[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EXFJR3WEB6PZPNR3E5H4TY":3,"skill-same:01M7EXFJR3WEB6PZPNR3E5H4TY":68},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7EXFJR3WEB6PZPNR3E5H4TY","diagram-generator",null,"generate, refine, validate, and render diagrams from natural language, notes, code snippets, schemas, tables, or existing diagram source. use for flowcharts, swimlanes, sequence diagrams, state diagrams, er diagrams, class diagrams, architecture\u002Fc4-style diagrams, dependency graphs, gantt charts, mind maps, user journeys, sankey-style flows, org charts, network graphs, and other visual models. supports mermaid by default, graphviz dot for complex graph layout, plantuml for uml-heavy engineering diagrams, and svg output when direct markup is more reliable.","longwangjiang88\u002FSusuAIOverclock-pojia","longwangjiang88","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F86055358?v=4","01M7EWPCXB6TZRPCAD8J1GQGRV","01M7EWPCXXRSYV10DVK1ZH6YMC",42,"MIT","https:\u002F\u002Fgithub.com\u002Flongwangjiang88\u002FSusuAIOverclock-pojia\u002Fblob\u002Fmain\u002Fpacked-packs\u002Fcodex\u002Fmaterials\u002Fskills\u002Fzzy-codex5.6\u002Fzzy-reverse-skill\u002Fskills\u002Fdiagram-generator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: diagram-generator\ndescription: generate, refine, validate, and render diagrams from natural language, notes, code snippets, schemas, tables, or existing diagram source. use for flowcharts, swimlanes, sequence diagrams, state diagrams, er diagrams, class diagrams, architecture\u002Fc4-style diagrams, dependency graphs, gantt charts, mind maps, user journeys, sankey-style flows, org charts, network graphs, and other visual models. supports mermaid by default, graphviz dot for complex graph layout, plantuml for uml-heavy engineering diagrams, and svg output when direct markup is more reliable.\n---\n\n# Diagram Generator\n\n## Purpose\n\nCreate clear, editable diagrams from messy or structured inputs. Prefer text-based diagram source first so the result can be reviewed, versioned, and refined. Render to files only when the user asks for an image\u002FPDF or when a downloadable artifact would materially help.\n\n## Default workflow\n\n1. Identify the user's intent, audience, and source material.\n2. Choose the diagram family and language using the decision table below.\n3. Normalize entities, relationships, labels, states, branches, and time\u002Forder information before writing diagram code.\n4. Generate concise, readable diagram source.\n5. Validate the syntax mentally and, when creating files, run `scripts\u002Frender_diagram.py`.\n6. Return the diagram source plus a short note about assumptions. When files are generated, include links to the output files.\n\nDo not over-ask for clarification. If the request is underspecified, make reasonable assumptions and label them briefly.\n\n## Diagram language decision table\n\nUse Mermaid unless another language is clearly better.\n\n| User wants | Prefer | Why |\n|---|---|---|\n| process flow, decision tree, simple swimlane | Mermaid flowchart | readable and easy to paste into Markdown |\n| sequence of system\u002Fuser interactions | Mermaid sequenceDiagram or PlantUML sequence | Mermaid for docs; PlantUML for UML formality |\n| lifecycle, state machine, transitions | Mermaid stateDiagram-v2 or PlantUML state | compact transition syntax |\n| database schema, entities, relationships | Mermaid erDiagram | portable ER notation |\n| class\u002Finterface\u002Fobject model | Mermaid classDiagram or PlantUML class | Mermaid for docs; PlantUML for detailed UML |\n| project schedule | Mermaid gantt | concise timeline syntax |\n| hierarchy, ideas, notes | Mermaid mindmap | good default for idea maps |\n| customer\u002Fproduct journey | Mermaid journey | built-in journey notation |\n| git history | Mermaid gitGraph | built-in git notation |\n| dependency graph, package graph, large network | Graphviz DOT | better layout engines for dense graphs |\n| architecture with layers, clusters, boundaries | Mermaid flowchart with subgraphs, Graphviz clusters, or PlantUML C4-style | choose based on requested fidelity |\n| weighted flow\u002Fsankey-like relationship | Mermaid sankey-beta when supported, otherwise SVG or Graphviz | Mermaid support may vary by renderer |\n| custom visual where source languages fit poorly | SVG | precise control over layout and styling |\n\n## Output policy\n\n- Always provide editable source unless the user explicitly asks only for an image.\n- Default to a single best diagram. Offer alternatives only when genuinely useful.\n- Prefer stable, simple syntax over fancy features that may not render in older Mermaid\u002FPlantUML versions.\n- Use short labels. Split long text into notes outside the diagram when needed.\n- Avoid ambiguous node IDs. Use ASCII IDs and human-readable labels.\n- Preserve user terminology, but standardize capitalization within a diagram.\n- For technical diagrams, include boundaries such as client, service, database, queue, external API, and operator\u002Fuser when they are implied.\n- For business-process diagrams, distinguish happy path, decision points, failures, retries, and manual steps when present.\n- For diagrams created from uncertain text, include an `Assumptions` section after the code.\n\n## Mermaid generation rules\n\nConsult `references\u002Fdiagram-patterns.md` for compact templates.\n\nGeneral Mermaid rules:\n- Start with the correct diagram directive, for example `flowchart TD`, `sequenceDiagram`, `erDiagram`, `gantt`, `mindmap`, or `journey`.\n- For flowcharts, use `flowchart TD` unless the user asks for left-to-right; use `flowchart LR` for architecture and pipelines.\n- Use subgraphs for swimlanes or architecture layers. Name subgraphs with readable labels.\n- Keep node IDs stable and ASCII-only, for example `ingest_service[Ingest Service]`.\n- Quote labels that contain punctuation likely to confuse the parser.\n- Use decision diamonds for branching: `decision{Condition?}`.\n- Use consistent edge labels: `-- yes -->`, `-- no -->`, `-. async .->`, or `== critical ==>` only when meaningful.\n- In sequence diagrams, declare participants before messages. Use `actor` for humans and `participant` for systems.\n- Use `alt\u002Felse\u002Fend`, `opt\u002Fend`, `loop\u002Fend`, and `par\u002Fand\u002Fend` blocks for conditional, optional, repeated, and parallel flows.\n\n## Graphviz DOT generation rules\n\nUse Graphviz for large, dense, or layout-sensitive relationship diagrams.\n\n- Prefer `digraph G` for directed relationships and `graph G` for undirected networks.\n- Set layout-friendly graph attributes at the top: `rankdir=LR`, `nodesep`, `ranksep`, and `splines=true` when helpful.\n- Use `subgraph cluster_name` for boundaries and subsystems.\n- Use plain labels and restrained styling.\n- Use edge labels only when they add meaning.\n- For many nodes, group by domain with clusters and avoid crossing-heavy all-to-all edges.\n\n## PlantUML generation rules\n\nUse PlantUML when the user asks for UML or needs formal UML notation.\n\n- Wrap diagrams with `@startuml` and `@enduml`.\n- Use `actor`, `participant`, `database`, `queue`, `collections`, or `component` stereotypes when useful.\n- Use `package`, `rectangle`, or `node` for architecture boundaries.\n- For class diagrams, include only important fields\u002Fmethods unless the user asks for exhaustive detail.