Borrowing it
Nothing to install: this file belongs to bonnguyenitc/antigravity-superpowers. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bonnguyenitc/antigravity-superpowers/main/.agent/skills/product-manager/SKILL.mdgit clone --depth 1 https://github.com/bonnguyenitc/antigravity-superpowersWrote 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/bonnguyenitc/antigravity-superpowers/product-manager)<a href="https://agentmods.dev/skills/bonnguyenitc/antigravity-superpowers/product-manager"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/antigravity-superpowers/product-manager/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/bonnguyenitc/antigravity-superpowers/product-manager"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/antigravity-superpowers/product-manager.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 | $0.00031 | $0.00920 |
| Opus 5.5 | $0.00012 | $0.00368 |
| Sonnet 5.5 | $0.00006 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
product-manager 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 1mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Manager Lens
Philosophy: Build outcomes, not outputs. Ship learning, not just features. The best feature is often the one you decide not to build.
⚠️ ASK BEFORE ASSUMING
| What | Why it matters |
|---|---|
| Stage? Pre-PMF / Post-PMF / Scaling | Changes everything about what to build |
| Who is the user? | Can't prioritize without knowing whose problem |
| What outcome matters? Revenue / retention / activation | Determines what "done" looks like |
| Existing data? | Don't hypothesize what you can measure |
Core Instincts
- Jobs-to-be-done (JTBD) — users don't want features; they want to make progress in their lives
- Outcome over output — "MAU +20%" beats "shipped 10 features"
- Pareto ruthlessness — 20% of features deliver 80% of value; cut the rest
- Small bets, fast learning — ship to learn, not to finish
- Pre-PMF: talk to users; post-PMF: read the data
Prioritization Frameworks
| Framework | When to use |
|---|---|
| ICE (Impact × Confidence × Ease) | Quick scoring across many ideas |
| RICE (Reach × Impact × Confidence ÷ Effort) | When reach varies significantly |
| MoSCoW (Must/Should/Could/Won't) | Scoping a release |
| Opportunity Scoring | When you have survey data on importance vs satisfaction |
Indie hacker rule: If a feature doesn't directly help activation, retention, or revenue — it's probably a "Won't" for now.
❌ Anti-Patterns to Avoid
| ❌ NEVER DO | Why | ✅ DO INSTEAD |
|---|---|---|
| Build based on one user request | 1 user ≠ your market | Find the pattern across 5+ interviews |
| Big bang launch | Months of work, one chance to be right | Shape → Bet → Ship → Learn loop |
| Vanity metrics as goals | Page views don't pay rent | Retention, activation, revenue |
| Feature factory (output focus) | Team ships but nothing improves | Set outcome targets, measure impact |
| Build before validating | Wasted dev weeks | Fake door test, landing page, prototype first |
| Roadmap spans > 3 months | World changes faster than plans | 6-week cycles max for indie hackers |
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.
- 1mo ago First seen · 106 lines · 31 tokens per session scan A e6e1e0ea2ff3
product-manager is a skill published in the GitHub repository bonnguyenitc/antigravity-superpowers (20 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 920 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.
Other skills, from other repositories
file-a-task
File work into nohuman (taskadd) and check on it (taskstatus) via the nohuman MCP bridge, instead of doing the work inline.
iot-ai-tasks
Natural-language task lifecycle and authoritative backend routing with validation, WIP control, evidence, audit and Founder handoff.
iot-ai-status
Explain current tasks, active waves, meetings, providers, tests, audits, checkpoints and next actors in one management view.
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
starting-a-new-project
Use when the workspace is empty, has no code, and the user brings a raw project idea. Normally reached via setting-up-a-project; not for an existing project.
agy-lead
Orchestrate an ongoing task with AGY while the current agent owns key decisions, review, and delivery. Use when the user invokes /agy-lead or asks you to coordinate a task using AGY.