[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JV29WNJ5ZSH4PE6BJM4B3G":3,"skill-same:01M6JV29WNJ5ZSH4PE6BJM4B3G":64},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M6JV29WNJ5ZSH4PE6BJM4B3G","git-worktree-isolation",null,"基于 Git Worktree 的任务隔离工作流：每个开发任务在独立 worktree 中执行， 确保主工作区干净、并行任务互不干扰，完成后结构化决策合并\u002FPR\u002F保留\u002F丢弃。 与 parallel-execution 的 worktree 基础设施互补，本 skill 聚焦任务级隔离策略。","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1571,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FColin4k1024\u002Ftsp\u002Fskills\u002Fgit-worktree-isolation\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32],"git","worktree","git worktree","isolation","worktree isolation","git worktree isolation","pr","harness","engineering","execution","parallel","superpowers","worktrees","parallel-execution","2026-11-10 10:12:30",false,"---\nname: git-worktree-isolation\ndescription: >\n  基于 Git Worktree 的任务隔离工作流：每个开发任务在独立 worktree 中执行，\n  确保主工作区干净、并行任务互不干扰，完成后结构化决策合并\u002FPR\u002F保留\u002F丢弃。\n  与 parallel-execution 的 worktree 基础设施互补，本 skill 聚焦任务级隔离策略。\norigin: superpowers-using-git-worktrees + harness-engineering\n---\n\n# Git Worktree Isolation\n\n## 用途\n\n- 确保每个开发任务（feature \u002F fix \u002F spike）在 **隔离的 worktree + 分支** 中执行，主工作区始终保持可切换状态。\n- 在多 agent 并行场景下，每个 agent 拥有独立文件系统视图，避免写冲突。\n- 任务完成后提供 **结构化收口决策**（merge \u002F PR \u002F keep \u002F discard），而不是任凭 worktree 积累。\n\n## 触发信号\n\n- `\u002Fteam-execute` 分派的并行实现任务。\n- `wave-execution` 中同一 Wave 的多个工作项。\n- 需要在不影响主分支的情况下进行探索性实现或 spike。\n- 当前工作区有未提交变更，但需要紧急处理另一个任务。\n- Code review 后的修改需要在隔离环境中完成。\n\n## 核心原则\n\n1. **一个任务 = 一个 worktree = 一个分支**——不共用 worktree。\n2. **worktree 有明确生命周期**——创建时绑定任务 ID，完成后必须做收口决策。\n3. **主工作区是调度中心**——编排和合并在主工作区进行，实现在 worktree 中进行。\n\n## 工作流\n\n### 1. 创建隔离环境\n\n```bash\n# 命名规则: .worktrees\u002F{slug}-{task-id}\ngit worktree add .worktrees\u002F{slug}-{task-id} -b task\u002F{slug}\u002F{task-id}\n\n# 验证隔离\ncd .worktrees\u002F{slug}-{task-id}\ngit branch --show-current   # → task\u002F{slug}\u002F{task-id}\n```\n\n**命名约定：**\n\n| 元素 | 格式 | 示例 |\n|------|------|------|\n| Worktree 路径 | `.worktrees\u002F{slug}-{task-id}` | `.worktrees\u002Fauth-T001` |\n| 分支名 | `task\u002F{slug}\u002F{task-id}` | `task\u002Fauth\u002FT001` |\n| Spike 分支 | `spike\u002F{slug}\u002F{description}` | `spike\u002Fauth\u002Foauth-flow` |\n\n### 2. 在 worktree 中执行\n\n```\n进入 worktree 目录 →\n  加载任务上下文（STATE.md 对应工作项）→\n  执行实现 →\n  运行测试 →\n  提交到 worktree 分支\n```\n\n**执行约束：**\n\n- 每个 worktree 中的 agent 只操作任务范围内的文件。\n- 不在 worktree 中修改共享配置（package.json \u002F pom.xml 等），除非任务明确要求。\n- 提交信息包含任务 ID：`feat(T001): implement auth flow`。\n\n### 3. 