deep-structural-analysis-skill
Multi-lens structural analysis skill: adversarial-first analysis across 16 lenses in 4 categories with 10 structural tools, confidence calibration, and fact-bound layered output.
多视角深层结构分析技能:16 透镜 4 类别、10 个结构工具,先攻击默认立场,产出置信度校准、事实绑定的分层结论。
How to install
dsh plugin add github:tetckx/deep-structural-analysis-skill git clone https://github.com/tetckx/deep-structural-analysis-skill ~/.claude/skills/deep-structural-analysis-skill About
Deep Structural Analysis — 使用须知 **Read this in other languages:** :us: English 跨学科深度结构分析技能。当前版本 **v1.9.5** · 渐进式架构 · 16透镜4类别 · 10核心工具 · 立场切换发现引擎 + 攻击循环协议 + 推演四查 + 行为实验精简。 它是什么 对复杂社会/经济/哲学/系统性问题做多学科交叉分析:分解 → 研究(web search)→ 多透镜分析 → 结构工具 → 合成(交叉验证+置信度标注+分层输出)。所有结论事实绑定、置信度分级、盲点显式标注。 何时使用 | 触发 | 例子 | |------|------| | 用户要求深度分析 | "深度分析一下当下的就业形势" | | 多角度探索 | "从多个角度分析这个现象" | | 特定框架 | "用三向看这个问题" | | 结构性 why | "为什么劳动法执行这么难" | 不适用:事实解释("为什么天空是蓝色的")、调试、总结、信息查询——直接简短回答。 案例(实际输出形态) 对"为什么城市地铁普遍亏损却仍在持续扩建"的分析(示例 · 分析时间 2026-08-08)产出如下形态: 深度声明:Standard · 复杂度域 Complex 【暴露靶子】默认立场:"地铁持续亏损 = 应该停止扩建"(待攻击) 【核心发现】"亏损…
Recommendation signals
Meta
- License
- MIT
- Language
- –
- GitHub stars
- 1
- mo. downloads
- –
- Last push
- 2026-08-21
- Created
- 2026-07-21
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- adversarial-review, ai-skill, analysis-framework, claude-code-skill, claude-code-skills, claude-skills, deep-analysis, dsh-plugin, dsh-plugins, multi-lens, opencode-skill, opencode-skills, prompt-engineering, skill, skills, structural-analysis
Related plugins
superpowers
obra/superpowers
An agentic skills framework & software development methodology that works.
mcp-server-chart
antvis/mcp-server-chart
🤖 A visualization mcp & skills contains 25+ visual charts using @antvis. Using for chart generation and data analysis.
ruflo
ruvnet/claude-flow
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
caveman
JuliusBrussee/caveman
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman