[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7574T5WQT8KSW7YYPQDCZ7E":3,"skill-same:01M7574T5WQT8KSW7YYPQDCZ7E":66},{"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":38,"commitSha":39,"skillDirectory":40,"forksCount":14,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M7574T5WQT8KSW7YYPQDCZ7E","hermes-kanban-swarm",null,"Orchestrate, configure, and execute multi-agent workflows (Swarms) using Hermes Kanban boards and profiles.","SatangThevalue\u002Fai-skills","SatangThevalue","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F17944930?v=4","01M756VHQQ58XSM5PDS03W79VY","Sa-Tang","01M756VHRNYXRY7HM230S4YHVV",0,"MIT","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-ai-agents\u002Fhermes-kanban-swarm\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: hermes-kanban-swarm\ndescription: \"Orchestrate, configure, and execute multi-agent workflows (Swarms) using Hermes Kanban boards and profiles.\"\nversion: 1.0.0\nauthor: Tonthong\nlicense: MIT\nplatforms: [linux, macos]\nmetadata:\n  hermes:\n    tags: [hermes, multi-agent, swarm, kanban, automation, orchestration]\n---\n\n# Hermes Kanban Swarm Workflows\n\nThis skill provides the standard operating procedure for configuring, deploying, and managing multi-agent swarms using Hermes Agent's native Kanban system and named profiles. \n\nUse this skill when:\n- Setting up parallel or pipelined multi-agent systems (e.g., Researcher -> Writer -> Reviewer).\n- Organizing long-running collaborative tasks that must survive restarts or require human-in-the-loop review.\n- Troubleshooting stuck worker tasks, dispatcher routing, or profile configuration.\n\n## 1. Setup & Profile Creation\n\nTo run a multi-agent swarm, you must first define the specialized roles as independent Hermes profiles.\n\n### Step 1: Create Profiles\nCreate a profile for each role. Pass `--description` (used by the decomposer for routing) and `--clone` (to copy API keys, `.env`, configuration, and custom skills while keeping session history isolated).\n```bash\nhermes profile create researcher --description \"Researches topics using web search and extraction tools\" --clone\nhermes profile create writer --description \"Drafts and synthesizes research into structured markdown reports\" --clone\nhermes profile create reviewer --description \"Reviews written text for technical accuracy and formatting compliance\" --clone\n```\n\n### Step 2: Verify Profiles\nVerify that the profiles are successfully created and mapped to command aliases:\n```bash\nhermes profile list\n```\nEach profile has a command alias at `~\u002F.local\u002Fbin\u002F\u003Cprofile>` (e.g., `researcher chat`, `writer setup`).\n\n---\n\n## 2. Instantiating a Swarm\n\nHermes Kanban Swarms run on a shared SQLite database (`~\u002F.hermes\u002Fkanban.db` for the default board).\n\n### Creating a Swarm (CLI)\nInitialize a Swarm v1 graph (Parallel Workers -> Verifier -> Synthesizer) with the `hermes kanban swarm` command:\n```bash\nhermes kanban swarm \"Research and write a report on the current status of Swarm AI Agent in 2026\" \\\n  --worker researcher:\"Research Swarm AI Agents status\" \\\n  --verifier reviewer \\\n  --synthesizer writer\n```\n\nThis creates a task graph where:\n- A root card (e.g. `t_19b6c277`) is marked `done` immediately to serve as the shared blackboard.\n- Worker tasks (e.g. `t_6a25ac43`) are assigned to their respective profiles and set to `ready`.\n- The verifier task is set to `todo` and blocked until the workers complete.\n- The synthesizer task is set to `todo` and blocked until the verifier passes.\n\n---\n\n## 3. Worker Execution & Dispatching\n\nBy default, tasks in the `ready` state sit in the queue until claimed by a worker lane.\n\n### Manual Dispatch (Forced Tick)\nTo run or test the dispatcher immediately instead of waiting for the gateway daemon:\n```bash\nhermes kanban dispatch\n```\nThe dispatcher will automatically claim the task, create an isolated workspace under `~\u002F.hermes\u002Fkanban\u002Fworkspaces\u002F\u003Ctask_id>`, and spawn the corresponding profile process (e.g., `hermes -p researcher chat -q ...`).\n\n### Monitoring & Auditing\nTrack execution progress and trace logs:\n```bash\n# View active tasks and their state\nhermes kanban list\n\n# Check attempt history, run count, and elapsed time for a task\nhermes kanban runs \u003Ctask_id>\n\n# Display live logs or stdout of the active worker process\nhermes kanban log \u003Ctask_id>\n```\n\n---\n\n## 4. Key Developer Invariants & Pitfalls\n\n### Ephemeral Workspaces\nBy default, tasks use `scratch` workspaces located at `~\u002F.hermes\u002Fkanban\u002Fworkspaces\u002F\u003Ctask_id>`. \n- **Pitfall:** This directory is **wiped immediately** upon task completion. \n- **Fix:** If workers write files that must persist, they must copy them to a shared host path or write them directly to a directory workspace (e.g., `dir:\u002Fabsolute\u002Fpath\u002Fto\u002Fproject`) instead of scratch space. Alternatively, log paths can be recorded in comments or metadata.