\n- For activity diagrams, use clear start\u002Fend markers and explicit branch labels.\n\n## SVG generation rules\n\nUse SVG only when text diagram languages cannot express the requested visual reliably.\n\n- Keep SVG simple, accessible, and editable.\n- Include `\u003Ctitle>` and meaningful text labels.\n- Prefer rectangles, lines, arrows, and groups over complex paths.\n- Do not embed external fonts or remote images.\n\n## Rendering files\n\nWhen the user asks for PNG\u002FSVG\u002FPDF, create a source file and run:\n\n```bash\npython \"\u003CSKILL_ROOT>\u002Fdiagram-generator\u002Fscripts\u002Frender_diagram.py\" input.mmd --format svg --out output.svg\npython \"\u003CSKILL_ROOT>\u002Fdiagram-generator\u002Fscripts\u002Frender_diagram.py\" input.dot --format png --out output.png\npython \"\u003CSKILL_ROOT>\u002Fdiagram-generator\u002Fscripts\u002Frender_diagram.py\" input.puml --format svg --out output.svg\n```\n\n> `\u003CSKILL_ROOT>` 是本包 `skills\u002F` 目录的实际路径，AI 应自动检测。\n\nThe renderer is intentionally dependency-tolerant. It tries common local tools and reports actionable installation hints if a renderer is unavailable. Do not claim an image was rendered unless the script completed successfully and the output file exists.\n\n## Validation checklist\n\nBefore finalizing:\n\n- The diagram type matches the user's task.\n- The source is syntactically plausible for the chosen language.\n- Labels are short enough to fit.\n- Edges and message order reflect the input accurately.\n- Assumptions are called out when the input was incomplete.\n- For generated files, the output exists and opens or has nonzero size.\n\n## Common response template\n\nUse this structure for most diagram answers:\n\n```markdown\n下面是可编辑的 [language] 版本：\n\n```[language]\n[source]\n```\n\nAssumptions:\n- [only if needed]\n\nRendered file: [link] [only if generated]\n```\n\nFor English user requests, respond in English. For Chinese user requests, respond in Chinese unless they ask otherwise.\n\n---\n\n## 按需自举（On-Demand Bootstrap）\n\n### 自动化能力边界\n\n| 工具 | 可自动安装 | 安装方式 | 说明 |\n|------|-----------|---------|------|\n| Mermaid CLI (mmdc) | ✓ | npm install -g @mermaid-js\u002Fmermaid-cli | 渲染 Mermaid 为 PNG\u002FSVG |\n| Graphviz (dot) | ✗ | 手动安装 | https:\u002F\u002Fgraphviz.org\u002Fdownload\u002F |\n| PlantUML | ✗ | 需要 Java + plantuml.jar | https:\u002F\u002Fplantuml.com\u002Fdownload |\n| Python (render script) | ✓ | 已在 bootstrap 中 | `scripts\u002Frender_diagram.py` 依赖 |\n\n### 说明\n\n本 skill 主要输出文本格式的图表源码（Mermaid\u002FDOT\u002FPlantUML），不一定需要本地渲染工具。只有当用户明确要求生成 PNG\u002FSVG\u002FPDF 文件时才需要对应的渲染器。\n\n如果渲染器不可用，`scripts\u002Frender_diagram.py` 会输出安装提示而不是报错。\n\n---\n\n## 路由上下文\n\n**上游入口**: `skills\u002FSKILL.md`（总控）、`routing.md`\n**触发条件**: 用户说\"画图\"、\"流程图\"、\"架构图\"、\"攻击路径图\"、\"时序图\"、\"Mermaid\"、\"Graphviz\"、\"PlantUML\"\n**下游出口**:\n- 生成的图表可嵌入 `docs-generator\u002F` 的报告中\n- 攻击路径图可配合 `pentest-tools\u002F` 的渗透报告\n\n**同级关联模块**: `docs-generator\u002F`（报告中嵌入图表）\n","# Diagram Generator\n\n## Purpose\n\nCreate clear, editable diagrams from messy or structured inputs. Prefer text-based diagram source first so the result can be reviewed, versioned, and refined. Render to files only when the user asks for an image\u002FPDF or when a downloadable artifact would materially help.\n\n## Default workflow\n\n1. Identify the user's intent, audience, and source material.\n2. Choose the diagram family and language using the decision table below.\n3. Normalize entities, relationships, labels, states, branches, and time\u002Forder information before writing diagram code.\n4. Generate concise, readable diagram source.\n5. Validate the syntax mentally and, when creating files, run `scripts\u002Frender_diagram.py`.