[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6VC4TA5639832NRSXKCT8MD":3,"skill-same:01M6VC4TA5639832NRSXKCT8MD":78},{"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":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":13,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":58,"install":59,"resources":71},"01M6VC4TA5639832NRSXKCT8MD","springboot-patterns",null,"Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.","sakamoto-family-smile\u002Fagent_monorepo","sakamoto-family-smile","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F132812403?v=4","01M6RTAT3H8PMWX5SJ65KP3VYF","01M6RTAV321WB5RAHCWTZMX5CV",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fecc\u002Fspringboot-patterns\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"patterns","springboot patterns","work","for","rest api design","spring boot architecture","processing","caching","java spring","async","use","design","spring","access","api","architecture patterns","data","spring boot","logging","architecture","2026-11-10 10:12:30",false,"---\nname: batch-tasks\ndescription: Execute TODO.md steps via unattended Claude Code sessions\nwhen_to_use: \"execute TODO.md steps, run specific tasks from a list, batch execute named tasks, 批量执行, run steps from TODO — NOT for goal-file loops (use \u002Floop) or task planning (use \u002Forchestrate)\"\nargument-hint: '[step2 step4 ...] | \"task1\" \"task2\" ... | --run [file] | --dry-run [file] | --parallel [file]'\nuser_invocable: true\n---\n\n# Batch Tasks Skill\n\nRead steps from TODO.md, auto-plan implementation details, and run them sequentially (or in parallel) via `claude -p`. Each task runs in a fresh Claude Code session with pre-generated plans.\n\n## Key features\n\n- **TODO.md integration** — Reads project TODO.md, parses steps and unchecked items. Default: first uncompleted step. Specify steps: `\u002Fbatch-tasks step2 step4`.\n- **Auto-planning** — Before writing tasks, the skill researches relevant files in the current session (which has codebase context) and generates detailed implementation plans with file paths, line numbers, and patterns to follow. This dramatically reduces token waste from redundant exploration in `claude -p` sessions.\n- **Scout scoring** — Each task is scored (0-100) before execution. Tasks scoring \u003C50 are skipped and a GitHub Issue is created instead. Tasks 50-79 are flagged as risky.\n- **Per-task model assignment** — Each task is automatically assigned `haiku` (simple deletions, \u003C20 lines), `sonnet` (standard features, 2-4 files), or `opus` (architectural, 5+ files) based on complexity.\n- **Per-task timeout & retries** — Each task has a configurable timeout (default 10 min) and retry count (default 2). Timed-out or failed tasks are rolled back via git and retried automatically.\n- **Failure resilience** — Failed tasks don't kill the batch. After all retries are exhausted, failures are logged to PROGRESS.md and a GitHub Issue is created automatically.\n- **Parallel execution** — `--parallel` flag runs independent tasks concurrently using git worktrees, with automatic conflict detection and merge.\n- **Background execution** with live progress monitoring\n\n## Usage\n\n### Execute TODO steps (primary usage)\n```\n\u002Fbatch-tasks              # First uncompleted step from TODO.md\n\u002Fbatch-tasks step2        # Execute Step 2\n\u002Fbatch-tasks step2 step4  # Execute Steps 2 and 4\n```\n\n### Run from quoted task descriptions\n```\n\u002Fbatch-tasks \"Fix sidebar padding\" \"Add loading skeleton to \u002Fprojects\"\n```\n\n### Run \u002F preview an existing task file\n```\n\u002Fbatch-tasks --run                # Serial execution\n\u002Fbatch-tasks --parallel           # Parallel execution (git worktrees)\n\u002Fbatch-tasks --dry-run\n```\n\n## How it works\n\n1. **Parse TODO.md** — Finds the target step(s), extracts unchecked `- [ ]` items\n2. **Planning phase** — For each item, searches the codebase (Glob\u002FGrep), reads relevant files, and generates a detailed plan with exact file paths, line numbers, and implementation steps\n3. **Scout scoring** — Each task is scored on readiness (target files found, patterns clear, no blocking deps). Tasks scoring \u003C50 are skipped.