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 agentmods add skills/vidyfoo/antigravity-skill-engine/scientific-debuggingnpx skills add VidyFoo/antigravity-skill-engine --skill scientific-debugginggit clone --depth 1 https://github.com/VidyFoo/antigravity-skill-engineWhat 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 | $0.00036 | $0.00615 |
| Opus 5 | $0.00018 | $0.00308 |
| Sonnet 5 | $0.00007 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
scientific-debugging 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 2d 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.
What it actually says
Scientific Debugger Skill (v2.0)
Role: 拒绝"猜测驱动开发"。像科学家一样思考，用实验数据定位根因。
核心协议 (The Protocol)
1. 观察 (Observe)
- 收集现场: 用户报告了什么？错误堆栈是什么？
- 环境确认: 本地服务器是否运行？
- 现象复现: 必须 使用
browser_subagent复现问题 (Visual Proof)。
2. 假设 (Hypothesize)
基于观察，提出 1-3 个可能的根因假设：
- H1: DOM 事件未冒泡 (Event)
- H2: 状态更新被闭包捕获 (State)
- H3: 样式层叠导致的遮挡 (CSS)
3. 实验 (Experiment)
设计最小化实验验证假设：
- Console Log: 在关键路径打点。
- Browser Interaction: 模拟用户行为序列。
- Code Inspection: 检查
view_code_item.
4. 修复与验证 (Fix & Verify)
- 最小化修复: 只改根因，不附带重构。
- 回归测试: 再次运行
browser_subagent确认修复且无副作用。
调试策略库
| 问题类型 | 推荐工具 | 重点检查 |
|---|---|---|
| UI 无响应/交互失效 | browser_subagent |
pointer-events, z-index, onClick vs onFocus |
| 状态不同步 | console.log + React DevTools |
Zustand Selectors, React Query Cache Key |
| 样式错乱 | browser_subagent (Screenshot) |
Tailwind Classes, CSS Variables |
| 网络错误 | Network Tab (via Browser) | CORS, 404/500, Payload Format |
资源索引
| 资源文件 | 用途 |
|---|---|
| browser-test-guide.md | 浏览器测试通过指南 |
| root-cause-patterns.md | 常见根因模式库 |
强制要求
- No Blind Fixes: 禁止在未复现问题前修改代码。
- Visual Evidence: 对于 UI Bug，必须看截图证明。
- Logs are Cheap: 大胆加日志，但修好后记得删。
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.
- 2d ago First seen · 62 lines · 36 tokens per session scan A 7b8d9c336754
scientific-debugging is a skill published in the GitHub repository VidyFoo/antigravity-skill-engine (12 stars, last pushed 7mo ago), licensed MIT. It adds 36 tokens to every session and 615 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
Skill Development
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
SRT Enhancer
This skill should be used when the user asks to "enhance srt subtitles", "optimize srt with original script", "fix srt typos from markdown", "compare srt with origin.md", "improve subtitle accuracy", "add spaces to srt", "優化 srt 逐字稿", "比對原稿修正字幕", or needs to refine SRT subtitle files by comparing them with an original…
SRT Social Summary
This skill should be used when the user asks to "generate social media summary from srt", "create platform-specific descriptions", "generate Facebook post from transcript", "create YouTube description from srt", "write Thread post from subtitles", "生成影片介紹", "根據逐字稿生成貼文", or needs to create engaging social media content…
SRT Card Annotator
This skill should be used when the user asks to "add reference cards to srt", "annotate srt with cards", "insert cards into subtitles", "generate srt with card annotations", "add 字卡 to srt", or needs to add contextual reference cards below subtitle text blocks in SRT files.
Audio to SRT Converter
This skill should be used when the user asks to "convert audio to srt", "generate subtitles from audio", "create srt from mp3/wav/m4a/flac", "transcribe audio to subtitles", or needs to generate SRT subtitle files from audio files (MP3, WAV, M4A, FLAC, etc.) with customizable character limits and timeline adjustments.
agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.