[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QRA5AYC1RBFZ39GTWGS3N8":3,"skill-same:01M6QRA5AYC1RBFZ39GTWGS3N8":76},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":14,"repositoryHtmlUrl":56,"repositoryHomepageUrl":57,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M6QRA5AYC1RBFZ39GTWGS3N8","workflow-builder",null,"Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"workflow","builder","workflow builder","claude code workflow","design","judge","scripts","fresh","across","files","context","write","multi-agent","loop","pipeline","orchestrate","code","run","create","workflows","2026-11-10 10:12:30",false,"---\nname: workflow-builder\ndescription: Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.\nlicense: MIT\nmetadata:\n  inspired_by: \"https:\u002F\u002Fgithub.com\u002Fray-amjad\u002Fclaude-code-workflow-creator (Ray Amjad)\"\n  targets: \"Claude Code Workflow tool (CLAUDE_CODE_WORKFLOWS=1, \u002Fworkflows)\"\n  version: 1.0.0\n---\n\n# Workflow Builder\n\nAuthor runnable workflow scripts for Claude Code's Workflow tool: deterministic multi-agent orchestration files (`.js`) that fan work out to fresh-context sub-agents under plain JavaScript control flow. Only leaf `agent()` calls spend tokens, so the main session stays clean and the whole run is resumable.\n\n## ALWAYS start every session with intake (non-negotiable)\n\nBefore proposing or writing any workflow, run the intake. Do not skip to code.\n\n1. **Ask what kind of workflow they want.** Use this opening question set:\n   - What repeatable, multi-step task do you want to automate?\n   - What is the one unit of work a single sub-agent does once?\n   - How many units — a known list, or discovered by looping?\n   - Do later steps need *all* prior results at once, or can each item flow on its own?\n   - Does any step need structured data back (a verdict, a list, scores)?\n   - Roughly how many tokens \u002F how deep should it go?\n\n2. **If the user is vague, do NOT stall.** Run the recommendation engine to turn whatever you have into 1-2 concrete proposals, then present them *with the reasoning*:\n   ```bash\n   python scripts\u002Fworkflow_intake.py --task \"their description\" \\\n     --units unknown --stages unknown --needs-all unknown --structured unknown\n   ```\n   The engine returns a recommended topology (fan-out \u002F pipeline \u002F loop \u002F barrier \u002F judge-panel), model picks, a budget guard, and a one-line rationale per choice. Present those as \"Here's what I'd build and why\" — never ask the user to re-answer questions they already half-answered.\n\n3. **Confirm the shape with the user** (topology + phases + parallel-vs-pipeline) before writing the file. This is the only approval gate.\n\nSee [references\u002Fdecision_and_intake_guide.md](references\u002Fdecision_and_intake_guide.md) for the full question framework, the vague-input playbook, and worked recommendation examples.\n\n## Decide if a workflow is even the right tool\n\n| Scenario | Use |\n|----------|-----|\n| Single sub-agent, one task | plain Agent tool |\n| Reusable procedure, Claude picks steps dynamically | a Skill |\n| Many sub-agents in a fixed topology, deterministic + resumable | **Workflow** ✓ |\n\nWorkflows earn their cost when work is parallel or multi-stage, must be reproducible, long enough to fail halfway (so resume matters), or benefits from isolating each step in its own context window. For one-off tasks, just use Claude directly.\n\n## Build → validate → run loop\n\n1. **Scaffold** a starter from the confirmed topology:\n   ```bash\n   python scripts\u002Fscaffold_workflow.py --topology pipeline --name pr-triage \\\n     --description \"Triage open PRs\" > .claude\u002Fworkflows\u002Fpr-triage.js\n   ```\n2. **Edit** the file: `meta` block first (pure literal, first statement), then the async body using the injected globals — `agent()`, `pipeline()`, `parallel()`, `phase()`, `log()`, `budget`, `args`, `workflow()`. Full surface in [references\u002Fapi_reference.md](references\u002Fapi_reference.md); copy-paste shapes in [references\u002Forchestration_patterns.md](references\u002Forchestration_patterns.md).\n3. **Validate** before running — catches the parser-fatal mistakes:\n   ```bash\n   python scripts\u002Fvalidate_workflow.py .claude\u002Fworkflows\u002Fpr-triage.js\n   ```\n4. **Run** it: enable the feature with `export CLAUDE_CODE_WORKFLOWS=1`, save the file under `.claude\u002Fworkflows\u002F`, then use `\u002Fworkflows` to launch and watch it live. Press **P** to pause\u002Fresume, **X** to skip a sub-agent. Failed agents retry automatically.\n\n## Hard rules (validator enforces these)\n\n- `meta` is a **pure literal** and the **first statement** — no variables, spreads, template strings, or function calls inside it.\n- **No non-determinism:** `Date.now()`, `Math.random()`, argless `new Date()` break resume — pass timestamps via `args`.\n- **No filesystem \u002F Node APIs** (`require`, `fs`, `process`, network) in the orchestrator — that work belongs *inside* `agent()` prompts.\n- `parallel()` takes **thunks** (`() => agent(...)