Inspector Scene Recovery

Inspector 试玩页 → Creator 场景复刻(P+S 编排)。S 侧用本仓库 cocos-inspector MCP 读快照/纹理;P 侧用 cocos-meta-mcp 在 Creator 建树与磁盘补丁。使用时机:复刻试玩场景、 scene-to-creator、PowerOfThor2/godeebxp 恢复、纹理 manifest 绑定。

49 stars 44 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add kurenai-studio/CososInspector --skill inspector-scene-recovery
Manual install
git clone --depth 1 https://github.com/kurenai-studio/CososInspector.git /tmp/CososInspector
mkdir -p ~/.claude/skills
cp -r /tmp/CososInspector/.cursor/skills/inspector-scene-recovery ~/.claude/skills/inspector-scene-recovery

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Inspector → Creator 场景复刻(本仓库 Skill)

## 角色分工(P + S)

| 侧 | 工具 / Skill | 职责 |
|----|----------------|------|
| **S(读取)** | 本仓库 `cocos-inspector` MCP + 扩展 | 试玩页快照、Sprite 纹理、诊断日志 |
| **P(写入)** | `cocosmcp` + Skill **`cocos-meta-mcp-scene`** | Creator 建树、`save-scene`、磁盘补丁约束 |
| **编排** | 本 Skill + `docs/features/scene-recovery.md` | 端到端命令、参数、验收 |

上游 **`cocos-meta-mcp-scene`** 工作流 D 只写 P 侧;S 侧快照与纹理**必须读本 Skill**。

相关上游 Skill(个人目录 `~/.cursor/skills/`,连接前应先读):

- `cocos-meta-mcp-scene` — 建场景、避免 dirty 弹窗、批量补丁约束
- `creator-scene-editing` — eval 操作场景,禁止手改 `.scene`
- `cocos-meta-mcp-recipes` — `cocosmcp` 注册表与 preview/console recipe
- `creator-preview-refresh` — TS 改完强制进预览验收

## 前置

1. `npm run build` + Chrome 重载扩展(标题应显示 `v2.x`)
2. 终端常驻:`npm run cocos-bridge -- --domain <host> --page-url-match <url片段>`
3. Cursor MCP:`cocos-inspector`(本仓库 `tools/mcp-cocos-inspector/index.mjs`)
4. Creator 打开目标工程,`cocos-meta-mcp` 扩展启用;MCP `cocosmcp` 的 `cwd` 指向工程根
5. 试玩页 F5,Inspector MCP 绿点;`cocos_inspector_list_bridges` 确认 `extensionConnected`

多实例路由见 `docs/features/inspector-mcp-multi-instance.md`(优先 `wsPort` / `domain`)。

## S 侧:导出快照与纹理

```text
cocos_export_scene_snapshot → tmp/<game>-scene-snapshot.json
cocos_list_sprites(或缓存 --live-sprites JSON)
cocos_download_texture / scene-to-creator --with-textures
```

**nodeId 漂移**:快照 ID 与试玩页 live ID 常不一致;`scene-to-creator` 按 **path** 匹配 live
sprite 再 `downloadTexture`,manifest 仍 keyed 快照 id。可 `--live-sprites` 跳过慢速
`listSprites`。
Read the full skill on GitHub

Details

Skill name
inspector-scene-recovery
Path
.cursor/skills/inspector-scene-recovery/SKILL.md
Repo updated
20 August 2026

FAQ

What does the Inspector Scene Recovery skill do?

Inspector 试玩页 → Creator 场景复刻(P+S 编排)。S 侧用本仓库 cocos-inspector MCP 读快照/纹理;P 侧用 cocos-meta-mcp 在 Creator 建树与磁盘补丁。使用时机:复刻试玩场景、 scene-to-creator、PowerOfThor2/godeebxp 恢复、纹理 manifest 绑定。

How do I install the Inspector Scene Recovery skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add kurenai-studio/CososInspector --skill inspector-scene-recovery. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Inspector Scene Recovery popular?

It lives in kurenai-studio/CososInspector, which has 49 GitHub stars and 44 forks.

Related skills

Agent Browser

223

NeverSight/learn-skills.dev

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

AI, LLMs & Agents42

Website Finishing Director

150

guia-matthieu/clawfu-skills

Run a structured 5-pass finishing audit on any website before launch — scoring visual polish, technical foundation, UX completeness, content quality, and cross-device readiness on 100 points. Use when: **Pre-launch** - Final validation before going live; **Post-redesign** - Verify nothing broke during the overhaul; **Client handoff** - Structured proof that the site is ready; **Quarterly review** - Catch accumulated debt; **Single-pass focus** - Run just Pass 2 after a perf sprint

AI, LLMs & AgentsIn 1 list32

Agent Skill Builder

223

NeverSight/learn-skills.dev

Load when the user wants to create, update, or refactor an agent skill, improve skill routing, split overlong skill instructions, or turn a repeated agent workflow into a reusable skill. Hand off to skill-creator for eval runs, packaging, and trigger-description optimization.

AI, LLMs & Agents42

Web Search Tavily

191

jwynia/agent-skills

Search the web using Tavily API for high-quality, AI-optimized results with advanced filtering options. Use when you need structured search results, domain filtering, relevance scores, or AI-generated answer summaries. Requires TAVILY_API_KEY. Keywords: tavily, advanced search, filtered search, domain filtering, relevance scoring.

AI, LLMs & Agents24

Agent Tools

223

NeverSight/learn-skills.dev

Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

AI, LLMs & Agents42

Theory of Constraints

228

pproenca/dot-skills

Apply the Theory of Constraints (Goldratt's Five Focusing Steps) to find and fix the single bottleneck that caps a process, workflow, pipeline, or Agent Skill/plugin's throughput. Use whenever optimizing speed, lead time, cost, or token/context budget of a system — CI/build pipelines, dev value streams (idea→review→merge→ship), an Agent Skill's trigger/context flow, or runtime code paths — ESPECIALLY when you don't know where to optimize, a local speedup didn't improve the whole, work piles up at a stage, everything is busy but little ships, adding capacity didn't help, or a policy/rule (not a

AI, LLMs & Agents19

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.