\n4. **Model assignment** — Each task gets assigned `haiku`, `sonnet`, or `opus` based on complexity\n5. Tasks are written to `tasks.txt` in delimited block format\n6. `~\u002F.claude\u002Fscripts\u002Frun-tasks.sh` (serial) or `~\u002F.claude\u002Fscripts\u002Frun-tasks-parallel.sh` (parallel) executes tasks\n7. Each task runs with a timeout; on failure, working tree is rolled back and the task is retried\n8. Logs go to `logs\u002Fclaude-tasks\u002F` with timestamps (per attempt)\n9. After all tasks complete: success\u002Ffailure summary, failures logged to PROGRESS.md + GitHub Issue\n\n## After batch-tasks completes\n\nRun `\u002Fcommit` to commit worker output (tasks run in-tree; changes may not be\ncommitted yet). It does not push — publication needs `--publish` or an existing\ndelivery authority.\nRun `\u002Freview` to verify behavior anchors still pass after autonomous changes.\n","# Batch Tasks Skill\n\nRead steps from TODO.md, auto-plan implementation details, and run them sequentially (or in parallel) via `claude -p`. Each task runs in a fresh Claude Code session with pre-generated plans.\n\n## Key features\n\n- **TODO.md integration** — Reads project TODO.md, parses steps and unchecked items. Default: first uncompleted step. Specify steps: `\u002Fbatch-tasks step2 step4`.\n- **Auto-planning** — Before writing tasks, the skill researches relevant files in the current session (which has codebase context) and generates detailed implementation plans with file paths, line numbers, and patterns to follow. This dramatically reduces token waste from redundant exploration in `claude -p` sessions.\n- **Scout scoring** — Each task is scored (0-100) before execution. Tasks scoring \u003C50 are skipped and a GitHub Issue is created instead. Tasks 50-79 are flagged as risky.\n- **Per-task model assignment** — Each task is automatically assigned `haiku` (simple deletions, \u003C20 lines), `sonnet` (standard features, 2-4 files), or `opus` (architectural, 5+ files) based on complexity.\n- **Per-task timeout & retries** — Each task has a configurable timeout (default 10 min) and retry count (default 2). Timed-out or failed tasks are rolled back via git and retried automatically.\n- **Failure resilience** — Failed tasks don't kill the batch. After all retries are exhausted, failures are logged to PROGRESS.md and a GitHub Issue is created automatically.\n- **Parallel execution** — `--parallel` flag runs independent tasks concurrently using git worktrees, with automatic conflict detection and merge.\n- **Background execution** with live progress monitoring\n\n## Usage\n\n### Execute TODO steps (primary usage)\n```\n\u002Fbatch-tasks              # First uncompleted step from TODO.md\n\u002Fbatch-tasks step2        # Execute Step 2\n\u002Fbatch-tasks step2 step4  # Execute Steps 2 and 4\n```\n\n### Run from quoted task descriptions\n```\n\u002Fbatch-tasks \"Fix sidebar padding\" \"Add loading skeleton to \u002Fprojects\"\n```\n\n### Run \u002F preview an existing task file\n```\n\u002Fbatch-tasks --run                # Serial execution\n\u002Fbatch-tasks --parallel           # Parallel execution (git worktrees)\n\u002Fbatch-tasks --dry-run\n```\n\n## How it works\n\n1. **Parse TODO.md** — Finds the target step(s), extracts unchecked `- [ ]` items\n2. **Planning phase** — For each item, searches the codebase (Glob\u002FGrep), reads relevant files, and generates a detailed plan with exact file paths, line numbers, and implementation steps\n3. **Scout scoring** — Each task is scored on readiness (target files found, patterns clear, no blocking deps). Tasks scoring \u003C50 are skipped.\n4. **Model assignment** — Each task gets assigned `haiku`, `sonnet`, or `opus` based on complexity\n5. Tasks are written to `tasks.txt` in delimited block format\n6. `~\u002F.claude\u002Fscripts\u002Frun-tasks.sh` (serial) or `~\u002F.claude\u002Fscripts\u002Frun-tasks-parallel.sh` (parallel) executes tasks\n7. Each task runs with a timeout; on failure, working tree is rolled back and the task is retried\n8. Logs go to `logs\u002Fclaude-tasks\u002F` with timestamps (per attempt)\n9. After all tasks complete: success\u002Ffailure summary, failures logged to PROGRESS.md + GitHub Issue\n\n## After batch-tasks completes\n\nRun `\u002Fcommit` to commit worker output (tasks run in-tree; changes may not be\ncommitted yet). It does not push — publication needs `--publish` or an existing\ndelivery authority.\nRun `\u002Freview` to verify behavior anchors still pass after autonomous changes.