[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D75P3KDER4SWTYNHZP0BCY":3,"skill-same:01M7D75P3KDER4SWTYNHZP0BCY":46},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M7D75P3KDER4SWTYNHZP0BCY","ac-whitebox",null,"AllstarCoding 流水环节 9 使用。当所有任务通过评审、需要对项目完整状态做白盒测试、产出白盒测试文档、执行测试、解析问题清单、驱动修复循环时加载本技能。评估对象是当前项目的完整状态，不只改动面。","hxquan-q\u002Fopen-forge","hxquan-q","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180607655?v=4","01M7D70QBFWC9ZVGC49W3Y6J1M","xquan","01M7D70QC45F445W6V1AK76JZ7",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhxquan-q\u002Fopen-forge\u002Fblob\u002Fmain\u002Fpackages\u002Fplugins\u002Fpresets\u002Fallstar-coding\u002Fagent\u002Fskills\u002Fac-whitebox\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ac-whitebox\ndescription: AllstarCoding 流水环节 9 使用。当所有任务通过评审、需要对项目完整状态做白盒测试、产出白盒测试文档、执行测试、解析问题清单、驱动修复循环时加载本技能。评估对象是当前项目的完整状态，不只改动面。\n---\n\u003C!-- Copyright The Open Forge contributors. -->\n\n# AC 白盒测试（流水环节 9）\n\n目标：**全部任务（T）通过评审后**，对**当前项目的完整状态**（不只改动面，没涉及改动的也要评估）做白盒测试。产出白盒测试文档 → 测试子执行 → 结构化问题清单 → 修复循环 → 直到无严重问题。\n\n**执行者**：白盒测试文档由白测子产出（spawn 一次性）；测试执行由白测子完成（可复用会话）；修复走 followup_task 唤醒对应任务的开发子。写域（ac-pipeline §0.3）：`whitebox.md` + `test-results\u002F**` + 项目 `test\u002F` 目录——T2 范围允许档，临时物有界。\n\n## 1. 测试范围（从三处派生）\n\n1. requires.md 验收标准（A# 条目）——逐条要有测试覆盖\n2. design.md 测试策略节（白盒重点：调用链验证点）\n3. reviews.md 遗留 [一般] 项与各 T 风险记录——重点回归\n4. **项目整体健康**（本流水特定：没涉及改动的部分也要纳入评估视野——项目层体检）\n\n## 2. 项目健康总检（先于逐用例，三项必查）\n\n| # | 检查项 | 方法 | 判定 |\n|---|--------|------|------|\n| P1 | 结构完整性 | 对照 tasks.md：声明的文件全部存在；`git status` 无任务卡外的孤儿文件 | 缺文件\u002F孤儿 → [严重] |\n| P2 | 正常启动 | 构建通过 + 项目能起（按项目实际：dev server \u002F 服务进程） | 构建失败\u002F起不来 → [严重] |\n| P3 | 已有功能冲突（冒烟） | 挑改动面邻近的**既有**核心功能 2-3 条跑通（回归思维） | 冒烟挂 → [严重] |\n\n规则：体检结果进 whitebox.md 的 P 区；任何 P 项 [严重] → 完成判定必须等 P 项全过；证据要求同机器可判条目（命令输出贴报告，不口头断言）。\n\n## 3. whitebox.md 模板\n\n```markdown\n# 白盒测试文档\n状态: 草案 | 执行中 | 已执行 | 更新: \u003C时间>\n## 1. 测试计划\n| # | 用例 | 来源 | 命令\u002F方法 | 判定 |\n|---|------|------|-----------|------|\n| P1 | 项目健康总检 | §2 | \u003C三条命令> | 三项全过 |\n| W1 | \u003C测什么> | A1 | \u003C可执行命令> | \u003C期望> |\n## 2. 执行环境\n\u003C平台、工具链、测试框架、运行目录>\n## 3. 问题清单 schema\nseverity(严重|一般|轻微)\u002Ffile\u002Fline\u002Ftest(W#)\u002Fmessage(≤200字符)\u002FstackTail；\nverdict: 任一严重→fail；无严重但一般≥3→fail；否则 pass\n## 4. 结果（执行后回填）\n\u003C用例状态 + 问题清单 + 总结论>\n```\n\n用例设计要点：**可执行优先**（能落成命令\u002F测试脚本的不写\"人工检查\"）；每条注明来源（A#\u002FS#\u002F回归）；启动类用例附运行时长要求（如连续运行 ≥5 分钟无报错）。\n\n## 4. 执行通道（测试子）\n\n1. 测试命令后台跑、输出**落盘**（`--reporter=json --outputFile=\u003C路径>` 或重定向文件）再读——避免管道捕获陷阱。\n2. 