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-playtest-qa-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-playtest-qa-director)<a href="https://agentmods.dev/skills/lightblink/cocos-creator-local-mcp/cocos-playtest-qa-director"><img src="https://agentmods.dev/badge/skills/lightblink/cocos-creator-local-mcp/cocos-playtest-qa-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-playtest-qa-director"><img src="https://agentmods.dev/badge/skills/lightblink/cocos-creator-local-mcp/cocos-playtest-qa-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 | $0.00083 | $0.01440 |
| Opus 5 | $0.00042 | $0.00720 |
| Sonnet 5 | $0.00017 | $0.00288 |
| Haiku 4.5 | $0.00008 | $0.00144 |
Grade A, and why
cocos-playtest-qa-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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cocos Playtest QA Director
Overview
Use this skill to convert "it builds" into evidence that a Cocos mini-game works for players. The output should define what to test, how to observe it, what evidence proves success, and what defects block progress.
This skill coordinates with Cocos local build, scene assembly, gameplay architecture, game design, interaction UX, balance, and art direction.
Core Workflow
- Define the verification target.
- Identify whether the task is smoke test, design playtest, balance pass, UX pass, regression, local WeChat build, or release-candidate check.
- Create test scenarios.
- Cover launch, first action, scoring/reward, fail, win, pause, restart, scene reload, and any platform-specific path.
- For random systems, include fixed-seed reproducibility scenarios and enough repeated runs to reveal obvious distribution, streak, fairness, or unwinnable-content issues.
- Gather evidence.
- Prefer command output, build logs, screenshots, runtime logs, Cocos editor bridge summaries, WeChat DevTools logs, and reproduced steps.
- For phone-first games, capture or inspect at least one target-runtime viewport screenshot and check playfield scale, HUD readability, control size, safe-area placement, and cropping/letterboxing before calling the slice playable.
- For from-zero playable slices, record whether first-loop visuals, UI, SFX, and music are generated/imported, deliberately placeholder-only, or missing. Do not let geometry-only visuals pass as production-ready without an explicit waiver.
- For generated assets, include asset-review evidence for role fit, orientation, alpha/silhouette quality, mobile readability, collision fit, and whether required sequence animations are present.
- For random gameplay, collect seed, config, sample count, observed distribution, notable streaks, and reproduction steps for any random failure.
- Triage findings.
- Classify blockers, high-risk bugs, design issues, polish issues, and deferred risks.
- Separate player-facing defects from developer cleanup.
- Decide next action.
- Recommend fix, retest, cut scope, tune numbers, revise UX, regenerate assets, or accept risk.
- Record acceptance.
- State exactly which gates passed, failed, or were not run.
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 · 104 lines · 83 tokens per session scan A 71b6679af729
cocos-playtest-qa-director is a skill published in the GitHub repository lightblink/cocos-creator-local-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 1,440 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…
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
tests-run
Execute Unity tests (EditMode or PlayMode) and return per-test results. Supports filtering by test assembly, namespace, class, and method. Refreshes the AssetDatabase first; defers execution across domain reloads if scripts changed. Precondition: every open scene must be saved — dirty scenes abort the run.
unity-agent-workflows
Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first…