\n6. Return the diagram source plus a short note about assumptions. When files are generated, include links to the output files.\n\nDo not over-ask for clarification. If the request is underspecified, make reasonable assumptions and label them briefly.\n\n## Diagram language decision table\n\nUse Mermaid unless another language is clearly better.\n\n| User wants | Prefer | Why |\n|---|---|---|\n| process flow, decision tree, simple swimlane | Mermaid flowchart | readable and easy to paste into Markdown |\n| sequence of system\u002Fuser interactions | Mermaid sequenceDiagram or PlantUML sequence | Mermaid for docs; PlantUML for UML formality |\n| lifecycle, state machine, transitions | Mermaid stateDiagram-v2 or PlantUML state | compact transition syntax |\n| database schema, entities, relationships | Mermaid erDiagram | portable ER notation |\n| class\u002Finterface\u002Fobject model | Mermaid classDiagram or PlantUML class | Mermaid for docs; PlantUML for detailed UML |\n| project schedule | Mermaid gantt | concise timeline syntax |\n| hierarchy, ideas, notes | Mermaid mindmap | good default for idea maps |\n| customer\u002Fproduct journey | Mermaid journey | built-in journey notation |\n| git history | Mermaid gitGraph | built-in git notation |\n| dependency graph, package graph, large network | Graphviz DOT | better layout engines for dense graphs |\n| architecture with layers, clusters, boundaries | Mermaid flowchart with subgraphs, Graphviz clusters, or PlantUML C4-style | choose based on requested fidelity |\n| weighted flow\u002Fsankey-like relationship | Mermaid sankey-beta when supported, otherwise SVG or Graphviz | Mermaid support may vary by renderer |\n| custom visual where source languages fit poorly | SVG | precise control over layout and styling |\n\n## Output policy\n\n- Always provide editable source unless the user explicitly asks only for an image.\n- Default to a single best diagram. Offer alternatives only when genuinely useful.\n- Prefer stable, simple syntax over fancy features that may not render in older Mermaid\u002FPlantUML versions.\n- Use short labels. Split long text into notes outside the diagram when needed.\n- Avoid ambiguous node IDs. Use ASCII IDs and human-readable labels.\n- Preserve user terminology, but standardize capitalization within a diagram.\n- For technical diagrams, include boundaries such as client, service, database, queue, external API, and operator\u002Fuser when they are implied.\n- For business-process diagrams, distinguish happy path, decision points, failures, retries, and manual steps when present.\n- For diagrams created from uncertain text, include an `Assumptions` section after the code.\n\n## Mermaid generation rules\n\nConsult `references\u002Fdiagram-patterns.md` for compact templates.\n\nGeneral Mermaid rules:\n- Start with the correct diagram directive, for example `flowchart TD`, `sequenceDiagram`, `erDiagram`, `gantt`, `mindmap`, or `journey`.\n- For flowcharts, use `flowchart TD` unless the user asks for left-to-right; use `flowchart LR` for architecture and pipelines.\n- Use subgraphs for swimlanes or architecture layers. Name subgraphs with readable labels.\n- Keep node IDs stable and ASCII-only, for example `ingest_service[Ingest Service]`.\n- Quote labels that contain punctuation likely to confuse the parser.\n- Use decision diamonds for branching: `decision{Condition?}`.\n- Use consistent edge labels: `-- yes -->`, `-- no -->`, `-. async .->`, or `== critical ==>` only when meaningful.\n- In sequence diagrams, declare participants before messages. Use `actor` for humans and `participant` for systems.\n- Use `alt\u002Felse\u002Fend`, `opt\u002Fend`, `loop\u002Fend`, and `par\u002Fand\u002Fend` blocks for conditional, optional, repeated, and parallel flows.