落盘编码：Windows 下 PowerShell `>` 重定向默认 UTF-16 会误判 binary——用框架自带 outputFile 或 `Out-File -Encoding utf8` 或 node 直接写。\n3. 环境级跑不起来（装依赖失败\u002F框架崩）→ 记\"待主控处理\"，不算测试失败。\n4. 问题清单落盘 `docs\u002Fac\u002Ftest-results\u002Fissues-latest.md`（Markdown 表格 + 汇总行），历史轮次存 `issues-round-\u003Cn>.md`。\n5. 问题状态流转：`待修` → `已修`（复跑通过）\u002F `未修`（有不能修的理由，待用户裁决）\u002F `新引入`（下轮重点）。\n\n## 5. 修复循环（主控驱动）\n\n1. 问题清单含任一 [严重]，或 [一般]≥3 → 派修复：\n   - 问题可定位到具体任务 → `followup_task(dev_t\u003Cn>, ...)` 唤醒该任务开发子（优先，保留其上下文）\n   - 跨多任务\u002F无法定位 → 主控评估后指派（新起修复子或最相关开发子）\n2. 修复 settlement → 复跑受影响用例 → 更新问题清单（已修\u002F未修\u002F新引入）。\n3. **跳回规则**：问题根源在上游产物（需求错了\u002F设计错了）→ 该开发子不得改上游文档，上报主控 → 主控打回对应文档环节（ac-pipeline §5.3）→ 受影响下游作废重走。\n4. 循环直至：无 [严重] 且 [一般] 清零或用户接受遗留。修复轮次上限 3 轮，超限上报裁决。\n5. 每轮 state.md 更新（executions+1，子环节粒度记录）。\n\n## 6. 完成判定（进黑盒的前置）\n\n- [ ] 项目健康总检 P1\u002FP2\u002FP3 全过（证据在案）\n- [ ] 全部 W 用例执行完毕（通过\u002F豁免，豁免有理由）\n- [ ] 无未解决 [严重]\n- [ ] [一般] 清零或用户书面接受\n- [ ] 最终问题清单落盘 + whitebox.md 状态 `已执行`\n\n完成后：state.md 更新（环节 9 done）→ 环节 9 收口（ac-gate 校验）→ 打 stage 档（`stage 9\u002F白盒测试: 全部通过`，含 whitebox.md + test-results\u002F + 白盒轮修复的代码改动，经轻量 git 子代理 + V4，§0.5）→ 交接 ac-blackbox。\n","\u003C!-- Copyright The Open Forge contributors. -->\n\n# AC 白盒测试（流水环节 9）\n\n目标：**全部任务（T）通过评审后**，对**当前项目的完整状态**（不只改动面，没涉及改动的也要评估）做白盒测试。产出白盒测试文档 → 测试子执行 → 结构化问题清单 → 修复循环 → 直到无严重问题。\n\n**执行者**：白盒测试文档由白测子产出（spawn 一次性）；测试执行由白测子完成（可复用会话）；修复走 followup_task 唤醒对应任务的开发子。写域（ac-pipeline §0.3）：`whitebox.md` + `test-results\u002F**` + 项目 `test\u002F` 目录——T2 范围允许档，临时物有界。\n\n## 1. 测试范围（从三处派生）\n\n1. requires.md 验收标准（A# 条目）——逐条要有测试覆盖\n2. design.md 测试策略节（白盒重点：调用链验证点）\n3. reviews.md 遗留 [一般] 项与各 T 风险记录——重点回归\n4. **项目整体健康**（本流水特定：没涉及改动的部分也要纳入评估视野——项目层体检）\n\n## 2. 项目健康总检（先于逐用例，三项必查）\n\n| # | 检查项 | 方法 | 判定 |\n|---|--------|------|------|\n| P1 | 结构完整性 | 对照 tasks.md：声明的文件全部存在；`git status` 无任务卡外的孤儿文件 | 缺文件\u002F孤儿 → [严重] |\n| P2 | 正常启动 | 构建通过 + 项目能起（按项目实际：dev server \u002F 服务进程） | 构建失败\u002F起不来 → [严重] |\n| P3 | 已有功能冲突（冒烟） | 挑改动面邻近的**既有**核心功能 2-3 条跑通（回归思维） | 冒烟挂 → [严重] |\n\n规则：体检结果进 whitebox.md 的 P 区；任何 P 项 [严重] → 完成判定必须等 P 项全过；证据要求同机器可判条目（命令输出贴报告，不口头断言）。\n\n## 3. whitebox.md 模板\n\n```markdown\n# 白盒测试文档\n状态: 草案 | 执行中 | 已执行 | 更新: \u003C时间>\n## 1. 测试计划\n| # | 用例 | 来源 | 命令\u002F方法 | 判定 |\n|---|------|------|-----------|------|\n| P1 | 项目健康总检 | §2 | \u003C三条命令> | 三项全过 |\n| W1 | \u003C测什么> | A1 | \u003C可执行命令> | \u003C期望> |\n## 2. 执行环境\n\u003C平台、工具链、测试框架、运行目录>\n## 3. 问题清单 schema\nseverity(严重|一般|轻微)\u002Ffile\u002Fline\u002Ftest(W#)\u002Fmessage(≤200字符)\u002FstackTail；\nverdict: 任一严重→fail；无严重但一般≥3→fail；否则 pass\n## 4. 