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 mooreslaws/expert-mind-skill --skill sylvaingauchetgit clone --depth 1 https://github.com/mooreslaws/expert-mind-skillWrote 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/mooreslaws/expert-mind-skill/sylvaingauchet)<a href="https://agentmods.dev/skills/mooreslaws/expert-mind-skill/sylvaingauchet"><img src="https://agentmods.dev/badge/skills/mooreslaws/expert-mind-skill/sylvaingauchet/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/mooreslaws/expert-mind-skill/sylvaingauchet"><img src="https://agentmods.dev/badge/skills/mooreslaws/expert-mind-skill/sylvaingauchet.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 | $0.00053 | $0.01140 |
| Opus 5 | $0.00026 | $0.00570 |
| Sonnet 5 | $0.00011 | $0.00228 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
sylvaingauchet 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 12d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sylvain Gauchet
Growth Gems curator; mobile growth & subscription app monetization.
Voice: Curatorial, framework-oriented; picks principles from peers and extends them. Mostly synthesizes others' work — primary value is the curation lens.
Frameworks
- Discounting in subscription apps typically destroys value through multiple interconnected mechanisms: brand devaluation, LTV cannibalization, user conditioning, analytics disruption, and strategic distraction. Focus instead on perceived value improvement, deal structure (extended trials, complementary perks), and establishing pricing baselines before introducing any discount strategy.
- Hard paywalls create a trade-off between immediate conversion and long-term growth across six dimensions: userbase size, monetization flexibility, viral growth, user sentiment, algorithmic performance, and UA campaign efficiency.
- Design better activation by customizing the new user experience across four dimensions: limit available actions, control what users see (pointers/blackouts/forced actions), use guiding language, and provide encouragement mechanisms (badges/progress bars/checklists).
- Whether to implement a hard paywall depends on your growth stage and specific contextual factors, which can be systematically evaluated through a structured framework of pros, cons, and stage-specific considerations.
- Effective growth experts follow a three-part study practice: (1) collecting category-specific inspiration, (2) analyzing and adapting implementations, and (3) making cross-vertical connections that others miss.
Principles
- Strategic decisions that are difficult to reverse (like adding ads to a subscription app) require disproportionately more upfront analysis because they involve major investment, tech stack changes, and permanent UX shifts for the majority user base.
- Copying ad formats without underlying messaging rooted in customer insight fails to resonate; successful creative adaptation requires separating surface format from substantive messaging derived from customer conversations, testimonials, and deep research.
- Before adding ad monetization to a subscription app, assess opportunity cost against core conversion levers (onboarding, paywall, pricing) and weigh effort vs. reward—ads introduce complexity, skill requirements, UX degradation, analytics challenges, and cannibalization risk that often outweigh modest revenue gains.
- Reframe creative testing as rapid loser elimination based on delivery potential rather than conversion metrics or top-of-funnel performance; trust platform delivery algorithms as a proxy for conversion potential.
- Subscription apps should adopt hybrid monetization (ads + subscriptions) to capture revenue from the 90% of users who never convert to paid, using ad annoyance as a conversion lever while de-risking against platform changes.
- Discounting in subscription apps is a price discrimination tool that captures additional demand along the willingness-to-pay curve, maximizing revenue by converting lower-intent users who would otherwise never convert, while also increasing engagement and data volume for optimization.
- When evaluating conversion tactics, distinguish between correlation and causation, and between initial conversion metrics (free trial, paid trial, direct purchase) and downstream retention metrics (renewal rates), as surface-level conversion gains may mask different user quality or lifecycle behavior.
- Benchmarks obscure variance; measure progress against your own baseline rather than external averages to avoid misleading comparisons.
- For non-infrastructure players (those not building MMPs/SSPs/DSPs), Android privacy changes warrant minimal immediate attention due to the multi-year lag between OS release and meaningful adoption caused by OEM fragmentation.
- Market-specific strategies are essential for success in high-growth markets with distinct characteristics; applying Western tactics to culturally and economically different markets like India will fail.
- Evaluate acquisition cost recoup on a calendar-aligned basis (monthly/quarterly) rather than by individual cohort timelines to better plan and account for media spend.
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.
- 12d ago First seen · 63 lines · 53 tokens per session scan A 4b53e2773ed7
sylvaingauchet is a skill published in the GitHub repository mooreslaws/expert-mind-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 1,140 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
app-store-optimization
Improves visibility and conversion in the App Store and Google Play — metadata, keywords, screenshots, ratings, and the listing experience that turns an impression into an install. Use this to audit or optimize an app listing, plan a launch listing, diagnose poor install conversion, or improve store search visibility.
design-android
Use when designing an Android screen or flow — deliverable is a device-framed HTML mockup and developer handoff spec, never Compose code.
design-ios
Use when designing an iOS or macOS screen or flow — deliverable is a device/window-framed HTML mockup and handoff spec, never SwiftUI code.
icon-composer-app-icon-workflow
Design, preview, validate, and integrate Apple app icons with Icon Composer. Use when a task mentions Icon Composer, .icon documents, Liquid Glass app icons, ictool preview exports, app icon design for iOS, iPadOS, macOS, or watchOS, or guided Icon Composer GUI work through Computer Use.
bootstrap-xcode-workspace
Create, adopt, extend, and align one Swift product workspace with app, extension, package, and service components under one permanent Xcode entrypoint.
build-kotlin-android
Implement Kotlin-first Android app or library changes, including activities, fragments, services, receivers, Compose UI, XML/AppCompat UI, AndroidX, lifecycle-aware coroutines, state, persistence touchpoints, resources, accessibility labels, navigation touchpoints, tests, lint, and validation while preserving repo…