\n\n### Stalled Tasks\n- **Symptom:** Tasks remain in the `ready` state indefinitely.\n- **Cause:** The dispatcher is not running.\n- **Fix:** Run `hermes gateway start` (if configured to run gateway-dispatch) or invoke manual ticks with `hermes kanban dispatch`.\n\n### Shared Bot Token Conflicts\n- **Pitfall:** If multiple profiles attempt to launch the gateway (`hermes gateway run\u002Fstart`) using the same Telegram or Discord bot token, the processes will block each other.\n- **Fix:** Run only one main gateway dispatcher. Let worker lanes execute as command-line agents (`hermes -p \u003Cprofile> chat -q`) instead of standalone gateway bots.\n\n---\n\n## 5. External Task Synchronization (Google Tasks & Mobile Tracking)\n\nHermes Kanban tasks can be automatically mirrored into Google Tasks, organized by profile\u002Fassignee for real-time mobile tracking and notifications.\n\n- **Flow Script**: `zero-touch-prefect\u002Fkanban_google_tasks_sync.py`\n- **Orchestration**: Runs as a Prefect 2.x Flow logging to `http:\u002F\u002F100.115.66.121:4200`\n- **Schedule**: Every 1 minute via crontab and lockfile wrapper (`~\u002F.hermes\u002Fscripts\u002Frun_kanban_google_tasks_sync.sh`).\n- **Detailed Reference**: See `references\u002Fgoogle_tasks_prefect_sync.md`.\n\n","# Hermes Kanban Swarm Workflows\n\nThis skill provides the standard operating procedure for configuring, deploying, and managing multi-agent swarms using Hermes Agent's native Kanban system and named profiles. \n\nUse this skill when:\n- Setting up parallel or pipelined multi-agent systems (e.g., Researcher -> Writer -> Reviewer).\n- Organizing long-running collaborative tasks that must survive restarts or require human-in-the-loop review.\n- Troubleshooting stuck worker tasks, dispatcher routing, or profile configuration.\n\n## 1. Setup & Profile Creation\n\nTo run a multi-agent swarm, you must first define the specialized roles as independent Hermes profiles.\n\n### Step 1: Create Profiles\nCreate a profile for each role. Pass `--description` (used by the decomposer for routing) and `--clone` (to copy API keys, `.env`, configuration, and custom skills while keeping session history isolated).\n```bash\nhermes profile create researcher --description \"Researches topics using web search and extraction tools\" --clone\nhermes profile create writer --description \"Drafts and synthesizes research into structured markdown reports\" --clone\nhermes profile create reviewer --description \"Reviews written text for technical accuracy and formatting compliance\" --clone\n```\n\n### Step 2: Verify Profiles\nVerify that the profiles are successfully created and mapped to command aliases:\n```bash\nhermes profile list\n```\nEach profile has a command alias at `~\u002F.local\u002Fbin\u002F\u003Cprofile>` (e.g., `researcher chat`, `writer setup`).\n\n---\n\n## 2. Instantiating a Swarm\n\nHermes Kanban Swarms run on a shared SQLite database (`~\u002F.hermes\u002Fkanban.db` for the default board).\n\n### Creating a Swarm (CLI)\nInitialize a Swarm v1 graph (Parallel Workers -> Verifier -> Synthesizer) with the `hermes kanban swarm` command:\n```bash\nhermes kanban swarm \"Research and write a report on the current status of Swarm AI Agent in 2026\" \\\n  --worker researcher:\"Research Swarm AI Agents status\" \\\n  --verifier reviewer \\\n  --synthesizer writer\n```\n\nThis creates a task graph where:\n- A root card (e.g. `t_19b6c277`) is marked `done` immediately to serve as the shared blackboard.\n- Worker tasks (e.g. `t_6a25ac43`) are assigned to their respective profiles and set to `ready`.\n- The verifier task is set to `todo` and blocked until the workers complete.\n- The synthesizer task is set to `todo` and blocked until the verifier passes.\n\n---\n\n## 3. Worker Execution & Dispatching\n\nBy default, tasks in the `ready` state sit in the queue until claimed by a worker lane.\n\n### Manual Dispatch (Forced Tick)\nTo run or test the dispatcher immediately instead of waiting for the gateway daemon:\n```bash\nhermes kanban dispatch\n```\nThe dispatcher will automatically claim the task, create an isolated workspace under `~\u002F.hermes\u002Fkanban\u002Fworkspaces\u002F\u003Ctask_id>`, and spawn the corresponding profile process (e.g., `hermes -p researcher chat -q ...`).