[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AWT4NWHJBC9R4YGF54CQ7G":3,"skill-same:01M7AWT4NWHJBC9R4YGF54CQ7G":56},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":49},"01M7AWT4NWHJBC9R4YGF54CQ7G","taskmaster",null,"Stop hook that keeps the agent working until all plans and user requests are\n100% complete. Fires when the agent tries to stop, re-examines the plan and\ntask list, and forces continuation if anything is unfinished. Prevents\npremature stopping on multi-step tasks.","barkleesanders\u002Fclaude-code-starter","barkleesanders","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F30680901?v=4","01M7AW019CGBYWDA8MFJEN1JXC","Barklee Sanders","01M7AW01A5H994ASJ2QZPW67AV",4,"MIT","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Ftaskmaster\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: taskmaster\nuser-invocable: true\ndescription: |\n  Stop hook that keeps the agent working until all plans and user requests are\n  100% complete. Fires when the agent tries to stop, re-examines the plan and\n  task list, and forces continuation if anything is unfinished. Prevents\n  premature stopping on multi-step tasks.\nauthor: blader\nversion: 1.0.0\n---\n\n# Taskmaster\n\nA stop hook that prevents the agent from stopping prematurely. When a response\nfinishes and the agent is about to stop, this hook intercepts and prompts it\nto re-examine whether all work is truly done.\n\n## How It Works\n\n1. **Agent tries to stop** — the stop hook fires.\n2. **The hook checks** for incomplete signals (pending tasks, recent errors, blind spots in infra\u002Fconfig work — see reason text in check-completion.sh).\n3. **Agent is prompted** to verify: original requests addressed, plan steps\n   completed, tasks resolved, errors fixed, no loose ends.\n4. **If work remains**, the agent continues. If truly done, it confirms and\n   the hook allows the stop on the next cycle.\n\n## Loop Protection\n\nA session-scoped counter limits continuations to **10 by default**. Set\n`TASKMASTER_MAX` environment variable to change:\n\n```bash\nexport TASKMASTER_MAX=20  # allow up to 20 continuations\nexport TASKMASTER_MAX=0   # infinite — never cap (relies on stop_hook_active check only)\n```\n\n## Setup\n\nThe hook must be registered in `~\u002F.claude\u002Fsettings.json`:\n\n```json\n{\n  \"hooks\": {\n    \"Stop\": [\n      {\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"$HOME\u002F.claude\u002Fskills\u002Ftaskmaster\u002Fhooks\u002Fcheck-completion.sh\",\n            \"timeout\": 10\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\n## Disabling\n\nTo temporarily disable, either:\n- Remove or comment out the Stop hook in `~\u002F.claude\u002Fsettings.json`\n- Set `TASKMASTER_MAX=1` to allow only one continuation check\n\n## Lighter Alternative: `\u002Fgoal` (Claude Code 2.1.139+)\n\nFor one-shot autonomous loops where you don't need taskmaster's full\nplan + task list + beads + worktree + AI-verify gating, use the built-in\n`\u002Fgoal` command instead:\n\n```\n\u002Fgoal all CI checks green and all worktrees pushed\n```\n\n`\u002Fgoal` sets a single completion condition and Claude keeps working across\nturns until it's met. Useful when:\n\n- You want a *specific* exit criterion, not \"no incomplete signals\"\n- The work is bounded (one feature, one bug, one cleanup) and beads\u002Fworktree\n  state doesn't matter\n- You want the agent to stop the moment the goal is met, even if other\n  in_progress beads exist\n\nUse **taskmaster** (this skill, always-on Stop hook) when:\n\n- Multi-step plans, multiple beads, multiple worktrees in flight\n- You want adjacent-safety gating (WORKTREE_BLOCK, AI_VERIFY_BLOCK, BEADS_BLOCK)\n- The \"done\" condition is fuzzy (\"ship the feature properly\")\n\nThe two compose: a `\u002Fgoal` session still runs through taskmaster's Stop hook,\nso worktree\u002FAI-verify safety still applies even when goal-driven.\n","# Taskmaster\n\nA stop hook that prevents the agent from stopping prematurely. When a response\nfinishes and the agent is about to stop, this hook intercepts and prompts it\nto re-examine whether all work is truly done.\n\n## How It Works\n\n1. **Agent tries to stop** — the stop hook fires.\n2. **The hook checks** for incomplete signals (pending tasks, recent errors, blind spots in infra\u002Fconfig work — see reason text in check-completion.sh).\n3. **Agent is prompted** to verify: original requests addressed, plan steps\n   completed, tasks resolved, errors fixed, no loose ends.\n4. **If work remains**, the agent continues. If truly done, it confirms and\n   the hook allows the stop on the next cycle.