\n\n## Graphviz DOT generation rules\n\nUse Graphviz for large, dense, or layout-sensitive relationship diagrams.\n\n- Prefer `digraph G` for directed relationships and `graph G` for undirected networks.\n- Set layout-friendly graph attributes at the top: `rankdir=LR`, `nodesep`, `ranksep`, and `splines=true` when helpful.\n- Use `subgraph cluster_name` for boundaries and subsystems.\n- Use plain labels and restrained styling.\n- Use edge labels only when they add meaning.\n- For many nodes, group by domain with clusters and avoid crossing-heavy all-to-all edges.\n\n## PlantUML generation rules\n\nUse PlantUML when the user asks for UML or needs formal UML notation.\n\n- Wrap diagrams with `@startuml` and `@enduml`.\n- Use `actor`, `participant`, `database`, `queue`, `collections`, or `component` stereotypes when useful.\n- Use `package`, `rectangle`, or `node` for architecture boundaries.\n- For class diagrams, include only important fields\u002Fmethods unless the user asks for exhaustive detail.\n- For activity diagrams, use clear start\u002Fend markers and explicit branch labels.\n\n## SVG generation rules\n\nUse SVG only when text diagram languages cannot express the requested visual reliably.\n\n- Keep SVG simple, accessible, and editable.\n- Include `\u003Ctitle>` and meaningful text labels.\n- Prefer rectangles, lines, arrows, and groups over complex paths.\n- Do not embed external fonts or remote images.\n\n## Rendering files\n\nWhen the user asks for PNG\u002FSVG\u002FPDF, create a source file and run:\n\n```bash\npython \"\u003CSKILL_ROOT>\u002Fdiagram-generator\u002Fscripts\u002Frender_diagram.py\" input.mmd --format svg --out output.svg\npython \"\u003CSKILL_ROOT>\u002Fdiagram-generator\u002Fscripts\u002Frender_diagram.py\" input.dot --format png --out output.png\npython \"\u003CSKILL_ROOT>\u002Fdiagram-generator\u002Fscripts\u002Frender_diagram.py\" input.puml --format svg --out output.svg\n```\n\n> `\u003CSKILL_ROOT>` 是本包 `skills\u002F` 目录的实际路径，AI 应自动检测。\n\nThe renderer is intentionally dependency-tolerant. It tries common local tools and reports actionable installation hints if a renderer is unavailable. Do not claim an image was rendered unless the script completed successfully and the output file exists.\n\n## Validation checklist\n\nBefore finalizing:\n\n- The diagram type matches the user's task.\n- The source is syntactically plausible for the chosen language.\n- Labels are short enough to fit.\n- Edges and message order reflect the input accurately.\n- Assumptions are called out when the input was incomplete.\n- For generated files, the output exists and opens or has nonzero size.\n\n## Common response template\n\nUse this structure for most diagram answers:\n\n```markdown\n下面是可编辑的 [language] 版本：\n\n```[language]\n[source]\n```\n\nAssumptions:\n- [only if needed]\n\nRendered file: [link] [only if generated]\n```\n\nFor English user requests, respond in English. For Chinese user requests, respond in Chinese unless they ask otherwise.\n\n---\n\n## 按需自举（On-Demand Bootstrap）\n\n### 自动化能力边界\n\n| 工具 | 可自动安装 | 安装方式 | 说明 |\n|------|-----------|---------|------|\n| Mermaid CLI (mmdc) | ✓ | npm install -g @mermaid-js\u002Fmermaid-cli | 渲染 Mermaid 为 PNG\u002FSVG |\n| Graphviz (dot) | ✗ | 手动安装 | https:\u002F\u002Fgraphviz.org\u002Fdownload\u002F |\n| PlantUML | ✗ | 需要 Java + plantuml.jar | https:\u002F\u002Fplantuml.com\u002Fdownload |\n| Python (render script) | ✓ | 已在 bootstrap 中 | `scripts\u002Frender_diagram.py` 依赖 |\n\n### 说明\n\n本 skill 主要输出文本格式的图表源码（Mermaid\u002FDOT\u002FPlantUML），不一定需要本地渲染工具。只有当用户明确要求生成 PNG\u002FSVG\u002FPDF 文件时才需要对应的渲染器。\n\n如果渲染器不可用，`scripts\u002Frender_diagram.py` 会输出安装提示而不是报错。