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 lightblink/cocos-creator-local-mcp --skill cocos-interaction-ux-directorgit clone --depth 1 https://github.com/lightblink/cocos-creator-local-mcpWrote 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/lightblink/cocos-creator-local-mcp/cocos-interaction-ux-director)<a href="https://agentmods.dev/skills/lightblink/cocos-creator-local-mcp/cocos-interaction-ux-director"><img src="https://agentmods.dev/badge/skills/lightblink/cocos-creator-local-mcp/cocos-interaction-ux-director/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/lightblink/cocos-creator-local-mcp/cocos-interaction-ux-director"><img src="https://agentmods.dev/badge/skills/lightblink/cocos-creator-local-mcp/cocos-interaction-ux-director.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 | $0.00075 | $0.01121 |
| Opus 5 | $0.00037 | $0.00561 |
| Sonnet 5 | $0.00015 | $0.00224 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
cocos-interaction-ux-director 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cocos Interaction UX Director
Overview
Use this skill to make Cocos mini-games feel understandable, responsive, and playable on mobile touch screens. The output should translate game intent into input rules, UI states, feedback layers, and implementation requirements.
This skill coordinates with game design, art direction, gameplay architecture, scene assembly, and playtest QA.
Core Workflow
- Map the player journey.
- Cover launch, first comprehension, first input, first reward, first failure, restart, and exit.
- Remove nonessential screens from the first local playable loop.
- Define controls.
- Specify gesture, target area, dead zone, drag/click behavior, hold behavior, and cancellation.
- Make keyboard controls optional developer conveniences, not the primary path.
- Design feedback layers.
- For each action, define tactile-equivalent visual feedback, sound, motion, score/UI update, and game-state consequence.
- Keep the fastest feedback local and immediate.
- Specify UI states.
- Define HUD, pause, result, revive, settings, loading, and tutorial states only when needed.
- State entry and exit conditions explicitly.
- Protect mobile readability.
- Declare the target viewport set, orientation, design resolution, fit policy, and safe-area assumptions before implementation handoff.
- Check thumb reach, button size, contrast, occlusion, information hierarchy, text length, and whether the primary playfield uses the intended share of the screen.
- Avoid tiny tap targets, unintentionally shrunken playfields, and control schemes that require precision the screen cannot support.
- Treat fixed desktop-pixel layouts without an adaptation model as a blocking UX issue for phone-first games.
- Create implementation handoff.
- List Cocos nodes, UI components, serialized properties, events, and animation/tween feedback needed.
UX Deliverables
For substantial tasks, return:
- Player journey: first 30 seconds and repeat session.
- Control spec: input zones, gestures, edge cases, and fallback.
- Mobile playfield spec: safe area, thumb zone, occlusion risks, target aspect ranges, and narrow-screen behavior.
- Touch parameters: drag bounds, dead zone in pixels or screen percentage, release/cancel behavior, hold behavior, and multi-touch policy.
- UI state map: state names, transitions, blocked inputs, visible elements.
- Fail/restart flow: number of actions, default focus, blocked inputs, and recovery timing.
- Feedback matrix: action, immediate cue, state change, delayed cue.
- Onboarding plan: what is taught by layout, motion, text, or first safe action.
- Implementation notes: required components, prefabs, audio cues, and animations.
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.
- 11d ago First seen · 96 lines · 75 tokens per session scan A 38686d1622e9
cocos-interaction-ux-director is a skill published in the GitHub repository lightblink/cocos-creator-local-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 1,121 once invoked, about $0.0004 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
cocos-asset-pipeline-director
Plan, generate, adapt, validate, and import Cocos Creator 3.x game assets through a configured Cocos Asset Forge-compatible MCP. Use whenever the user asks for Cocos assets, sprites, sprite sheets, tilesets, UI packs, effects, placeholders, audio, art bibles, Cocos-ready metadata, asset folders, bundle placement…
cocos-asset-review-director
Review generated or imported Cocos Creator game assets against game design, art direction, gameplay semantics, animation needs, technical quality, mobile readability, interaction feedback, audio fit, performance risk, and runtime import constraints. Use after asset generation or adaptation, before importing assets…
cocos-art-direction-director
Direct visual style, art bibles, asset consistency, prompt language, sprite readability, UI visual systems, animation style, and Cocos-ready asset QA for game art pipelines. Use before asset generation when Codex needs to define a coherent look, guide or critique generated assets, coordinate with cocosassetforge…
roblox-ui
Build production Roblox interfaces with ScreenGui/PlayerGui lifecycle, responsive UDim2 layouts, safe insets, reusable editable Instances, cross-device input and selection, restrained motion, cleanup, and multi-viewport verification. Use for Roblox HUDs, inventories, shops, settings, ability bars, ScrollingFrames…
game-ui-ux
Design and build game UI/UX — HUDs, menus, and overlays — that survive every screen: anchor- based responsive layout, resolution/aspect scaling and safe areas, keyboard/gamepad focus navigation, a screen/menu state stack, and event-driven (not polled) HUD updates. Engine- neutral patterns that pair with the detected…
ux-design
Guided, section-by-section UX spec authoring for a screen, flow, or HUD. Reads game concept, player journey, and relevant GDDs to provide context-aware design guidance. Produces ux-spec.md (per screen/flow) or hud-design.md using the studio templates.