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/discover)<a href="https://agentmods.dev/commands/phuryn/pm-skills/discover"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/discover/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/discover"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/discover.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 | $0.00016 | $0.01087 |
| Opus 5 | $0.00008 | $0.00544 |
| Sonnet 5 | $0.00003 | $0.00217 |
| Haiku 4.5 | $0.00002 | $0.00109 |
Grade A, and why
discover 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/discover -- Full Discovery Cycle
Run a structured product discovery process that moves from divergent thinking to focused validation. This command chains multiple skills into a single end-to-end workflow.
Invocation
/discover Smart notification system for our project management tool
/discover New product: AI writing assistant for non-native speakers
/discover # asks what you're discovering
Workflow
Step 1: Understand the Discovery Context
Determine whether this is:
- Existing product — continuous discovery on a known product with real users
- New product — initial discovery for a concept without validated demand
Ask the user:
- What are you exploring? (product idea, feature area, opportunity space)
- What do you already know? (prior research, customer feedback, data)
- What decisions will this discovery inform? (build/kill, prioritize, pivot)
Accept context from uploaded files (research, PRDs, transcripts, data), links, or conversation.
Step 2: Brainstorm Ideas (Divergent Phase)
Apply the brainstorm-ideas-existing or brainstorm-ideas-new skill:
- Generate ideas from PM, Designer, and Engineer perspectives
- Present the top 10 ideas with brief rationale
- Ask the user to select 3-5 ideas to carry forward, or accept all
Checkpoint: "Here are 10 ideas. Which ones should we stress-test? Pick 3-5, or I can carry all forward."
Step 3: Identify Assumptions (Critical Thinking Phase)
For each selected idea, apply the identify-assumptions-existing or identify-assumptions-new skill:
- Surface assumptions across risk categories:
- Value: Will users want this?
- Usability: Can users figure it out?
- Feasibility: Can we build it?
- Viability: Does the business case work?
- Go-to-Market (new products only): Can we reach and convert users?
- Use devil's advocate multi-perspective analysis
- Compile a master list of all assumptions across all ideas
Step 4: Prioritize Assumptions (Focus Phase)
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 · 132 lines · 16 tokens per session scan A d5173f02b61c
discover is a command published in the GitHub repository phuryn/pm-skills (26,507 stars, last pushed 7d ago), licensed MIT. It adds 16 tokens to every session and 1,087 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
retro
Facilitate a post-launch or sprint retrospective anchored to OKRs.
discover
Run a full discovery cycle — problem framing, JTBD demand-side analysis, assumption mapping, opportunity sizing, and OST mapping — from a rough idea to validated opportunity.
plan-sprint
Plan the upcoming sprint — epic breakdown, user story decomposition, RICE prioritization, dependency check, and capacity allocation.
roadmap
Build or review your roadmap — OKR alignment, Now/Next/Later structuring, dependency mapping, and stakeholder views, pulling live Linear/Jira state.
set-okrs
Structure OKRs — define objectives, write measurable key results, align to strategy, stress-test for quality, and cascade across teams.
stakeholder-update
Generate tailored stakeholder updates by audience — pulls live tracker state from Linear/Jira, formats by audience (exec / engineering / customer) using Pyramid Principle.