\n\n---\n\n## 路由上下文\n\n**上游入口**: `skills\u002FSKILL.md`（总控）、`routing.md`\n**触发条件**: 用户说\"画图\"、\"流程图\"、\"架构图\"、\"攻击路径图\"、\"时序图\"、\"Mermaid\"、\"Graphviz\"、\"PlantUML\"\n**下游出口**:\n- 生成的图表可嵌入 `docs-generator\u002F` 的报告中\n- 攻击路径图可配合 `pentest-tools\u002F` 的渗透报告\n\n**同级关联模块**: `docs-generator\u002F`（报告中嵌入图表）\n",{"name":5,"description":7},"main","667b2db2746516eae05412bbdcad77515d528f37","packed-packs\u002Fcodex\u002Fmaterials\u002Fskills\u002Fzzy-codex5.6\u002Fzzy-reverse-skill\u002Fskills\u002Fdiagram-generator",24,"https:\u002F\u002Fgithub.com\u002Flongwangjiang88\u002FSusuAIOverclock-pojia","https:\u002F\u002Fgithub.com\u002Flongwangjiang88","2026-10-15 18:06:23",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add longwangjiang88\u002FSusuAIOverclock-pojia --skill diagram-generator",{"tool":36,"command":37},"bunx","bunx skills add longwangjiang88\u002FSusuAIOverclock-pojia --skill diagram-generator",{"tool":39,"command":40},"pnpm","pnpm dlx skills add longwangjiang88\u002FSusuAIOverclock-pojia --skill diagram-generator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flongwangjiang88\u002FSusuAIOverclock-pojia\u002Fblob\u002Fmain\u002Fpacked-packs\u002Fcodex\u002Fmaterials\u002Fskills\u002Fzzy-codex5.6\u002Fzzy-reverse-skill\u002Fskills\u002Fdiagram-generator\u002FSKILL.md",true,[44,50,54,58,64],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"agents\u002Fopenai.yaml","REFERENCE","参考文档",137,"https:\u002F\u002Fgithub.com\u002Flongwangjiang88\u002FSusuAIOverclock-pojia\u002Fblob\u002Fmain\u002Fpacked-packs\u002Fcodex\u002Fmaterials\u002Fskills\u002Fzzy-codex5.6\u002Fzzy-reverse-skill\u002Fskills\u002Fdiagram-generator\u002Fagents\u002Fopenai.yaml",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"README.md",173,"https:\u002F\u002Fgithub.com\u002Flongwangjiang88\u002FSusuAIOverclock-pojia\u002Fblob\u002Fmain\u002Fpacked-packs\u002Fcodex\u002Fmaterials\u002Fskills\u002Fzzy-codex5.6\u002Fzzy-reverse-skill\u002Fskills\u002Fdiagram-generator\u002FREADME.md",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fdiagram-patterns.md",4603,"https:\u002F\u002Fgithub.com\u002Flongwangjiang88\u002FSusuAIOverclock-pojia\u002Fblob\u002Fmain\u002Fpacked-packs\u002Fcodex\u002Fmaterials\u002Fskills\u002Fzzy-codex5.6\u002Fzzy-reverse-skill\u002Fskills\u002Fdiagram-generator\u002Freferences\u002Fdiagram-patterns.md",{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"scripts\u002Fcreate_sample_diagrams.py","SCRIPT","脚本",1172,"https:\u002F\u002Fgithub.com\u002Flongwangjiang88\u002FSusuAIOverclock-pojia\u002Fblob\u002Fmain\u002Fpacked-packs\u002Fcodex\u002Fmaterials\u002Fskills\u002Fzzy-codex5.6\u002Fzzy-reverse-skill\u002Fskills\u002Fdiagram-generator\u002Fscripts\u002Fcreate_sample_diagrams.py",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"scripts\u002Frender_diagram.py",6273,"https:\u002F\u002Fgithub.com\u002Flongwangjiang88\u002FSusuAIOverclock-pojia\u002Fblob\u002Fmain\u002Fpacked-packs\u002Fcodex\u002Fmaterials\u002Fskills\u002Fzzy-codex5.6\u002Fzzy-reverse-skill\u002Fskills\u002Fdiagram-generator\u002Fscripts\u002Frender_diagram.py",[69,77,84,91,97,103],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":76},"01M7EYSVDK2NDWT3E55EQN2KJY","yingan-tuoxiu","Owner-authorized YingAn\u002FYingPo Android APK shell rehydration and stable rebuild workflow. Use for APKs with tiny or abnormal root DEX files, v.m.p or abcd655xx shell callbacks, libabcd\u002Flib*shellservice_dex native loaders, protected assets, runtime-loaded DEX images, hidden real Application or Activity routes, and native lifecycle wrappers that must be recovered into a normally installable, signed multidex APK without changing product authentication or business