[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JQDC1H3D9TKC7K18MX2RX":3,"skill-same:01M71JQDC1H3D9TKC7K18MX2RX":68},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":5,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M71JQDC1H3D9TKC7K18MX2RX","swarm",null,"Fan out a task across N independent workers, drain every wave, and return one evidenced report. Use when the user asks to swarm, parallelize, race approaches, run a gauntlet, divide exhaustive coverage, or when `henry-mode` reaches a settled parallel-work stage.","caezium\u002Fskills","caezium","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113233555?v=4","01M71JB77ZPBAWEK009Y2W8BP7","Henry Zhang","01M71JB792NVXCWSYD27HQ0964",3,"MIT","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fswarm\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fswarm\u002FSKILL.md",[],[5,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"use","across","task","user","one","fan out","stage","when","workers","mode","report","run","work","parallel","drain","coverage","2026-11-10 10:12:30",false,"---\nname: swarm\ndescription: Fan out a task across N independent workers, drain every wave, and return one evidenced report. Use when the user asks to swarm, parallelize, race approaches, run a gauntlet, divide exhaustive coverage, or when `henry-mode` reaches a settled parallel-work stage.\n---\n\n# Swarm\n\nFan out a task as coverage slices, identical race arms, or a deliberate mixture. The coordinator owns framing, writable boundaries, aggregation, and the final judgment.\n\n## Harness availability\n\n| Harness | Worker mechanism | Drain \u002F follow-up | Fallback |\n|---|---|---|---|\n| Cursor | Available Task\u002Fsubagent calls; cloud workers only when explicitly supported | Native task results | Run local workers or sequential slices |\n| Claude Code | Available Agent\u002FTask calls, optionally in background | Native result\u002Fwait mechanism | Sequential slices |\n| Codex \u002F T3 | `spawn_agent` | `wait_agent`; use `followup_task` for another bounded turn | Run waves within the advertised slot limit, then sequential slices |\n| No delegation tool | None | None | Execute every slice sequentially with the same brief and schema |\n\nInherit the parent model by default. Use model overrides only when the user requests a model race or the harness exposes valid choices. Never invent aliases. N is total workers, not simultaneous slots; run waves until all N have a terminal result.\n\n## Frame\n\n1. State the done predicate and final artifact.\n2. Choose `coverage`, `race`, or `mixed`. For a race, declare `first-pass`, `rank-all`, or `best-of` before launch.\n3. Set N from the user's request or the number of independent slices.\n4. Give every writing worker an exclusive directory, worktree, branch, or file set. Keep the shared contract outside worker write scopes.\n5. Track four phases with the harness's plan\u002Ftodo feature when available: frame, fan out, aggregate, report.\n\n## Fan out\n\nLaunch as many workers together as the harness permits. Every brief must stand alone and include:\n\n- goal and exact slice\u002Frace arm;\n- read and write scope, including do-not-touch fences;\n- verification command or observable predicate;\n- required report schema: `PASS`, `ISSUES`, or `BLOCKED`, followed by artifact paths and evidence.\n\nIf a worker drops out, retry only when doing so is safe and useful; otherwise continue and record the gap. Never let two workers edit the same mutable target concurrently.\n\n## Aggregate\n\nDrain every launched worker before concluding. Inspect artifacts rather than trusting summaries. Coverage requires a terminal result for every slice; races use the selection rule declared up front. Deduplicate findings, surface disagreements, and keep raw worker dumps out of the main thread.\n\n## Report\n\nReturn one compact table with slice\u002Farm, status, evidence, and selected result; then list issues, disagreements, gaps\u002Fdropouts, and the race rule. A swarm is complete only when every requested slice is accounted for.\n\n\u003C!-- Adapted from poteto\u002Fpstack swarm, MIT License, Lauren Tan, cursor\u002Fplugins@51a96e0. -->\n","# Swarm\n\nFan out a task as coverage slices, identical race arms, or a deliberate mixture. The coordinator owns framing, writable boundaries, aggregation, and the final judgment.\n\n## Harness availability\n\n| Harness | Worker mechanism | Drain \u002F follow-up | Fallback |\n|---|---|---|---|\n| Cursor | Available Task\u002Fsubagent calls; cloud workers only when explicitly supported | Native task results | Run local workers or sequential slices |\n| Claude Code | Available Agent\u002FTask calls, optionally in background | Native result\u002Fwait mechanism | Sequential slices |\n| Codex \u002F T3 | `spawn_agent` | `wait_agent`; use `followup_task` for another bounded turn | Run waves within the advertised slot limit, then sequential slices |\n| No delegation tool | None | None | Execute every slice sequentially with the same brief and schema |\n\nInherit the parent model by default. Use model overrides only when the user requests a model race or the harness exposes valid choices. Never invent aliases. N is total workers, not simultaneous slots; run waves until all N have a terminal result.\n\n## Frame\n\n1. State the done predicate and final artifact.