`), not bare promises. Default to `pipeline()` unless a stage needs the whole prior result set.\n- **Guard every open-ended loop** with a counter or `budget.remaining()` check — unguarded loops hit the 1000-agent cap.\n- Filter skipped\u002Ffailed agents: `results.filter(Boolean)`.\n\n## Tooling\n\n- `scripts\u002Fworkflow_intake.py` — intake recommendation engine (topology + model + budget + rationale from vague input).\n- `scripts\u002Fvalidate_workflow.py` — stdlib linter for the rules above; PASS \u002F WARN \u002F FAIL with line numbers.\n- `scripts\u002Fscaffold_workflow.py` — generate a starter `.js` for any topology.\n- `assets\u002Ftemplates\u002F` — fan-out, pipeline, loop-until-budget starters. `assets\u002Fexamples\u002F` — a complete runnable workflow.\n\nAll scripts run with `--sample` (no args) and `--help`.\n","# Workflow Builder\n\nAuthor runnable workflow scripts for Claude Code's Workflow tool: deterministic multi-agent orchestration files (`.js`) that fan work out to fresh-context sub-agents under plain JavaScript control flow. Only leaf `agent()` calls spend tokens, so the main session stays clean and the whole run is resumable.\n\n## ALWAYS start every session with intake (non-negotiable)\n\nBefore proposing or writing any workflow, run the intake. Do not skip to code.\n\n1. **Ask what kind of workflow they want.** Use this opening question set:\n   - What repeatable, multi-step task do you want to automate?\n   - What is the one unit of work a single sub-agent does once?\n   - How many units — a known list, or discovered by looping?\n   - Do later steps need *all* prior results at once, or can each item flow on its own?\n   - Does any step need structured data back (a verdict, a list, scores)?\n   - Roughly how many tokens \u002F how deep should it go?\n\n2. **If the user is vague, do NOT stall.** Run the recommendation engine to turn whatever you have into 1-2 concrete proposals, then present them *with the reasoning*:\n   ```bash\n   python scripts\u002Fworkflow_intake.py --task \"their description\" \\\n     --units unknown --stages unknown --needs-all unknown --structured unknown\n   ```\n   The engine returns a recommended topology (fan-out \u002F pipeline \u002F loop \u002F barrier \u002F judge-panel), model picks, a budget guard, and a one-line rationale per choice. Present those as \"Here's what I'd build and why\" — never ask the user to re-answer questions they already half-answered.\n\n3. **Confirm the shape with the user** (topology + phases + parallel-vs-pipeline) before writing the file. This is the only approval gate.\n\nSee [references\u002Fdecision_and_intake_guide.md](references\u002Fdecision_and_intake_guide.md) for the full question framework, the vague-input playbook, and worked recommendation examples.\n\n## Decide if a workflow is even the right tool\n\n| Scenario | Use |\n|----------|-----|\n| Single sub-agent, one task | plain Agent tool |\n| Reusable procedure, Claude picks steps dynamically | a Skill |\n| Many sub-agents in a fixed topology, deterministic + resumable | **Workflow** ✓ |\n\nWorkflows earn their cost when work is parallel or multi-stage, must be reproducible, long enough to fail halfway (so resume matters), or benefits from isolating each step in its own context window. For one-off tasks, just use Claude directly.\n\n## Build → validate → run loop\n\n1. **Scaffold** a starter from the confirmed topology:\n   ```bash\n   python scripts\u002Fscaffold_workflow.py --topology pipeline --name pr-triage \\\n     --description \"Triage open PRs\" > .claude\u002Fworkflows\u002Fpr-triage.js\n   ```\n2. **Edit** the file: `meta` block first (pure literal, first statement), then the async body using the injected globals — `agent()`, `pipeline()`, `parallel()`, `phase()`, `log()`, `budget`, `args`, `workflow()`. Full surface in [references\u002Fapi_reference.md](references\u002Fapi_reference.md); copy-paste shapes in [references\u002Forchestration_patterns.md](references\u002Forchestration_patterns.md).\n3. **Validate** before running — catches the parser-fatal mistakes:\n   ```bash\n   python scripts\u002Fvalidate_workflow.py .claude\u002Fworkflows\u002Fpr-triage.js\n   ```\n4. **Run** it: enable the feature with `export CLAUDE_CODE_WORKFLOWS=1`, save the file under `.claude\u002Fworkflows\u002F`, then use `\u002Fworkflows` to launch and watch it live. Press **P** to pause\u002Fresume, **X** to skip a sub-agent. Failed agents retry automatically.\n\n## Hard rules (validator enforces these)\n\n- `meta` is a **pure literal** and the **first statement** — no variables, spreads, template strings, or function calls inside it.\n- **No non-determinism:** `Date.now()`, `Math.random()`, argless `new Date()` break resume — pass timestamps via `args`.\n- **No filesystem \u002F Node APIs** (`require`, `fs`, `process`, network) in the orchestrator — that work belongs *inside* `agent()` prompts.\n- `parallel()` takes **thunks** (`() => agent(...)`), not bare promises. Default to `pipeline()` unless a stage needs the whole prior result set.