[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79B4RVK49G8QG1V6PR3JEB0":3,"skill-same:01M79B4RVK49G8QG1V6PR3JEB0":60},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M79B4RVK49G8QG1V6PR3JEB0","governance-doc-design",null,"Use when authoring governance, rule, or design docs.","yhyu13\u002FAgentSkillsVault","yhyu13","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F19365678?v=4","01M79A3XCF5M26GEWS60XQQRWW","俞航","01M79A3XD7YZ779GGWS41K367S",3,"MIT","https:\u002F\u002Fgithub.com\u002Fyhyu13\u002FAgentSkillsVault\u002Fblob\u002Fmain\u002FSKILL\u002Fsoftware-development\u002Ftier3\u002Fgovernance-doc-design\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: governance-doc-design\ndescription: Use when authoring governance, rule, or design docs.\nversion: 1.0.0\nauthor: Hermes Agent\nlicense: MIT\nmetadata:\n  hermes:\n    tags: [docs, governance, rules, design-system, conventions]\n    related_skills: [hermes-agent-skill-authoring, technical-design-document]\n---\n\n# Governance Doc Design\n\nA disciplined structure for project governance docs — product rules, design\nrules, dev rules, and legal\u002Fcompliance. Derived from the Cindy client repo's\n`docs\u002F` conventions (\u003Ccindy-repo>\u002Fdocs), which is the reference\nimplementation; the pattern is reusable for any repo that wants rules an agent\ncan actually follow.\n\n## When to Use\n\n- Authoring a NEW product\u002Fdesign\u002Fdev\u002Flegal rule doc, or a design spec \u002F decision\n  log \u002F index for a repo.\n- Updating an existing rule doc and needing to know which bucket it belongs in\n  and how to keep it self-consistent.\n- Setting up (or auditing) a `docs\u002F` tree so that rules are discoverable,\n  traceable to code, and checkable by tests rather than only by reading.\n\n## Core principles\n\n1. **Separate intent from implementation.** Product rules say \"what the user\n   should get \u002F what behavior must not break\"; design rules say \"how it looks \u002F\n   interacts\"; dev rules say \"how code implements and verifies it\". Never mix\n   them in one file — each bucket has its own 收录标准 (inclusion criteria).\n2. **Status is explicit and binding.** Every doc is either `authoritative`\n   (约束力, agents must follow) or `参考` (background\u002Fspike, non-binding). A\n   doc that doesn't state its status is ambiguous — that's a defect.\n3. **A rule must say WHEN to read it, not just what it says.** Every rule doc\n   opens with a `读取时机` (when-to-read) line so an agent knows when it applies.\n4. **Every rule states trigger \u002F must-do \u002F must-not \u002F verify \u002F exception.** The\n   dev-rules 收录标准 is the canonical shape of a single rule.\n5. **Trace to code, not prose.** Rules cite a 事实来源 (source-of-truth) table —\n   the authoritative file path (e.g. `colors.ts`, `layoutTree.ts`) that the rule\n   governs. \"grep the source\" beats \"trust the doc\".\n6. **Rules should be enforced by tests\u002Flint, not just by reading.** If a rule\n   can be frozen as a test invariant, do it and cite the test file. A rule only\n   an agent reads will drift.\n7. **Decisions are append-only.** Overturned decisions are never deleted — they\n   are marked 作废\u002F推翻\u002F修正 and kept so the trail is legible.\n\n## The four buckets\n\n| bucket | governs | 收录标准 (a doc belongs here when…) |\n|---|---|---|\n| `product-rules\u002F` | product behavior, UX, cross-end consistency | \"what the user should get \u002F what must not break\" |\n| `design-rules\u002F` | visual, interaction, content design | \"how it looks \u002F interacts \u002F reads\" |\n| `dev-rules\u002F` | engineering constraints, implementation, verification | \"how code implements \u002F verifies, what tech ops are forbidden\" |\n| `legal\u002F` | compliance, licenses, SBOM | legal\u002Fcompliance artifacts |\n\nLocalized rules for a single directory\u002Fmodule go in that directory's nested\n`AGENTS.md`; only cross-cutting or long-explanation rules go in `docs\u002F`.