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 hoatv2211/GameStudio-CodexKIT --skill game-screenshot-showcase-and-store-packaginggit clone --depth 1 https://github.com/hoatv2211/GameStudio-CodexKITWrote 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/hoatv2211/gamestudio-codexkit/game-screenshot-showcase-and-store-packaging)<a href="https://agentmods.dev/skills/hoatv2211/gamestudio-codexkit/game-screenshot-showcase-and-store-packaging"><img src="https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/game-screenshot-showcase-and-store-packaging/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/hoatv2211/gamestudio-codexkit/game-screenshot-showcase-and-store-packaging"><img src="https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/game-screenshot-showcase-and-store-packaging.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 | $0.00044 | $0.01592 |
| Opus 5 | $0.00022 | $0.00796 |
| Sonnet 5 | $0.00009 | $0.00318 |
| Haiku 4.5 | $0.00004 | $0.00159 |
Grade A, and why
game-screenshot-showcase-and-store-packaging 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 11d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Screenshot Showcase and Store Packaging
Overview
Capture and package Unity screenshots through an approval-gated workflow: discover the target moments, propose the exact checklist, capture only after approval, review the images visually, and package approved outputs without overwriting raw evidence or taking storefront actions.
Provenance
This workflow is conceptually inspired by ParthJadhav/app-store-screenshots (MIT). No source text or code was copied into this skill.
When to use
Use for Unity PlayMode feature capture, showcase contact sheets, approved slide decks, and report-only screenshot packaging for Steam, mobile stores, or WebGL listings.
When NOT to use
Do not use for qualitative playtest synthesis without capture/package scope; route that work to playtest-evidence. Do not use to upload assets, sign binaries, accept legal terms, log into storefront accounts, or press submit; route publication readiness to store-submission-checklist. If the core question is runtime execution proof, Unity build proof, or a missing HUD/widget, route to build-and-runtime-verification, unity-batchmode-build-verification, or unity-ui-rendering-debugging.
Required inputs and context discovery
Collect the Unity project root, target scenes or entry points, feature beats to capture, viewport/device targets, locale, intended store/platform, approved evidence/output roots, privacy redaction rules, reviewer identity, and whether a Unity Editor or PlayMode runner is actually available.
Safety and risk level
This workflow may write new evidence files and report-only HTML/JSON outputs, but it must never overwrite raw captures, delete rejected evidence, traverse outside approved roots, consume credentials, or perform upload/signing/submission. Redact or exclude player names, email addresses, account IDs, chats, or other sensitive content that appears in screenshots.
Workflow
- Discover.
Completion criterion: the exact feature moments, scenes, capture roots, device targets, and no-touch paths are named, and adjacent concerns are routed to
playtest-evidence,build-and-runtime-verification,unity-batchmode-build-verification,unity-ui-rendering-debugging, orstore-submission-checklistwhen they are the real owner. - Propose the interactive checklist.
Completion criterion: an explicit
capture-planis prepared with ordered flows, viewport, locale, timeout, reviewer, and approval state, and no capture starts before human approval. - Capture only after approval.
Completion criterion: Unity Editor or PlayMode capture runs only after approval, raw files are preserved as immutable evidence, and each capture yields a
capture-recordwith hash, byte size, dimensions, build/editor snapshot, runtime result, visual review placeholder, and limitations. If Unity Editor, PlayMode, or the approved runtime path is unavailable, this phase isBLOCKED; do not substitute old screenshots, mocked renders, or compile confidence. - Visual review.
Completion criterion: approved and rejected captures remain traceable through
verify-captureresults and an HTML contact sheet, and runtime verdicts stay separate from visual verdicts. A visually strong image with weak runtime evidence is not a runtime PASS; a runtime PASS does not auto-approve composition, crops, or messaging. - Package.
Completion criterion: only approved showcase selections become a
showcase-deckandstore-export-manifest, store readiness stays separate from runtime and visual verdicts, and packaging remains report-only with no resizing, upload, signing, or submission.
What ships with it
7 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.
- 11d ago First seen · 112 lines · 44 tokens per session scan A e4d8f0c6c5b1
game-screenshot-showcase-and-store-packaging is a skill published in the GitHub repository hoatv2211/GameStudio-CodexKIT (3 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 1,592 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 2026-08-31.
Other skills, from other repositories
moai-domain-svg-infographic
Author editable SVG technical infographics — architecture, flow, comparison, hierarchy — by computing the layout numerically before writing markup, then rendering a 2x PNG via headless Chromium. Carries a CJK-first font stack, a deterministic source lint, and mermaid-vs-SVG selection rules.
threejs-world-generation
Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs. Use for cinematic 3D terrain, semantic regions, procedural biomes, explicit landmarks, environmental scattering, camera fly-throughs, world diagnostics, or requests for a real 3D environment rather than generated 2D footage.…
3d-asset-generation
Generate, reconstruct, inspect, and route production 3D assets for OpenMontage worlds using Atlas Cloud, fal.ai, licensed catalogs, and Blender.
sc-skill
Capture deterministic macOS screenshots for testing, docs, release notes, and marketing assets. Use when asked to automate app screenshots, batch-generate screenshot sets, standardize window sizing/composition, or choose between Peekaboo and native macOS screenshot tooling.
sound-effects
Generate sound effects from text descriptions using ElevenLabs. Use when creating sound effects, generating audio textures, producing ambient sounds, cinematic impacts, UI sounds, or any audio that isn't speech. Supports looping, duration control, and prompt influence tuning.
character-rigging
Build data-driven 2D character rigs for local animation: parts, pivots, layers, constraints, views, and reusable rig packages.