\n\n## Loop Protection\n\nA session-scoped counter limits continuations to **10 by default**. Set\n`TASKMASTER_MAX` environment variable to change:\n\n```bash\nexport TASKMASTER_MAX=20  # allow up to 20 continuations\nexport TASKMASTER_MAX=0   # infinite — never cap (relies on stop_hook_active check only)\n```\n\n## Setup\n\nThe hook must be registered in `~\u002F.claude\u002Fsettings.json`:\n\n```json\n{\n  \"hooks\": {\n    \"Stop\": [\n      {\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"$HOME\u002F.claude\u002Fskills\u002Ftaskmaster\u002Fhooks\u002Fcheck-completion.sh\",\n            \"timeout\": 10\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\n## Disabling\n\nTo temporarily disable, either:\n- Remove or comment out the Stop hook in `~\u002F.claude\u002Fsettings.json`\n- Set `TASKMASTER_MAX=1` to allow only one continuation check\n\n## Lighter Alternative: `\u002Fgoal` (Claude Code 2.1.139+)\n\nFor one-shot autonomous loops where you don't need taskmaster's full\nplan + task list + beads + worktree + AI-verify gating, use the built-in\n`\u002Fgoal` command instead:\n\n```\n\u002Fgoal all CI checks green and all worktrees pushed\n```\n\n`\u002Fgoal` sets a single completion condition and Claude keeps working across\nturns until it's met. Useful when:\n\n- You want a *specific* exit criterion, not \"no incomplete signals\"\n- The work is bounded (one feature, one bug, one cleanup) and beads\u002Fworktree\n  state doesn't matter\n- You want the agent to stop the moment the goal is met, even if other\n  in_progress beads exist\n\nUse **taskmaster** (this skill, always-on Stop hook) when:\n\n- Multi-step plans, multiple beads, multiple worktrees in flight\n- You want adjacent-safety gating (WORKTREE_BLOCK, AI_VERIFY_BLOCK, BEADS_BLOCK)\n- The \"done\" condition is fuzzy (\"ship the feature properly\")\n\nThe two compose: a `\u002Fgoal` session still runs through taskmaster's Stop hook,\nso worktree\u002FAI-verify safety still applies even when goal-driven.\n",{"name":5,"author":24,"version":25,"description":26,"user-invocable":27},"blader","1.0.0","Stop hook that keeps the agent working until all plans and user requests are\n100% complete. Fires when the agent tries to stop, re-examines the plan and\ntask list, and forces continuation if anything is unfinished. Prevents\npremature stopping on multi-step tasks.\n",true,"main","e7b39d448c7d905feed2b044d3ccdf60822596ab","skills\u002Ftaskmaster",0,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter","https:\u002F\u002Fgithub.com\u002Fbarkleesanders","barkleesanders.com","Stay Hungry, Stay Foolish","2026-11-06 08:47:06",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":27},[39,42,45],{"tool":40,"command":41},"npx","npx skills add barkleesanders\u002Fclaude-code-starter --skill taskmaster",{"tool":43,"command":44},"bunx","bunx skills add barkleesanders\u002Fclaude-code-starter --skill taskmaster",{"tool":46,"command":47},"pnpm","pnpm dlx skills add barkleesanders\u002Fclaude-code-starter --skill taskmaster","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Ftaskmaster\u002FSKILL.md",[50],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"hooks\u002Fcheck-completion.sh","SCRIPT","脚本",16542,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Ftaskmaster\u002Fhooks\u002Fcheck-completion.sh",[57,63,70,77,84,91],{"skillNo":58,"name":59,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7AWV75B37B6YKG7ZKGZ783F","zi-search","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fzi-search\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7AWTZA3JGK1T7V1HS543FG7","visualise","Render inline interactive visuals — SVG diagrams, HTML widgets, charts, and explainers — directly in the conversation. Use this skill whenever the user asks to visualize, diagram, chart, illustrate, or explain something visually, or when an explanation would genuinely benefit from a spatial\u002Finteractive diagram rather than text. Also triggers for: flowcharts, architecture diagrams, data visualizations, interactive explainers, comparison layouts, UI mockups, and any request containing 'show me', 'draw', 'map out', 'visualize', or 'diagram'. Even when the user doesn't explicitly ask for a visual, use this skill proactively when the topic has spatial, sequential, or systemic relationships that a diagram would clarify better than prose.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvisualise\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7AWTR056C3P9R3VS8YVM2WX","video","When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks. Also use when the user mentions 'video production,' 'AI video,' 'Remotion,' 'Hyperframes,' 'HeyGen,' 'Synthesia,' 'Veo,' 'Runway,' 'Kling,' 'Pika,' 'video generation,' 'AI avatar,' 'talking head video,' 'programmatic video,' 'video template,' 'explainer video,' 'product demo video,' 'video pipeline,' or 'make me a video.' Use this for video creation, generation, and production workflows. For video content strategy and what to post, see social-content. For paid video ad creative, see ad-creative.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvideo\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7AWTHTWBMTYZPMHHEYX3TTG","manim-video","Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric\u002Fmathematical content.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-use\u002Fskills\u002Fmanim-video\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7AWTCXDJ9NWFQW51ENM8A2Z","video-use","Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel, interviews. No presets, no menus. Ask questions, confirm the plan, execute, iterate, persist. Production-correctness rules are hard; everything else is artistic freedom.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-use\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7AWTA1D5FP895S33GHSA2G5","ui-improver","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fui-improver\u002FSKILL.md",[],[]]