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.
npx agentmods add commands/phuryn/pm-skills/generate-datagit 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/generate-data)<a href="https://agentmods.dev/commands/phuryn/pm-skills/generate-data"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/generate-data.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00632 |
| Opus 5 | $0.00009 | $0.00316 |
| Sonnet 5 | $0.00003 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
generate-data 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 4d 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:
- generate-data — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/generate-data -- Test Data Generator
Create realistic dummy datasets for development, testing, demos, or prototyping. Outputs as ready-to-use files in your preferred format.
Invocation
/generate-data 1000 users with names, emails, plan tier, signup date, and activity score
/generate-data E-commerce orders dataset: products, customers, timestamps, amounts
/generate-data Sample data matching this schema: [paste table definition]
Workflow
Step 1: Define the Dataset
Understand:
- What entities? (users, orders, events, products, etc.)
- What columns? (with data types and constraints)
- How many rows?
- Any relationships between tables?
- Any specific distributions? (e.g., "80% should be on the free plan")
- Any realistic constraints? (emails should be unique, dates should be chronological)
Step 2: Generate the Data
Apply the dummy-dataset skill:
- Create a Python script that generates the dataset
- Use realistic-looking data (not random strings): proper names, valid email formats, real-seeming dates
- Respect constraints: unique IDs, foreign key relationships, chronological ordering
- Apply specified distributions
- Execute the script and produce the output file
Step 3: Deliver
Output in the requested format (or ask):
- CSV: Most common, works everywhere
- JSON: For API testing or frontend development
- SQL INSERT: For populating test databases
- Python script: For reproducible generation (user can tweak and re-run)
## Generated Dataset: [Description]
**Rows**: [count]
**Columns**: [list]
**Format**: [CSV / JSON / SQL / Python]
### Schema
| Column | Type | Constraints | Distribution |
|--------|------|-----------|-------------|
### Sample (first 5 rows)
[Preview of the data]
### Files
- [data file]
- [generator script, if applicable]
Save data file and generator script to the user's workspace.
Step 4: Offer Follow-ups
- "Want me to add more columns or increase the dataset size?"
- "Should I create related tables (e.g., orders for these users)?"
- "Want me to write test scenarios that use this data?"
- "Should I create SQL queries to analyze this dataset?"
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.
- 4d ago First seen · 83 lines · 17 tokens per session scan A 48c10a51b38f
generate-data is a command published in the GitHub repository phuryn/pm-skills (25,964 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 632 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 2026-08-30.
Other commands, from other repositories
buyer-personas
Map the buying committee, then build alternatives-anchored messaging personas.
ideal-customer-profile
Build, enrich, or audit your ICP — trigger events, buyer map, JTBD, disqualifiers.
positioning-messaging
Build or audit positioning statements, messaging, and related output.
gtm-motions
Score and select a GTM motion stack against real deal economics, not a taxonomy tour.
interview-summary
Summarize a customer interview transcript using JTBD analysis.
prioritize
Score and rank initiatives using a GTM-native prioritization framework.