\n2. Choose `coverage`, `race`, or `mixed`. For a race, declare `first-pass`, `rank-all`, or `best-of` before launch.\n3. Set N from the user's request or the number of independent slices.\n4. Give every writing worker an exclusive directory, worktree, branch, or file set. Keep the shared contract outside worker write scopes.\n5. Track four phases with the harness's plan\u002Ftodo feature when available: frame, fan out, aggregate, report.\n\n## Fan out\n\nLaunch as many workers together as the harness permits. Every brief must stand alone and include:\n\n- goal and exact slice\u002Frace arm;\n- read and write scope, including do-not-touch fences;\n- verification command or observable predicate;\n- required report schema: `PASS`, `ISSUES`, or `BLOCKED`, followed by artifact paths and evidence.\n\nIf a worker drops out, retry only when doing so is safe and useful; otherwise continue and record the gap. Never let two workers edit the same mutable target concurrently.\n\n## Aggregate\n\nDrain every launched worker before concluding. Inspect artifacts rather than trusting summaries. Coverage requires a terminal result for every slice; races use the selection rule declared up front. Deduplicate findings, surface disagreements, and keep raw worker dumps out of the main thread.\n\n## Report\n\nReturn one compact table with slice\u002Farm, status, evidence, and selected result; then list issues, disagreements, gaps\u002Fdropouts, and the race rule. A swarm is complete only when every requested slice is accounted for.\n\n\u003C!-- Adapted from poteto\u002Fpstack swarm, MIT License, Lauren Tan, cursor\u002Fplugins@51a96e0. -->\n",{"name":5,"description":7},"main","6ef866230c1ba3459fd08fc65141dfd37fffd41a",0,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills","https:\u002F\u002Fskills.henryzh.dev","https:\u002F\u002Fgithub.com\u002Fcaezium","henryzh.dev","quant, data science, full-stack, robotics.\r\nbuilding cool stuff","2026-08-24 19:21:44",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add caezium\u002Fskills --skill swarm",{"tool":56,"command":57},"bunx","bunx skills add caezium\u002Fskills --skill swarm",{"tool":59,"command":60},"pnpm","pnpm dlx skills add caezium\u002Fskills --skill swarm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fswarm\u002FSKILL.md",true,[64],{"path":65,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":16},"LICENSE","许可证",1067,[69,91,118,136,156,177],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":85,"publishedAt":36},"01M71JT4RYCAS18RF6003YYR1D","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FSKILL.md",[75,80],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":81,"categoryName":82,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[86,87,88,89,20,90,27],"writing for agents","for","writing","editing","documents",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":100,"publishedAt":36},"01M71JT0GES4AZ5ADH8EADNN1Z","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwrangler\u002FSKILL.md",[97],{"categoryNo":98,"categoryName":99,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000010","后端与接口",[93,101,102,103,104,105,106,107,108,109,110,111,112,87,113,114,115,28,116,117],"cloudflare","d1","knowledge","workflows","cli","secrets","commands","syntax","cloudflare workers","r2","queues","running","containers","correct","load","best practices","store",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":36},"01M71JSWX4R203M32K9A18AAW8","workers-best-practices","Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fworkers-best-practices\u002FSKILL.md",[],[125,28,116,126,127,128,87,101,129,103,130,93,88,115,27,131,132,133,134,135],"workers best practices","observability","reviews","promises","worker","new","code","common","streaming","state","anti-patterns",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":36},"01M71JST6P88MXGT2MWDTPJGEG","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwizard\u002FSKILL.md",[],[138,112,143,87,144,145,146,147,20,148,27,149,24,150,151,152,153,154,155,106],"setting","up","ci","provisioning infrastructure","only","invoke","Bash","interactive","can","credentials","dashboard","generate","human",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":160,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":36},"01M71JSQ95S7BQ61DAPN95X2W4","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available evidence sources, searches each relevant category, and returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FSKILL.md",[],[158,164,165,166,167,87,168,169,20,170,32,171,172,173,174,175,176],"sources","thresholds","evidence","relevant","runtime","design","decisions","how","behavior","read","data","rationale","returns",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":186,"publishedAt":36},"01M71JSMHFVSH8HK8GXN6YAX6J","week-prep","Generate a briefing with calendar, tasks, and attention flags. Use for \"week prep\", \"briefing\", or \"what's on this week\".","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fweek-prep\u002FSKILL.md",[183],{"categoryNo":184,"categoryName":185,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000023","Skill与智能体开发",[187,188,189,190,191,87,192,193,194,195,20,149,196,197,198,154,199,173,200,201],"week prep","prep","deep","attention","get","search","messages","briefing","MCP","tasks","with","slack","calendar","flags","grep"]