\n",{"name":48,"description":49,"when_to_use":50,"argument-hint":51,"user_invocable":52},"batch-tasks","Execute TODO.md steps via unattended Claude Code sessions","execute TODO.md steps, run specific tasks from a list, batch execute named tasks, 批量执行, run steps from TODO — NOT for goal-file loops (use \u002Floop) or task planning (use \u002Forchestrate)","[step2 step4 ...] | \"task1\" \"task2\" ... | --run [file] | --dry-run [file] | --parallel [file]",true,"main","60a901a00f46e71601f58727cb5661f8d3fb6d24",".claude\u002Fskills\u002Fecc\u002Fspringboot-patterns","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile","2026-11-08 20:29:14",{"source":8,"skillName":48,"commands":60,"prompt":70,"zipAvailable":52},[61,64,67],{"tool":62,"command":63},"npx","npx skills add sakamoto-family-smile\u002Fagent_monorepo --skill batch-tasks",{"tool":65,"command":66},"bunx","bunx skills add sakamoto-family-smile\u002Fagent_monorepo --skill batch-tasks",{"tool":68,"command":69},"pnpm","pnpm dlx skills add sakamoto-family-smile\u002Fagent_monorepo --skill batch-tasks","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fecc\u002Fspringboot-patterns\u002FSKILL.md",[72],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"prompt.md","REFERENCE","参考文档",18240,"https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fmcp-package\u002Fskills\u002Fbatch-tasks\u002Fprompt.md",[79,111,119,139,162,186],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":91,"publishedAt":43},"01M6RW50THEFSKK42YNR8XFZA1","remotion-video-creation","Best practices for Remotion - Video creation in React. 29 domain-specific rules covering 3D, animations, audio, captions, charts, transitions, and more.","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fecc\u002Fremotion-video-creation\u002FSKILL.md",[85,88],{"categoryNo":86,"categoryName":87,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":89,"categoryName":90,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",[92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,26],"Video","remotion video","remotion video creation","creation","Remotion","Charts","Captions","Audio","3D","Composition","Animation","best practices","more","animations","domain-specific","domain","three","Rules","Lottie",{"skillNo":112,"name":113,"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":114,"categories":115,"keywords":116,"publishedAt":43},"01M6VCJ23NPECPSZJKGY691F75","hotcook-recipes","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002Fhotcook-agent\u002Fdata\u002Fskills\u002Fhotcook-recipes\u002FSKILL.md",[],[117,118],"hotcook recipes","recipes",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":133,"publishedAt":43},"01M6VCHHE00X5XHSDRD1KH1BW2","code-helper","Code review and assistance skill","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002Fagent-system-2\u002Fskills\u002Fcode-helper\u002Fskill.md",[125,128],{"categoryNo":126,"categoryName":127,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":129,"categoryName":130,"taxonomyType":131,"taxonomyTypeDesc":132},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[134,135,136,137,138],"code helper","helper","code","code review","review",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":151,"publishedAt":43},"01M6VCH3Q31A20H6SQ1H0J7JB2","research-assistant","Web research assistant skill using Brave Search MCP","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002Fagent-system-1\u002Fskills\u002Fresearch-assistant\u002Fskill.md",[145,148],{"categoryNo":146,"categoryName":147,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":149,"categoryName":150,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[152,153,154,155,156,157,158,159,160,161],"research assistant","research","assistant","MCP","web","search","brave search","web research","brave","web research assistant",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":170,"publishedAt":43},"01M6VCGZZGPNVJSCZ1JTMNZAHY","x-api","X\u002FTwitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fecc\u002Fx-api\u002FSKILL.md",[168,169],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":129,"categoryName":130,"taxonomyType":131,"taxonomyTypeDesc":132},[171,37,172,173,174,175,26,176,177,178,179,180,23,181,182,33,183,184,157,185],"x api","with","when","limits","rate","threads","reading","native","posting","platform","api integration","twitter","auth","analytics","OAuth",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":193,"publishedAt":43},"01M6VCGVX6DGB1FKTA53QBBCQB","workspace-surface-audit","Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.","https:\u002F\u002Fgithub.com\u002Fsakamoto-family-smile\u002Fagent_monorepo\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fecc\u002Fworkspace-surface-audit\u002FSKILL.md",[192],{"categoryNo":149,"categoryName":150,"taxonomyType":20,"taxonomyTypeDesc":21},[194,195,196,197,155,198,199,136,200,201,202,203,33,204,205,206,207,178,208,173],"workspace surface audit","workspace","audit","hooks","workflows","connectors","capabilities","harness","repo","environment","up","harness setup","active","env","value"]