结果（执行后回填）\n\u003C用例状态 + 问题清单 + 总结论>\n```\n\n用例设计要点：**可执行优先**（能落成命令\u002F测试脚本的不写\"人工检查\"）；每条注明来源（A#\u002FS#\u002F回归）；启动类用例附运行时长要求（如连续运行 ≥5 分钟无报错）。\n\n## 4. 执行通道（测试子）\n\n1. 测试命令后台跑、输出**落盘**（`--reporter=json --outputFile=\u003C路径>` 或重定向文件）再读——避免管道捕获陷阱。\n2. 落盘编码：Windows 下 PowerShell `>` 重定向默认 UTF-16 会误判 binary——用框架自带 outputFile 或 `Out-File -Encoding utf8` 或 node 直接写。\n3. 环境级跑不起来（装依赖失败\u002F框架崩）→ 记\"待主控处理\"，不算测试失败。\n4. 问题清单落盘 `docs\u002Fac\u002Ftest-results\u002Fissues-latest.md`（Markdown 表格 + 汇总行），历史轮次存 `issues-round-\u003Cn>.md`。\n5. 问题状态流转：`待修` → `已修`（复跑通过）\u002F `未修`（有不能修的理由，待用户裁决）\u002F `新引入`（下轮重点）。\n\n## 5. 修复循环（主控驱动）\n\n1. 问题清单含任一 [严重]，或 [一般]≥3 → 派修复：\n   - 问题可定位到具体任务 → `followup_task(dev_t\u003Cn>, ...)` 唤醒该任务开发子（优先，保留其上下文）\n   - 跨多任务\u002F无法定位 → 主控评估后指派（新起修复子或最相关开发子）\n2. 修复 settlement → 复跑受影响用例 → 更新问题清单（已修\u002F未修\u002F新引入）。\n3. **跳回规则**：问题根源在上游产物（需求错了\u002F设计错了）→ 该开发子不得改上游文档，上报主控 → 主控打回对应文档环节（ac-pipeline §5.3）→ 受影响下游作废重走。\n4. 循环直至：无 [严重] 且 [一般] 清零或用户接受遗留。修复轮次上限 3 轮，超限上报裁决。\n5. 每轮 state.md 更新（executions+1，子环节粒度记录）。\n\n## 6. 完成判定（进黑盒的前置）\n\n- [ ] 项目健康总检 P1\u002FP2\u002FP3 全过（证据在案）\n- [ ] 全部 W 用例执行完毕（通过\u002F豁免，豁免有理由）\n- [ ] 无未解决 [严重]\n- [ ] [一般] 清零或用户书面接受\n- [ ] 最终问题清单落盘 + whitebox.md 状态 `已执行`\n\n完成后：state.md 更新（环节 9 done）→ 环节 9 收口（ac-gate 校验）→ 打 stage 档（`stage 9\u002F白盒测试: 全部通过`，含 whitebox.md + test-results\u002F + 白盒轮修复的代码改动，经轻量 git 子代理 + V4，§0.5）→ 交接 ac-blackbox。\n",{"name":5,"description":7},"main","5b8347d653ab3cc1323c53dbeddd4c009b330d96","packages\u002Fplugins\u002Fpresets\u002Fallstar-coding\u002Fagent\u002Fskills\u002Fac-whitebox",0,"https:\u002F\u002Fgithub.com\u002Fhxquan-q\u002Fopen-forge","https:\u002F\u002Fwww.openvetta.com","https:\u002F\u002Fgithub.com\u002Fhxquan-q","2026-11-13 17:08:23",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add hxquan-q\u002Fopen-forge --skill ac-whitebox",{"tool":38,"command":39},"bunx","bunx skills add hxquan-q\u002Fopen-forge --skill ac-whitebox",{"tool":41,"command":42},"pnpm","pnpm dlx skills add hxquan-q\u002Fopen-forge --skill ac-whitebox","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhxquan-q\u002Fopen-forge\u002Fblob\u002Fmain\u002Fpackages\u002Fplugins\u002Fpresets\u002Fallstar-coding\u002Fagent\u002Fskills\u002Fac-whitebox\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7D79WJRKSSY9DXVHJ8VXS2G","review-canvas","Present a multi-file code review as a Canvas diff artifact. Use when the user asks for a review, 代码评审, 变更审查, or a cross-file summary of changes — not for a single edit (the chat diff card already shows it) or a prose report (report-canvas).","https:\u002F\u002Fgithub.com\u002Fhxquan-q\u002Fopen-forge\u002Fblob\u002Fmain\u002Fpackages\u002Fskill-presets\u002Freview-canvas\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7D79QD1TTMEJSC0XQN8ADSJ","report-canvas","Produce a standalone report, audit board, or long-form analysis as a Canvas artifact. Use when the user asks for a report, 报告, 审计看板, or a deliverable that should live beside chat — not when they only want a short chat answer or to inspect a live web page.","https:\u002F\u002Fgithub.com\u002Fhxquan-q\u002Fopen-forge\u002Fblob\u002Fmain\u002Fpackages\u002Fskill-presets\u002Freport-canvas\u002FSKILL.md",[],[],{"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},"01M7D79JZ390ZN0950BFNQGE6J","publish-ability","Publish a skill, scene, MCP server, plugin, or bundle to the Vetta ability marketplace. Use when the user asks to upload\u002Fpublish\u002Fsubmit an ability, put a plugin on the marketplace, share a skill with other users, or migrate an existing package into Vetta.","https:\u002F\u002Fgithub.com\u002Fhxquan-q\u002Fopen-forge\u002Fblob\u002Fmain\u002Fpackages\u002Fskill-presets\u002Fpublish-ability\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},"01M7D79DP3TX2CCZBT0W8CTZKT","install-ability","在本机 Vetta 中安装能力——插件（plugin）、Skill\u002F场景（scene）与 MCP 服务器。用户说「装一个插件 \u002F install plugin \u002F 从能力市场安装 \u002F 加一个 MCP server \u002F 配置 MCP \u002F 装个 skill」，或插件装完没生效、需要 reload、pending 版本没应用时使用。不用于安装 npm 依赖、IDE 插件、浏览器扩展，也不用于开发插件（那是 plugin-workbench）或创作 Skill（那是 create-skill）。","https:\u002F\u002Fgithub.com\u002Fhxquan-q\u002Fopen-forge\u002Fblob\u002Fmain\u002Fpackages\u002Fskill-presets\u002Finstall-ability\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},"01M7D799QHEKZBTFA47YXAWFJS","database-analysis","Answer business questions from connected databases with read-only queries, then analyze metrics, trends, rankings, breakdowns, and period comparisons. Use for 问数、查数、数据库分析、销量\u002F收入\u002F用户指标、同比环比 or follow-up data questions. Not for application database migrations or modifying records.","https:\u002F\u002Fgithub.com\u002Fhxquan-q\u002Fopen-forge\u002Fblob\u002Fmain\u002Fpackages\u002Fskill-presets\u002Fdatabase-analysis\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},"01M7D795QA8HPGGC6NJ6J5EEJC","create-skill","Create or update Vetta-compatible Agent Skills. Use when the user asks to create a skill, add a SKILL.md workflow, register a skill in skills-manifest.json, package a skill in a Vetta plugin, or add a built-in Vetta skill preset.","https:\u002F\u002Fgithub.com\u002Fhxquan-q\u002Fopen-forge\u002Fblob\u002Fmain\u002Fpackages\u002Fskill-presets\u002Fcreate-skill\u002FSKILL.md",[],[]]