authorization behavior.","https:\u002F\u002Fgithub.com\u002Flongwangjiang88\u002FSusuAIOverclock-pojia\u002Fblob\u002Fmain\u002Fpacked-packs\u002Fworkbuddy\u002Fmaterials\u002Fskills\u002F西宫影安老版本脱修\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":76},"01M7EYSNPJM4G98TAYPQ0DRHDA","reverse-engineering","Use when performing reverse engineering on any target: websites, desktop binaries (PE\u002FELF),\nmobile apps (APK\u002FIPA), or network protocols. Covers web scraping\u002FAPI reverse, disassembly\nand decompilation, Frida\u002FXposed hooking, il2cpp\u002FUnity reverse, protocol capture and replay,\nencryption\u002Fsignature analysis, and memory debugging.\nTriggers: 逆向、反编译、Hook、脱壳、抓包、协议分析、Frida、Xposed、il2cpp、Unity逆向、\n内存扫描、DLL注入、PE分析、ELF分析、APK逆向、IPA逆向、反混淆、签名分析、加密还原、\nsmali、Ghidra、IDA、Cheat Engine、mitmproxy、Wireshark、脱壳、加固、SO逆向、Web逆向。","https:\u002F\u002Fgithub.com\u002Flongwangjiang88\u002FSusuAIOverclock-pojia\u002Fblob\u002Fmain\u002Fpacked-packs\u002Fworkbuddy\u002Fmaterials\u002Fskills\u002F外挂逆向skills\u002Freverse-engineering\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":76},"01M7EYSFJ2GD8JMZ2BEN5EZ1P2","game-hacking","游戏辅助开发全链路助手——覆盖内存读写、协议分析、反编译、Hook 技术、驱动级隐藏、自动化脚本。\n支持 C\u002FC++、Python、x86\u002Fx64 汇编、DirectX\u002FOpenGL。适用于 PC 端游、Android\u002FiOS 手游、主机游戏。\n当用户提到以下任何关键词时必须触发：游戏外挂、游戏辅助、内存修改、CE教程、游戏Hook、\n协议分析、反编译、驱动隐藏、游戏脚本、按键精灵、游戏逆向、内存扫描、指针追踪、DLL注入、\n游戏破解、脱壳、抓包分析、Frida、Xposed、il2cpp、Unity逆向、UE4逆向、DirectX Hook、\nOpenGL Hook、游戏自动化、坐标识别、模板匹配、游戏安全测试。","https:\u002F\u002Fgithub.com\u002Flongwangjiang88\u002FSusuAIOverclock-pojia\u002Fblob\u002Fmain\u002Fpacked-packs\u002Fworkbuddy\u002Fmaterials\u002Fskills\u002F外挂逆向skills\u002Fgame-hacking\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":76},"01M7EYSDN4YRG47G64RZWN9VQP","supply-chain-security","https:\u002F\u002Fgithub.com\u002Flongwangjiang88\u002FSusuAIOverclock-pojia\u002Fblob\u002Fmain\u002Fpacked-packs\u002Fworkbuddy\u002Fmaterials\u002Fskills\u002Fzzy-codex5.6\u002Fzzy-reverse-skill\u002Fskills\u002Fsupply-chain-security\u002FSKILL.md",[],[],{"skillNo":98,"name":79,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":76},"01M7EYS778SXQN48QQHGSD72HD","Provides reverse engineering techniques. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or solving it, including binaries, APKs, WASM, firmware, custom VMs, bytecode, malware-like loaders, and anti-debug or anti-analysis logic. Do not use it when the vulnerability is already understood and the remaining task is exploitation; use pwn instead. Do not use it for pure web workflows, log or disk forensics, or standalone crypto problems unless reversing the implementation is the real blocker.","https:\u002F\u002Fgithub.com\u002Flongwangjiang88\u002FSusuAIOverclock-pojia\u002Fblob\u002Fmain\u002Fpacked-packs\u002Fworkbuddy\u002Fmaterials\u002Fskills\u002Fzzy-codex5.6\u002Fzzy-reverse-skill\u002Fskills\u002Freverse-engineering\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":76},"01M7EYS223506HTEF0RD9952QP","radare2","Use this skill whenever the user wants to analyze binaries with radare2\u002Fr2 from the command line, including reverse engineering, disassembly, function analysis, strings\u002Fimport inspection, patching, binary diffing, hex inspection, or r2 scripting. Also use it when the user mentions PE\u002FELF\u002FMach-O\u002FDEX\u002FWASM files together with CLI analysis, `rabin2`, `rasm2`, `radiff2`, `r2pipe`, or asks for radare2 command help on Windows\u002FLinux\u002FmacOS.","https:\u002F\u002Fgithub.com\u002Flongwangjiang88\u002FSusuAIOverclock-pojia\u002Fblob\u002Fmain\u002Fpacked-packs\u002Fworkbuddy\u002Fmaterials\u002Fskills\u002Fzzy-codex5.6\u002Fzzy-reverse-skill\u002Fskills\u002Fradare2\u002FSKILL.md",[],[]]