchpoints, emotions, pain points, aha moments
- Identify the biggest drop-off points
- Highlight moments of delight worth amplifying
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.
- 2mo ago First seen · 122 lines · 19 tokens per session scan A 2de91d824085
research-users is a command published in the GitHub repository phuryn/pm-skills (27,745 stars, last pushed 9d ago), licensed MIT. It adds 19 tokens to every session and 936 once invoked, about $0.0001 per session on Opus 5.5. 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.
research-users compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| research-usersphuryn/pm-skills | Command | 28k | 9d ago | MIT | A | 19 | Claude Code |
| brief-meProductfculty-aipm/PM-Copilot-by-Product-Faculty | Command | 80 | 6mo ago | none | A | 0 | Claude Code |
| design-ai-featureProductfculty-aipm/PM-Copilot-by-Product-Faculty | Command | 80 | 6mo ago | none | A | 28 | Claude Code |
| competitive-intelProductfculty-aipm/PM-Copilot-by-Product-Faculty | Command | 80 | 6mo ago | none | A | 24 | Claude Code |
| discoverProductfculty-aipm/PM-Copilot-by-Product-Faculty | Command | 80 | 6mo ago | none | A | 32 | Claude Code |
| plan-launchProductfculty-aipm/PM-Copilot-by-Product-Faculty | Command | 80 | 6mo ago | none | A | 26 | Claude Code |
| retroProductfculty-aipm/PM-Copilot-by-Product-Faculty | Command | 80 | 6mo ago | none | A | 27 | Claude Code |