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 evanca/flutter-ai-rules --skill store-listing-assetsgit clone --depth 1 https://github.com/evanca/flutter-ai-rulesWrote 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/evanca/flutter-ai-rules/store-listing-assets)<a href="https://agentmods.dev/skills/evanca/flutter-ai-rules/store-listing-assets"><img src="https://agentmods.dev/badge/skills/evanca/flutter-ai-rules/store-listing-assets/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/evanca/flutter-ai-rules/store-listing-assets"><img src="https://agentmods.dev/badge/skills/evanca/flutter-ai-rules/store-listing-assets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.01293 |
| Opus 5 | $0.00018 | $0.00647 |
| Sonnet 5 | $0.00007 | $0.00259 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
store-listing-assets 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Store Listing Assets & Copy
Prepare the metadata, copy, and visual assets that go into an App Store / Google Play phone listing, sized and length-fit to each store's exact requirements. This is the listing production skill; pair it with a separate review-readiness audit at submission time so the fields are polished and the app itself is ready for review.
Two references hold the authoritative specs; consult them for exact numbers rather than reciting from memory (they drift):
references/mobile_listing_checklist.md— the actionable checklist (shared prep → per-store required → recommended → final check)references/spec_reference.md— the full spec tables, minimal valid examples, store-specific traps, and known gaps to verify live
Default scope is phone-only. Skip tablet, iPad, desktop, Chromebook, TV, watch, Mac, and visionOS assets unless the user says the app supports them — and if they do, note that those are separate asset families outside these specs.
How to use this skill
- Gather the inputs once (shared prep): final app name, what the app does in one sentence, primary category, whether it has ads, whether it collects/shares/tracks data, privacy policy URL, support contact, and launch languages. These feed both stores.
- Confirm which store(s) the user is targeting — the required set differs enough that doing both blindly wastes effort.
- Produce copy AND/OR assets per the requests below, always checking generated text against the live character/byte limits and generated images against the exact pixel/format specs.
Writing store copy (fit to limits)
Character limits are hard constraints — always count and show the count. Key limits (full set in the references):
| Field | Google Play | Apple |
|---|---|---|
| App name | 30 chars | 2–30 chars |
| Subtitle | — (no field) | 30 chars |
| Short description | 80 chars | — (use Promotional Text, 170) |
| Full description | 4,000 chars | 4,000 chars, plain text |
| Keywords | — (no field; don't keyword-stuff the description) | ≤100 bytes, each keyword >2 chars |
What ships with it
2 files 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 · 66 lines · 37 tokens per session scan A 851cf0be50d1
store-listing-assets is a skill published in the GitHub repository evanca/flutter-ai-rules (635 stars, last pushed 9d ago), licensed MIT. It adds 37 tokens to every session and 1,293 once invoked, about $0.0002 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
excalidraw-architect
Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more - using the excalidraw-architect-mcp server. Use whenever a reader would learn more from a picture than from prose, or when…
dart-expert
Expert-level Dart, Flutter, mobile development, and cross-platform apps. Use when the user mentions Flutter, mobile, cross platform, or widgets, or when the task involves Dart Language or Flutter Framework.
dart-sdk-changelog
Expert guide and lookup reference for the Dart SDK CHANGELOG, version history, experimental features, macros, and augmentations from Dart 1.x to modern Dart 3.x. Use this skill whenever the user asks "what's new in Dart X", "what's new in 3.13", "what's new in 3.12", asks how to find the minimum SDK version (minSdk)…
flutter-sdk-changelog
Expert guide and lookup reference for Flutter framework versions, widget deprecations, API replacements, Material 3 migrations, and the unbundling of standalone materialui and cupertinoui packages from Flutter 1.0 to modern Flutter (3.44+ / 3.47+). Use this skill whenever the user asks "what's new in Flutter X"…
enhance-web-ui
Polish an existing page's hierarchy, spacing, type, and visual personality. Use when "make this page polished/premium", "less crowded", or "better visual hierarchy". Understood / CPL → enhance-readability. Flow/IA → enhance-web-ux. Breakpoints → audit-responsive.
enhance-web-ux
NN/g-grounded enhancement of an existing page's flows — not a repo-wide slop audit. Use when "fix UX of /xxx" or "improve information density". Repo-wide authenticity plan → plan-antislop. Composition/type → enhance-web-ui. Dense prose / CPL / reading level → enhance-readability. Heuristics-only → audit-ux.