\n\n## Per-doc skeleton\n\nA well-formed rule\u002Fdesign doc follows this shape (Cindy's concrete example in\nparentheses):\n\n1. **Title + status blockquote** — the first lines are a blockquote:\n   `> 状态：权威\u002F参考`, `> 适用范围：…`, `> 读取时机：…之前`. This is the routing\n   signal; put it first, before any content.\n2. **事实来源 table** — `| 内容 | 权威来源 |` listing the code file(s) that are\n   the real source of truth.\n3. **Numbered sections (§1, §2, …)** — stable IDs. Section numbers are frozen\n   identifiers; renumbering breaks cross-references, so never renumber casually.\n   If a section is absorbed\u002Fmoved, leave a `§N 编号留占位` note.\n4. **Review 清单** — a checklist an agent\u002Freviewer runs against the diff.\n5. **验证方法** — the test\u002Ftypecheck command that must pass for changes touching\n   this rule.\n\nExample (dev-rule):\n```\n# 架构不变量\n> **状态**：权威开发规则（authoritative）\n> **读取时机**：新增或修改 package 依赖方向、main 加载方式、布局树结构之前\n\n## 事实来源\n| 内容 | 权威来源 |\n| 布局树结构定义 | apps\u002Fdesktop\u002Fsrc\u002Fshared\u002FlayoutTree.ts |\n\n## 1. package 解耦\n## 2. main 进程静态依赖\n## Review 清单\n## 验证方法\n```\n\n## Index and version ledger\n\n- **Top index (`docs\u002FREADME.md`)** — a table: `| 文档 | 类型 | 状态 | 治理\u002F相关代码 | owner |`.\n  Every doc registers here; a doc absent from the index is undiscoverable.\n- **Per-bucket index (`\u003Cbucket>\u002FREADME.md`)** — lists 收录标准 + current docs.\n- **Version ledger (design index)** — dated entries, newest first, each:\n  `- YYYY-MM-DD（主题）: what changed → where it landed (DESIGN.md §N + token\u002Ftest)`.\n  The ledger records change *history*; the spec file holds only current rules.\n\n## Append-only decision log\n\nSeparate the \"current truth\" from \"how we got here\":\n\n- The spec (e.g. `DESIGN.md`) holds **only currently-valid rules**.\n- The decision log (e.g. `design-decision-log.md`) holds **history** — each entry:\n  **date \u002F 决策 \u002F 背景与被取代方案 \u002F 现行落点** (which section + token\u002Ftest froze it).\n- It is **只增不改** (append-only, never rewrite history). Overturned decisions are\n  marked with explicit verbs: **推翻** (overthrown), **修正** (corrected), **作废但保留**\n  (voided but kept for trail). Never silently delete a past decision.\n- **Conflict rule**: when the spec and the decision log disagree, the spec wins.\n  State this explicitly in the log's header.\n\n## Errata discipline\n\nWhen a documented value turns out wrong:\n- Mark the stale text `~~struck through~~` with a date + reason + the replacement.\n- Do not silently edit history — leave the erratum visible.\n- Point to the frozen test\u002Fconstant that now locks the correct value.\n\n## Authoring workflow\n\n1. Determine the bucket (product \u002F design \u002F dev \u002F legal) — ask \"what does this\n   constrain: user outcome, appearance, or implementation?\".\n2. Check the bucket's 收录标准 — if it doesn't fit, put it in the right bucket or\n   in a nested `AGENTS.md`, not here.\n3. Write the doc with the skeleton above (status blockquote → 事实来源 → §sections\n   → Review 清单 → 验证方法).\n4. Register it in the top index + bucket index (type + status + owner).\n5. If it can be enforced mechanically, add the test\u002Flint and cite it in 验证方法.\n6. For a decision that changes\u002Foverthrows a prior one, append to the decision log\n   (date + 决策 + 背景 + 现行落点), never rewrite the spec silently.\n\n## Pitfalls\n\n- Mixing product intent with code detail in one doc (the top sin — buckets exist\n  to prevent it).\n- Omitting 状态\u002F读取时机 — the doc becomes a wall of text no agent knows when to read.\n- Renumbering §sections — breaks every cross-reference; freeze IDs, leave placeholders.\n- Rewriting a decision log entry instead of appending a 推翻\u002F修正 entry.\n- A rule that only lives in prose with no test — it will drift; freeze invariants.