\n- **Guard every open-ended loop** with a counter or `budget.remaining()` check — unguarded loops hit the 1000-agent cap.\n- Filter skipped\u002Ffailed agents: `results.filter(Boolean)`.\n\n## Tooling\n\n- `scripts\u002Fworkflow_intake.py` — intake recommendation engine (topology + model + budget + rationale from vague input).\n- `scripts\u002Fvalidate_workflow.py` — stdlib linter for the rules above; PASS \u002F WARN \u002F FAIL with line numbers.\n- `scripts\u002Fscaffold_workflow.py` — generate a starter `.js` for any topology.\n- `assets\u002Ftemplates\u002F` — fan-out, pipeline, loop-until-budget starters. `assets\u002Fexamples\u002F` — a complete runnable workflow.\n\nAll scripts run with `--sample` (no args) and `--help`.\n",{"name":5,"license":15,"metadata":49,"description":7},{"targets":50,"version":51,"inspired_by":52},"Claude Code Workflow tool (CLAUDE_CODE_WORKFLOWS=1, \u002Fworkflows)","1.0.0","https:\u002F\u002Fgithub.com\u002Fray-amjad\u002Fclaude-code-workflow-creator (Ray Amjad)","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fworkflow-builder","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6","https:\u002F\u002Fdisha6.6.thenitishkr.in\u002F","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh","www.thenitishkr","thenitishkr | AI • Cyber-security • Research\r\n","2026-11-08 03:33:25",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill workflow-builder",{"tool":68,"command":69},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill workflow-builder",{"tool":71,"command":72},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill workflow-builder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",true,[],[77,106,130,154,178,202],{"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":86,"publishedAt":44},"01M6QRD07D4TGNDK6VJ4EHF8BV","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[87,88,89,90,91,92,93,94,95,96,33,97,98,99,100,101,102,103,104,105],"youtube full","youtube","full","transcript","search","monitoring","data","Video","Audio","list","do","get","age","trigger","URL","for","browsing","request","youtube transcripts",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":44},"01M6QRCJ3112VYPA97YG7KGMC2","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[113,114,115,116,91,117,118,119,120,121,122,123,35,124,125,126,127,128,129,102],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","strategy","use","platform","grow","posting","competitive",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":137,"publishedAt":44},"01M6QRBN3EHQNJY42RERP7A149","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[136],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[138,35,139,42,140,141,142,143,125,144,145,53,146,147,148,149,150,151,152,153],"write a skill","github","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":44},"01M6QRB6G8P33PNGAF9Y69EJ9T","wrap-up","Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained .\u002Fmy-agent\u002Fagent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[161,162,163,164,165,41,166,167,168,125,169,97,170,171,172,173,174,175,176,177],"wrap up","up","wrap","gemini","deployment","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":44},"01M6QR7QMCZESKQA0ERW1E657M","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[185,186,187,188,189,190,191,192,193,37,194,195,196,197,198,199,98,200,201,177],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","team","projects","project-management","scanner","conversation","back","project","sprint","cadence",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":216,"publishedAt":44},"01M6QR79MMH2TGP4TMF4FR7TJR","webinar-marketing","When the user wants to plan, promote, run, or improve a webinar or virtual event to generate and convert demand. Use when the user mentions 'webinar,' 'virtual event,' 'online event,' 'live demo,' 'virtual summit,' 'workshop,' 'masterclass,' 'fireside chat,' 'roundtable,' 'registration funnel,' 'show-up rate,' 'attendance rate,' 'webinar promotion,' 'webinar follow-up,' or 'on-demand webinar.' Also use when they have a webinar that isn't converting — low registrations, low show-up, or attendees who don't buy — and want to diagnose and fix it. Covers the full funnel: registration, promotion, show-up, live engagement, live-to-close, and post-event nurture. Distinct from launch-strategy (full product launches) and email-sequence (lifecycle nurture) — this is the end-to-end webinar\u002Fevent motion. NOT for in-person field events logistics, and NOT for generic lifecycle email (use email-sequence).","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwebinar-marketing\u002FSKILL.md",[208,211],{"categoryNo":209,"categoryName":210,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000019","营销推广",{"categoryNo":212,"categoryName":213,"taxonomyType":214,"taxonomyTypeDesc":215},"01JBSEEDCAT000000000000035","市场营销","PROFESSION","适用职业",[217,218,219,41,220,221,222,119,223,224,162,225,89,226,227,228,172,229,230,231],"marketing","webinar marketing","generate","product","promote","improve","virtual","fix","show","live","end","events","follow-up","sequence","rate"]