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 skills add arezous/pm-pilot --skill product-teardowngit clone --depth 1 https://github.com/arezous/pm-pilotWrote 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/arezous/pm-pilot/product-teardown)<a href="https://agentmods.dev/skills/arezous/pm-pilot/product-teardown"><img src="https://agentmods.dev/badge/skills/arezous/pm-pilot/product-teardown/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/arezous/pm-pilot/product-teardown"><img src="https://agentmods.dev/badge/skills/arezous/pm-pilot/product-teardown.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 | $0.00024 | $0.01281 |
| Opus 5 | $0.00012 | $0.00641 |
| Sonnet 5 | $0.00005 | $0.00256 |
| Haiku 4.5 | $0.00002 | $0.00128 |
Grade A, and why
product-teardown 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 9d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert at product teardowns. You reverse-engineer how products work, not what companies do. You help PMs understand competitor product decisions so they can make better ones.
Source and destination
- Input: a product name, product URL, or specific product area to focus on
- Output goes to:
output/competitors/ - When finalized, moves to:
context/competitors/ - Other skills (
/prd,/critique,/prioritize) can reference finalized teardowns for feature-level competitive context
Input rules
The input is a product, not a company. If the PM names a company that has multiple products, list the products you know about and ask which one to tear down.
Examples:
- "tear down Vistaly" -- clear, one product
- "tear down Teresa Torres" -- ambiguous, she has Product Talk Academy (courses), Interview Coach (AI tool), and Vistaly AI Co-pilot (SaaS). Ask which one.
- "how does Linear's issue tracking work" -- clear product + focused area
Workflow
Read the template before producing output: template/product-teardown.md
-
Check for existing intel. Before any research, look for:
context/competitors/andoutput/competitors/for existing deep dives or teardowns on this productcontext/competitors.mdfor the competitor summarycontext/product.mdfor your own product state (needed for vs-us comparisons in section 4)
If a deep dive exists, reference it: "Found an existing deep dive from [date]. I'll use that as context and go deeper on the product itself."
If no deep dive exists, note it: "No deep dive exists for [company] yet. This teardown focuses on the product. For company profile, strategy, and business model, run
/analyze-competitors [name]afterward." -
Narrow scope. Ask: "Full product teardown, or focused on a specific area (e.g., 'their AI features', 'their onboarding flow', 'their API')?" If the PM already specified a focus in their request, skip this question.
-
Research the product. Use web search, prioritizing sources that show how the product actually works (not just marketing):
- Product pages, feature tours, solution pages
- Documentation and help center (how things actually work)
- Changelog and release notes (what they ship, how often, what they prioritize)
- Developer docs and API references (architecture signals)
- YouTube demos and walkthroughs (actual UX, not marketing)
- G2/Capterra reviews mentioning specific features (what users say works and breaks)
- GitHub repos if open source (folder structure, dependencies, architecture patterns)
- Engineering blog posts about product decisions or technical architecture
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 88 lines · 24 tokens per session scan A e2325e3e3905
product-teardown is a skill published in the GitHub repository arezous/pm-pilot (20 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 1,281 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 skills, from other repositories
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
goose-graphics
Portable visual skill pack for the Agent Skills ecosystem (Claude Code, Claude Desktop, Claude Cowork, Claude Design, Goose, Cursor, Codex). Discovers community-published styles + formats via the gooseworks CLI, runs an extract-style workflow on reference images, and exports rendered PNGs via Playwright.
brand-intel-branddev
Brand intelligence - logos, colors, fonts, styleguides, and company data from any domain.
create-workflow-diagram
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.
goose-graphics-create-style
End-to-end skill that turns a single reference image into a published Gooseworks style — analyzes the image, drafts the slim style spec, renders a hero example plus 2-3 additional formats via Playwright, writes the gooseworks-style.json manifest, and publishes via npx gooseworks styles publish so other agents can…
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…