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/interview)<a href="https://agentmods.dev/commands/phuryn/pm-skills/interview"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/interview/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/interview"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/interview.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 | $0.00013 | $0.01187 |
| Opus 5 | $0.00006 | $0.00593 |
| Sonnet 5 | $0.00003 | $0.00237 |
| Haiku 4.5 | $0.00001 | $0.00119 |
Grade A, and why
interview 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 7d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/interview -- Customer Interview Prep & Summary
Two modes: prep creates a structured interview script before you talk to customers, summarize extracts insights after you've done the interview.
Invocation
/interview prep Onboarding experience for enterprise users
/interview summarize [paste transcript or upload file]
/interview # asks which mode you need
Modes
Prep Mode
Create a structured interview script tailored to your research question.
Workflow
Step 1: Understand the Research Goal
Ask the user:
- What are you trying to learn? (specific research question)
- Who are you interviewing? (segment, role, relationship to product)
- How much time do you have? (15 min, 30 min, 60 min)
- What decisions will this research inform?
Step 2: Generate Interview Script
Apply the interview-script skill:
- Follow "The Mom Test" principles — ask about their life, not your idea
- No leading questions, no pitching, focus on past behavior and real situations
- Structure the script in sections:
## Interview Script: [Research Topic]
**Research Question**: [what we're trying to learn]
**Target Participant**: [who]
**Duration**: [X] minutes
### Warm-up (3-5 min)
[Rapport-building questions, role/context understanding]
### Core Exploration (15-40 min)
[JTBD probing, past behavior, current workflow, pain points]
- For each question: the question + why you're asking it + follow-up prompts
### Specific Topics (5-10 min)
[Targeted questions about specific features or concepts — if needed]
### Wrap-up (3-5 min)
[Open-ended closing, referral ask, next steps]
### Note-Taking Template
[Pre-formatted template to capture insights during the interview]
### Red Flags to Watch For
[Signs the conversation is going off-track or the participant is being polite rather than honest]
Step 3: Customize and Review
- Adjust question count to fit the time slot
- Add probing questions for specific hypotheses the user wants to test
- Flag questions that might lead the witness
- Offer a printable version (markdown file saved to workspace)
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.
- 7d ago First seen · 170 lines · 13 tokens per session scan A 977fe1c79179
interview is a command published in the GitHub repository phuryn/pm-skills (26,507 stars, last pushed 7d ago), licensed MIT. It adds 13 tokens to every session and 1,187 once invoked, about $0.0001 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 2026-09-15.
Other commands, from other repositories
experiment-ideas
Generate several concrete, brain-grounded growth ideas — channel, message, rationale, cost-efficiency — ranked by effort vs. impact.
value-prop-statements
Fan an existing positioning statement out into segment- and channel-specific value-prop copy variants, trace-checked against drift.
pmm-metrics
Define a North Star Metric and capped scorecard, or audit an existing metrics list for sprawl and vanity metrics.
alternatives-map
Build or deepen your competitive alternatives map — direct competitors, adjacent tools, DIY, and status quo — from real win/loss data.
gtm-motions
Score and select a GTM motion stack against real deal economics, not a taxonomy tour.
buyer-personas
Map the buying committee, then build alternatives-anchored messaging personas.