\n- Citing a value without its source file — \"trust the doc\" instead of \"grep the source\".\n\n## Verification\n\n- New doc appears in the top index AND its bucket index with a 状态 + owner.\n- Every rule has trigger \u002F must-do \u002F must-not \u002F verify \u002F exception (or an explicit\n  reason it doesn't need one).\n- 事实来源 table cites real file paths that actually exist (grep-checked).\n- Enforceable rules are backed by a test, and the test file is cited.\n","# Governance Doc Design\n\nA disciplined structure for project governance docs — product rules, design\nrules, dev rules, and legal\u002Fcompliance. Derived from the Cindy client repo's\n`docs\u002F` conventions (\u003Ccindy-repo>\u002Fdocs), which is the reference\nimplementation; the pattern is reusable for any repo that wants rules an agent\ncan actually follow.\n\n## When to Use\n\n- Authoring a NEW product\u002Fdesign\u002Fdev\u002Flegal rule doc, or a design spec \u002F decision\n  log \u002F index for a repo.\n- Updating an existing rule doc and needing to know which bucket it belongs in\n  and how to keep it self-consistent.\n- Setting up (or auditing) a `docs\u002F` tree so that rules are discoverable,\n  traceable to code, and checkable by tests rather than only by reading.\n\n## Core principles\n\n1. **Separate intent from implementation.** Product rules say \"what the user\n   should get \u002F what behavior must not break\"; design rules say \"how it looks \u002F\n   interacts\"; dev rules say \"how code implements and verifies it\". Never mix\n   them in one file — each bucket has its own 收录标准 (inclusion criteria).\n2. **Status is explicit and binding.** Every doc is either `authoritative`\n   (约束力, agents must follow) or `参考` (background\u002Fspike, non-binding). A\n   doc that doesn't state its status is ambiguous — that's a defect.\n3. **A rule must say WHEN to read it, not just what it says.** Every rule doc\n   opens with a `读取时机` (when-to-read) line so an agent knows when it applies.\n4. **Every rule states trigger \u002F must-do \u002F must-not \u002F verify \u002F exception.** The\n   dev-rules 收录标准 is the canonical shape of a single rule.\n5. **Trace to code, not prose.** Rules cite a 事实来源 (source-of-truth) table —\n   the authoritative file path (e.g. `colors.ts`, `layoutTree.ts`) that the rule\n   governs. \"grep the source\" beats \"trust the doc\".\n6. **Rules should be enforced by tests\u002Flint, not just by reading.** If a rule\n   can be frozen as a test invariant, do it and cite the test file. A rule only\n   an agent reads will drift.\n7. **Decisions are append-only.** Overturned decisions are never deleted — they\n   are marked 作废\u002F推翻\u002F修正 and kept so the trail is legible.\n\n## The four buckets\n\n| bucket | governs | 收录标准 (a doc belongs here when…) |\n|---|---|---|\n| `product-rules\u002F` | product behavior, UX, cross-end consistency | \"what the user should get \u002F what must not break\" |\n| `design-rules\u002F` | visual, interaction, content design | \"how it looks \u002F interacts \u002F reads\" |\n| `dev-rules\u002F` | engineering constraints, implementation, verification | \"how code implements \u002F verifies, what tech ops are forbidden\" |\n| `legal\u002F` | compliance, licenses, SBOM | legal\u002Fcompliance artifacts |\n\nLocalized rules for a single directory\u002Fmodule go in that directory's nested\n`AGENTS.md`; only cross-cutting or long-explanation rules go in `docs\u002F`.\n\n## Per-doc skeleton\n\nA well-formed rule\u002Fdesign doc follows this shape (Cindy's concrete example in\nparentheses):\n\n1. **Title + status blockquote** — the first lines are a blockquote:\n   `> 状态：权威\u002F参考`, `> 适用范围：…`, `> 读取时机：…之前`. This is the routing\n   signal; put it first, before any content.\n2. **事实来源 table** — `| 内容 | 权威来源 |` listing the code file(s) that are\n   the real source of truth.