收口决策\n\n任务完成后，在 **主工作区** 执行收口：\n\n| 决策 | 条件 | 操作 |\n|------|------|------|\n| **Merge** | 代码通过 review + 测试 | `git merge task\u002F{slug}\u002F{task-id}` + 清理 worktree |\n| **PR** | 需要异步 review 或 CI | 创建 PR + 保留 worktree 直到合并 |\n| **Keep** | 任务暂停但稳定 | 标记为 `paused`，保留 worktree |\n| **Discard** | spike 完成或方向废弃 | 删除 worktree + 分支 |\n\n```bash\n# Merge 路径\ncd \u002Fpath\u002Fto\u002Fmain-worktree\ngit merge --no-ff task\u002F{slug}\u002F{task-id} -m \"feat(T001): implement auth flow\"\ngit worktree remove .worktrees\u002F{slug}-{task-id}\ngit branch -d task\u002F{slug}\u002F{task-id}\n\n# Discard 路径\ngit worktree remove --force .worktrees\u002F{slug}-{task-id}\ngit branch -D spike\u002F{slug}\u002F{description}\n```\n\n### 4. 清理巡检\n\n定期（或每次 `\u002Fteam-review` 前）执行清理：\n\n```bash\n# 列出所有 worktree\ngit worktree list\n\n# 清理已删除的 worktree 引用\ngit worktree prune\n\n# 查找已合并但未清理的任务分支\ngit branch --merged main | grep 'task\u002F'\n```\n\n## 与 parallel-execution 的关系\n\n| 关注点 | parallel-execution | git-worktree-isolation |\n|--------|-------------------|----------------------|\n| 核心目标 | 多实例并行加速 | 任务级文件隔离 |\n| Worktree 使用 | 作为并行基础设施 | 作为隔离策略 |\n| 分支管理 | 自动创建\u002F合并 | 结构化收口决策 |\n| 清理策略 | 任务结束自动清理 | 显式四选一决策 |\n| 集成点 | wave-execution 调用 | 为 parallel-execution 提供隔离规范 |\n\n`parallel-execution` 调用 `git-worktree-isolation` 的隔离规范创建 worktree，`git-worktree-isolation` 依赖 `parallel-execution` 的任务分发能力。\n\n## 与 session-continuity 的关系\n\n- `\u002Fpause` 时：记录活跃 worktree 列表到 HANDOFF.json 的 `active_worktrees` 字段。\n- `\u002Fresume` 时：检查 worktree 状态，标记哪些仍然有效、哪些需要清理。\n\n## 配套约束\n\n1. `.worktrees\u002F` 目录加入 `.gitignore`，不提交到远程仓库。\n2. worktree 中不执行 `git rebase` 主分支——避免在隔离环境中引入合并复杂度。\n3. 超过 7 天未活动的 worktree 在清理巡检时标记为候选清理项。\n4. 共享锁文件（lockfile）变更在 merge 阶段统一解决，不在 worktree 中各自更新。\n\n## 验证标准\n\n- [ ] 创建的 worktree 路径遵循 `.worktrees\u002F{slug}-{task-id}` 命名规范\n- [ ] 每个 worktree 对应唯一分支，无分支共用\n- [ ] 任务完成后在 24h 内执行收口决策（merge \u002F PR \u002F keep \u002F discard）\n- [ ] `git worktree list` 无孤立 worktree\n- [ ] 已合并分支已被删除\n","# Git Worktree Isolation\n\n## 用途\n\n- 确保每个开发任务（feature \u002F fix \u002F spike）在 **隔离的 worktree + 分支** 中执行，主工作区始终保持可切换状态。\n- 在多 agent 并行场景下，每个 agent 拥有独立文件系统视图，避免写冲突。\n- 任务完成后提供 **结构化收口决策**（merge \u002F PR \u002F keep \u002F discard），而不是任凭 worktree 积累。\n\n## 触发信号\n\n- `\u002Fteam-execute` 分派的并行实现任务。\n- `wave-execution` 中同一 Wave 的多个工作项。\n- 需要在不影响主分支的情况下进行探索性实现或 spike。\n- 当前工作区有未提交变更，但需要紧急处理另一个任务。\n- Code review 后的修改需要在隔离环境中完成。\n\n## 核心原则\n\n1. **一个任务 = 一个 worktree = 一个分支**——不共用 worktree。\n2. **worktree 有明确生命周期**——创建时绑定任务 ID，完成后必须做收口决策。\n3. **主工作区是调度中心**——编排和合并在主工作区进行，实现在 worktree 中进行。\n\n## 工作流\n\n### 1. 创建隔离环境\n\n```bash\n# 命名规则: .worktrees\u002F{slug}-{task-id}\ngit worktree add .worktrees\u002F{slug}-{task-id} -b task\u002F{slug}\u002F{task-id}\n\n# 验证隔离\ncd .worktrees\u002F{slug}-{task-id}\ngit branch --show-current   # → task\u002F{slug}\u002F{task-id}\n```\n\n**命名约定：**\n\n| 元素 | 格式 | 示例 |\n|------|------|------|\n| Worktree 路径 | `.worktrees\u002F{slug}-{task-id}` | `.worktrees\u002Fauth-T001` |\n| 分支名 | `task\u002F{slug}\u002F{task-id}` | `task\u002Fauth\u002FT001` |\n| Spike 分支 | `spike\u002F{slug}\u002F{description}` | `spike\u002Fauth\u002Foauth-flow` |\n\n### 2. 