\n\n### Monitoring & Auditing\nTrack execution progress and trace logs:\n```bash\n# View active tasks and their state\nhermes kanban list\n\n# Check attempt history, run count, and elapsed time for a task\nhermes kanban runs \u003Ctask_id>\n\n# Display live logs or stdout of the active worker process\nhermes kanban log \u003Ctask_id>\n```\n\n---\n\n## 4. Key Developer Invariants & Pitfalls\n\n### Ephemeral Workspaces\nBy default, tasks use `scratch` workspaces located at `~\u002F.hermes\u002Fkanban\u002Fworkspaces\u002F\u003Ctask_id>`. \n- **Pitfall:** This directory is **wiped immediately** upon task completion. \n- **Fix:** If workers write files that must persist, they must copy them to a shared host path or write them directly to a directory workspace (e.g., `dir:\u002Fabsolute\u002Fpath\u002Fto\u002Fproject`) instead of scratch space. Alternatively, log paths can be recorded in comments or metadata.\n\n### Stalled Tasks\n- **Symptom:** Tasks remain in the `ready` state indefinitely.\n- **Cause:** The dispatcher is not running.\n- **Fix:** Run `hermes gateway start` (if configured to run gateway-dispatch) or invoke manual ticks with `hermes kanban dispatch`.\n\n### Shared Bot Token Conflicts\n- **Pitfall:** If multiple profiles attempt to launch the gateway (`hermes gateway run\u002Fstart`) using the same Telegram or Discord bot token, the processes will block each other.\n- **Fix:** Run only one main gateway dispatcher. Let worker lanes execute as command-line agents (`hermes -p \u003Cprofile> chat -q`) instead of standalone gateway bots.\n\n---\n\n## 5. External Task Synchronization (Google Tasks & Mobile Tracking)\n\nHermes Kanban tasks can be automatically mirrored into Google Tasks, organized by profile\u002Fassignee for real-time mobile tracking and notifications.\n\n- **Flow Script**: `zero-touch-prefect\u002Fkanban_google_tasks_sync.py`\n- **Orchestration**: Runs as a Prefect 2.x Flow logging to `http:\u002F\u002F100.115.66.121:4200`\n- **Schedule**: Every 1 minute via crontab and lockfile wrapper (`~\u002F.hermes\u002Fscripts\u002Frun_kanban_google_tasks_sync.sh`).\n- **Detailed Reference**: See `references\u002Fgoogle_tasks_prefect_sync.md`.\n\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":35,"description":7},"Tonthong","1.0.0",{"hermes":27},{"tags":28},[29,30,31,32,33,34],"hermes","multi-agent","swarm","kanban","automation","orchestration",[36,37],"linux","macos","main","236825fbf4e5956a8cd2b0bf843494f0a5dfaf04","skills\u002Fautonomous-ai-agents\u002Fhermes-kanban-swarm","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills","https:\u002F\u002Fgithub.com\u002FSatangThevalue","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fsatangthevalue\u002F","Hi, I'm Sa-Tang. 🖐️🖐️🖐️\r\nThanks for following.\r\nสวัสดีครับ สตังค์ครับผม\r\nขอบคุณหรับการติดตามครับ","2026-10-10 12:10:40",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add SatangThevalue\u002Fai-skills --skill hermes-kanban-swarm",{"tool":52,"command":53},"bunx","bunx skills add SatangThevalue\u002Fai-skills --skill hermes-kanban-swarm",{"tool":55,"command":56},"pnpm","pnpm dlx skills add SatangThevalue\u002Fai-skills --skill hermes-kanban-swarm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-ai-agents\u002Fhermes-kanban-swarm\u002FSKILL.md",true,[60],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fgoogle_tasks_prefect_sync.md","REFERENCE","参考文档",2511,"https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-ai-agents\u002Fhermes-kanban-swarm\u002Freferences\u002Fgoogle_tasks_prefect_sync.md",[67,74,81,88,95,102],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M76TQY0W54NCMRVE9HB8MMTA","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M76TNN9AYY91KD4DT415K1FF","subagent-driven-development","Execute plans via delegate_task subagents (2-stage review).","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fsubagent-driven-development\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M76TME6SXP9SYJZCXX5FFZHR","react-composition-2026","Teaches modern React composition patterns for 2025\u002F2026. Use when designing component APIs, building shared UI libraries, or refactoring prop-heavy components.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Freact-composition-2026\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M76TMAR2D5G9BKZWGEFJKWT2","react-2026","Provides a comprehensive guide to the modern React 2026 stack. Use when starting a new React project or modernizing an existing one with current frameworks, build tools, routing, state management, or AI integration.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Freact-2026\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M76TM2FA8ZFZR1S6ZM34WFFK","plan","Plan mode: write markdown plan to .hermes\u002Fplans\u002F, no exec.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fplan\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M76TJVNAWDZ7DYQK3ZS0X09J","hermes-s6-container-supervision","Modify, debug, or extend the s6-overlay supervision tree inside the Hermes Agent Docker image — adding new services, debugging profile gateways, understanding the Architecture B main-program pattern.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fhermes-s6-container-supervision\u002FSKILL.md",[],[]]