[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-857":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":10,"languages":10,"totalLinesOfCode":10,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":13,"stars7d":15,"stars30d":16,"stars90d":14,"forks30d":14,"starsTrendScore":17,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":20,"hasPages":20,"topics":22,"createdAt":10,"pushedAt":10,"updatedAt":23,"readmeContent":24,"aiSummary":25,"trendingCount":14,"starSnapshotCount":14,"syncStatus":26,"lastSyncTime":27,"discoverSource":28},857,"how","poteto\u002Fhow","poteto","skill for explaining architecture","",null,696,38,1,0,6,19,3,55.67,"MIT License",false,"main",[],"2026-06-12 04:00:06","# How — a Cursor skill for explaining codebases\n\nA Cursor plugin that adds the `\u002Fhow` skill: ask how a subsystem, feature, or flow works, and the agent produces a clear architectural explanation at the level of a senior engineer onboarding onto a new area.\n\n## What it does\n\nTwo modes, picked automatically from your question:\n\n- **Explain** (default) — explore the codebase and produce a structured explanation with sections for Overview, Key Concepts, How It Works, Where Things Live, and Gotchas.\n- **Critique** — explain first, then spawn multiple independent critics across different models to surface architectural problems.\n\nFor complex questions that span multiple files or services, the skill decomposes the question into 2–4 parallel exploration angles and spawns explorer subagents that gather findings in parallel. A synthesis agent then reconciles their findings into a single coherent explanation. Simple questions skip the fan-out and run end-to-end in a single agent.\n\n## Example prompts\n\n- \"How does message virtualization work?\"\n- \"Walk me through what happens when a user sends a message\"\n- \"How is the auth service structured? Also critique the design.\"\n- \"How does the auth middleware check permissions?\"\n\n## Structure\n\n```text\nhow\u002F\n├── .cursor-plugin\u002F\n│   └── plugin.json\n└── skills\u002F\n    └── how\u002F\n        ├── SKILL.md\n        └── references\u002F\n            ├── explainer-prompt.md\n            ├── explorer-prompt.md\n            ├── critic-prompt.md\n            └── critique-rubric.md\n```\n\n`SKILL.md` contains the top-level routing logic (simple vs. complex, explain vs. critique). The `references\u002F` folder holds the prompt templates that the agent hands to each subagent, plus the critique rubric used during the critique pass.\n\n## License\n\nMIT\n","该项目是一个Cursor插件，旨在通过添加`\u002Fhow`技能来解释代码库中的子系统、功能或流程的工作原理。其核心功能包括两种模式：默认的“解释”模式会生成包含概览、关键概念、工作原理、位置分布和注意事项等部分的结构化说明；而“批评”模式则会在解释后进一步使用多个模型对架构问题进行独立评估。对于复杂的问题，该技能能够将其分解为2-4个并行探索角度，并通过合成代理将结果整合成一致的解释。适用于新加入项目的高级工程师快速理解项目架构，或是希望从多角度审视现有代码库以发现潜在问题的场景。",2,"2026-06-11 02:39:50","CREATED_QUERY"]