在 worktree 中执行\n\n```\n进入 worktree 目录 →\n  加载任务上下文（STATE.md 对应工作项）→\n  执行实现 →\n  运行测试 →\n  提交到 worktree 分支\n```\n\n**执行约束：**\n\n- 每个 worktree 中的 agent 只操作任务范围内的文件。\n- 不在 worktree 中修改共享配置（package.json \u002F pom.xml 等），除非任务明确要求。\n- 提交信息包含任务 ID：`feat(T001): implement auth flow`。\n\n### 3. 收口决策\n\n任务完成后，在 **主工作区** 执行收口：\n\n| 决策 | 条件 | 操作 |\n|------|------|------|\n| **Merge** | 代码通过 review + 测试 | `git merge task\u002F{slug}\u002F{task-id}` + 清理 worktree |\n| **PR** | 需要异步 review 或 CI | 创建 PR + 保留 worktree 直到合并 |\n| **Keep** | 任务暂停但稳定 | 标记为 `paused`，保留 worktree |\n| **Discard** | spike 完成或方向废弃 | 删除 worktree + 分支 |\n\n```bash\n# Merge 路径\ncd \u002Fpath\u002Fto\u002Fmain-worktree\ngit merge --no-ff task\u002F{slug}\u002F{task-id} -m \"feat(T001): implement auth flow\"\ngit worktree remove .worktrees\u002F{slug}-{task-id}\ngit branch -d task\u002F{slug}\u002F{task-id}\n\n# Discard 路径\ngit worktree remove --force .worktrees\u002F{slug}-{task-id}\ngit branch -D spike\u002F{slug}\u002F{description}\n```\n\n### 4. 清理巡检\n\n定期（或每次 `\u002Fteam-review` 前）执行清理：\n\n```bash\n# 列出所有 worktree\ngit worktree list\n\n# 清理已删除的 worktree 引用\ngit worktree prune\n\n# 查找已合并但未清理的任务分支\ngit branch --merged main | grep 'task\u002F'\n```\n\n## 与 parallel-execution 的关系\n\n| 关注点 | parallel-execution | git-worktree-isolation |\n|--------|-------------------|----------------------|\n| 核心目标 | 多实例并行加速 | 任务级文件隔离 |\n| Worktree 使用 | 作为并行基础设施 | 作为隔离策略 |\n| 分支管理 | 自动创建\u002F合并 | 结构化收口决策 |\n| 清理策略 | 任务结束自动清理 | 显式四选一决策 |\n| 集成点 | wave-execution 调用 | 为 parallel-execution 提供隔离规范 |\n\n`parallel-execution` 调用 `git-worktree-isolation` 的隔离规范创建 worktree，`git-worktree-isolation` 依赖 `parallel-execution` 的任务分发能力。\n\n## 与 session-continuity 的关系\n\n- `\u002Fpause` 时：记录活跃 worktree 列表到 HANDOFF.json 的 `active_worktrees` 字段。\n- `\u002Fresume` 时：检查 worktree 状态，标记哪些仍然有效、哪些需要清理。\n\n## 配套约束\n\n1. `.worktrees\u002F` 目录加入 `.gitignore`，不提交到远程仓库。\n2. worktree 中不执行 `git rebase` 主分支——避免在隔离环境中引入合并复杂度。\n3. 超过 7 天未活动的 worktree 在清理巡检时标记为候选清理项。\n4. 共享锁文件（lockfile）变更在 merge 阶段统一解决，不在 worktree 中各自更新。\n\n## 验证标准\n\n- [ ] 创建的 worktree 路径遵循 `.worktrees\u002F{slug}-{task-id}` 命名规范\n- [ ] 每个 worktree 对应唯一分支，无分支共用\n- [ ] 任务完成后在 24h 内执行收口决策（merge \u002F PR \u002F keep \u002F discard）\n- [ ] `git worktree list` 无孤立 worktree\n- [ ] 已合并分支已被删除\n",{"name":5,"origin":38,"description":39},"superpowers-using-git-worktrees + harness-engineering","基于 Git Worktree 的任务隔离工作流：每个开发任务在独立 worktree 中执行， 确保主工作区干净、并行任务互不干扰，完成后结构化决策合并\u002FPR\u002F保留\u002F丢弃。 与 parallel-execution 的 worktree 基础设施互补，本 skill 聚焦任务级隔离策略。