\n3. **Numbered sections (§1, §2, …)** — stable IDs. Section numbers are frozen\n   identifiers; renumbering breaks cross-references, so never renumber casually.\n   If a section is absorbed\u002Fmoved, leave a `§N 编号留占位` note.\n4. **Review 清单** — a checklist an agent\u002Freviewer runs against the diff.\n5. **验证方法** — the test\u002Ftypecheck command that must pass for changes touching\n   this rule.\n\nExample (dev-rule):\n```\n# 架构不变量\n> **状态**：权威开发规则（authoritative）\n> **读取时机**：新增或修改 package 依赖方向、main 加载方式、布局树结构之前\n\n## 事实来源\n| 内容 | 权威来源 |\n| 布局树结构定义 | apps\u002Fdesktop\u002Fsrc\u002Fshared\u002FlayoutTree.ts |\n\n## 1. package 解耦\n## 2. main 进程静态依赖\n## Review 清单\n## 验证方法\n```\n\n## Index and version ledger\n\n- **Top index (`docs\u002FREADME.md`)** — a table: `| 文档 | 类型 | 状态 | 治理\u002F相关代码 | owner |`.\n  Every doc registers here; a doc absent from the index is undiscoverable.\n- **Per-bucket index (`\u003Cbucket>\u002FREADME.md`)** — lists 收录标准 + current docs.\n- **Version ledger (design index)** — dated entries, newest first, each:\n  `- YYYY-MM-DD（主题）: what changed → where it landed (DESIGN.md §N + token\u002Ftest)`.\n  The ledger records change *history*; the spec file holds only current rules.\n\n## Append-only decision log\n\nSeparate the \"current truth\" from \"how we got here\":\n\n- The spec (e.g. `DESIGN.md`) holds **only currently-valid rules**.\n- The decision log (e.g. `design-decision-log.md`) holds **history** — each entry:\n  **date \u002F 决策 \u002F 背景与被取代方案 \u002F 现行落点** (which section + token\u002Ftest froze it).\n- It is **只增不改** (append-only, never rewrite history). Overturned decisions are\n  marked with explicit verbs: **推翻** (overthrown), **修正** (corrected), **作废但保留**\n  (voided but kept for trail). Never silently delete a past decision.\n- **Conflict rule**: when the spec and the decision log disagree, the spec wins.\n  State this explicitly in the log's header.\n\n## Errata discipline\n\nWhen a documented value turns out wrong:\n- Mark the stale text `~~struck through~~` with a date + reason + the replacement.\n- Do not silently edit history — leave the erratum visible.\n- Point to the frozen test\u002Fconstant that now locks the correct value.\n\n## Authoring workflow\n\n1. Determine the bucket (product \u002F design \u002F dev \u002F legal) — ask \"what does this\n   constrain: user outcome, appearance, or implementation?\".\n2. Check the bucket's 收录标准 — if it doesn't fit, put it in the right bucket or\n   in a nested `AGENTS.md`, not here.\n3. Write the doc with the skeleton above (status blockquote → 事实来源 → §sections\n   → Review 清单 → 验证方法).\n4. Register it in the top index + bucket index (type + status + owner).\n5. If it can be enforced mechanically, add the test\u002Flint and cite it in 验证方法.\n6. For a decision that changes\u002Foverthrows a prior one, append to the decision log\n   (date + 决策 + 背景 + 现行落点), never rewrite the spec silently.\n\n## Pitfalls\n\n- Mixing product intent with code detail in one doc (the top sin — buckets exist\n  to prevent it).\n- Omitting 状态\u002F读取时机 — the doc becomes a wall of text no agent knows when to read.\n- Renumbering §sections — breaks every cross-reference; freeze IDs, leave placeholders.\n- Rewriting a decision log entry instead of appending a 推翻\u002F修正 entry.\n- A rule that only lives in prose with no test — it will drift; freeze invariants.\n- Citing a value without its source file — \"trust the doc\" instead of \"grep the source\".\n\n## Verification\n\n- New doc appears in the top index AND its bucket index with a 状态 + owner.\n- Every rule has trigger \u002F must-do \u002F must-not \u002F verify \u002F exception (or an explicit\n  reason it doesn't need one).\n- 事实来源 table cites real file paths that actually exist (grep-checked).\n- Enforceable rules are backed by a test, and the test file is cited.