\n","main","b0f0a87593c578a7898eccaf1b363f7f87c1f99b","plugins\u002FColin4k1024\u002Ftsp\u002Fskills\u002Fgit-worktree-isolation",490,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 02:12:02",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill git-worktree-isolation",{"tool":56,"command":57},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill git-worktree-isolation",{"tool":59,"command":60},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill git-worktree-isolation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FColin4k1024\u002Ftsp\u002Fskills\u002Fgit-worktree-isolation\u002FSKILL.md",true,[],[65,73,80,87,114,139],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":72},"01M746ZWACVKMZ1BJXJZHYJSSX","migrate-to-e2e","Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for \u002Fmigrate-to-e2e, \"migrate our tests to e2e\", \"port these Maestro flows\", \"move our TesterArmy tests\", or when a project has an e2e config and an older suite still running.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fmigrate-to-e2e\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":72},"01M746ZPTAX1Q0FBKAB1CYND7E","e2e","Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fe2e\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":72},"01M746ZJN784HVHMDP9MQGCSGG","create-verification-skill","Generate a project-local verify-\u003Capp> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for \u002Fcreate-verification-skill, \"make a verification skill for this repo\", or when a project has no scripted way to prove UI behavior.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fcreate-verification-skill\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":33},"01M716A6ETNB9B1SQ3GXZC75VR","deja-search","deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-search\u002FSKILL.md",[],[94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113],"search","deja search","never","error","ready","memory","re","decide","fix","design","debugging","when","you","done","reviewer","io","change","cli","merge","past",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":33},"01M716A3J2W5SENSE9VGMXB375","deja-reflect","End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-reflect\u002FSKILL.md",[],[121,122,123,109,124,125,126,127,128,129,130,131,132,133,99,134,135,136,137,138],"deja reflect","reflect","review","with","record","github","next","https","node","Rules","decisions","brew","remember","project rules","project","session","end","reflection",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":156,"publishedAt":33},"01M715T3RR4BAYSR57HPPTJ0PF","revid","Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftmakersas\u002Frevid-skills\u002Fskills\u002Frevid\u002FSKILL.md",[145,150,153],{"categoryNo":146,"categoryName":147,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":151,"categoryName":152,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":154,"categoryName":155,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000010","后端与接口",[141,157,158,159,160,161,162,135,163,100,164,165,166,167,105,168,169,170,171,172],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]