\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"description":7},"Hermes Agent","1.0.0",{"hermes":27},{"tags":28,"related_skills":34},[29,30,31,32,33],"docs","governance","rules","design-system","conventions",[35,36],"hermes-agent-skill-authoring","technical-design-document","main","3b63fa056f5de7956766fca020e9c71fdf2b0fab","SKILL\u002Fsoftware-development\u002Ftier3\u002Fgovernance-doc-design",0,"https:\u002F\u002Fgithub.com\u002Fyhyu13\u002FAgentSkillsVault","https:\u002F\u002Fgithub.com\u002Fyhyu13","https:\u002F\u002Fyhyu13.github.io","大丈夫自立于天地之间，岂可郁郁久居于人下\r\nA zealot of AI.","2026-11-14 20:53:07",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add yhyu13\u002FAgentSkillsVault --skill governance-doc-design",{"tool":52,"command":53},"bunx","bunx skills add yhyu13\u002FAgentSkillsVault --skill governance-doc-design",{"tool":55,"command":56},"pnpm","pnpm dlx skills add yhyu13\u002FAgentSkillsVault --skill governance-doc-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fyhyu13\u002FAgentSkillsVault\u002Fblob\u002Fmain\u002FSKILL\u002Fsoftware-development\u002Ftier3\u002Fgovernance-doc-design\u002FSKILL.md",true,[],[61,68,75,82,89,96],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7DZJW3GMCBHNCC1J37K73T7","feishu-kdocs-cli","Office cloud CLIs for agents: install, authenticate, verify and troubleshoot Feishu `lark-cli` and Kingsoft\u002FWPS Docs `kdocs-cli`, plus the three China office MCP endpoints (Feishu, WPS SkillHub, Tencent Docs). Use when setting up or re-logging-in 飞书 CLI \u002F 金山文档 CLI, when a command fails with missing scope \u002F PATH \u002F token \u002F device-code errors, when a kdocs or lark command returns 400001 or unknown action, or when wiring 飞书 \u002F 金山文档 \u002F 腾讯文档 MCP into Cindy, Claude or another host. Not a per-command reference: domain commands live in the lark-* Skills and the kdocs Skill.","https:\u002F\u002Fgithub.com\u002Fyhyu13\u002FAgentSkillsVault\u002Fblob\u002Fmain\u002FSKILL\u002Fdevops\u002Ftier0\u002Ffeishu-kdocs-cli\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7BE0VQF0T7ACMY3W9V27ZYG","vfx-fx","Cinematic and game VFX in Blender including smoke, fire, particles, trails, and Geometry Nodes FX setups via MCP.","https:\u002F\u002Fgithub.com\u002Fyhyu13\u002FAgentSkillsVault\u002Fblob\u002Fmain\u002FSKILL\u002Fgame-dev\u002Ftier2\u002Fvfx-fx\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7BE0Q23SY6QAW24XEADEH0N","uv-workflow","Production UV unwrapping for seam placement, UV packing, texel density, UDIM, lightmap UVs, and modular UV layouts. Use when preparing meshes for texturing and engine export in Blender via MCP.","https:\u002F\u002Fgithub.com\u002Fyhyu13\u002FAgentSkillsVault\u002Fblob\u002Fmain\u002FSKILL\u002Fgame-dev\u002Ftier2\u002Fuv-workflow\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7BE0JAKENVJB4Z0SV3Q7QGR","texture-workflow","Production texture workflow for atlases, baking AO\u002Fcurvature\u002Fnormal\u002Froughness maps, decals, and texture memory optimization. Use for game-ready texture pipelines in Blender via MCP.","https:\u002F\u002Fgithub.com\u002Fyhyu13\u002FAgentSkillsVault\u002Fblob\u002Fmain\u002FSKILL\u002Fgame-dev\u002Ftier2\u002Ftexture-workflow\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7BE0CYB7BDJP7HD5WTS2PJB","sculpting","Blender sculpting for organic and hard surface detail using Dyntopo, multiresolution, brushes, alpha workflow, wrinkles, and damage. Use when high-frequency surface detail is needed before retopology in Blender via MCP.","https:\u002F\u002Fgithub.com\u002Fyhyu13\u002FAgentSkillsVault\u002Fblob\u002Fmain\u002FSKILL\u002Fgame-dev\u002Ftier2\u002Fsculpting\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M7BE09TBX9NQ5EBHN4JZ9VXM","scene-assembly","Large scene layout in Blender with collections, linking, overrides, streaming-friendly organization, and set assembly via MCP.","https:\u002F\u002Fgithub.com\u002Fyhyu13\u002FAgentSkillsVault\u002Fblob\u002Fmain\u002FSKILL\u002Fgame-dev\u002Ftier2\u002Fscene-assembly\u002FSKILL.md",[],[]]