[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F5N7D3ABZXZPWHWQBZYAFM":3,"skill-same:01M7F5N7D3ABZXZPWHWQBZYAFM":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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7F5N7D3ABZXZPWHWQBZYAFM","agents-workflows",null,"Guides SuperAGI agent creation, workflow selection, prompt parsing, task queues, scheduling, and Celery execution loops.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsuper-agi\u002Fsub-skills\u002Fagents-workflows\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: agents-workflows\ndescription: \"Guides SuperAGI agent creation, workflow selection, prompt\n  parsing, task queues, scheduling, and Celery execution loops.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# SuperAGI Agents and Workflows\n\nUse this sub-skill when the task is about how SuperAGI agents are prompted,\nselected, queued, scheduled, executed, paused, resumed, or advanced through\nworkflow steps.\n\n## Read First\n\n- [references\u002Fworkflows.md](references\u002Fworkflows.md) for workflow types, seed\n  names, and execution flow.\n- [references\u002Fprompt-and-output-parsing.md](references\u002Fprompt-and-output-parsing.md)\n  for prompt builders, parser signatures, and output-shape expectations.\n- [references\u002Fexecution-loop.md](references\u002Fexecution-loop.md) for the agent,\n  job, and Celery loop from config to execution step.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for parser,\n  tool-selection, queue, permission, and scheduling failures.\n- [scripts\u002Fvalidate_agent_payload.py](scripts\u002Fvalidate_agent_payload.py) for a\n  safe structural check of agent\u002Frun payloads.\n\n## Core Concepts\n\n- **Goal-based workflow:** a single-step prompt loop that keeps selecting the\n  next tool until completion.\n- **Dynamic task workflow:** a task-analysis and task-prioritization loop that\n  revisits the task queue.\n- **Fixed task workflow:** a task queue that follows a fixed schedule of\n  initialization and queue steps.\n- **Tool workflow steps:** tool steps, wait steps, task-queue steps, and\n  permission-gated steps are all represented in the workflow models.\n- **Execution loop:** `superagi.worker` and `superagi.jobs.agent_executor`\n  coordinate scheduled agents, waiting workflows, resource summaries, and\n  webhook callbacks.\n\n## Typical Questions This Sub-skill Answers\n\n- Which workflow name should I assign to an agent template?\n- Why did the agent choose the wrong tool or produce invalid JSON?\n- Why is a task queue empty, repeated, or not advancing?\n- How do permission checkpoints and wait steps change execution?\n- Which Celery task or workflow seed owns a given behavior?\n\n## Safe Workflow\n\n1. Route by workflow family: agent templates and workflow names belong here,\n   not in API or toolkit sub-skills.\n2. Read prompt and parser references before changing or validating outputs.\n3. If the user provides a payload, use the validator script for a structural\n   check before thinking about execution.\n4. For real execution, remember that workflow code depends on Redis, a database,\n   and in many cases an LLM provider. Only run live execution when authorized.\n\n## Boundary Notes\n\n- HTTP route and model schema questions belong to `api-service`.\n- Tool implementation and toolkit registration belong to `toolkits-integrations`.\n- Provider, resource, and vector-store setup that a workflow merely consumes\n  belongs to `models-resources-vector`.\n","# SuperAGI Agents and Workflows\n\nUse this sub-skill when the task is about how SuperAGI agents are prompted,\nselected, queued, scheduled, executed, paused, resumed, or advanced through\nworkflow steps.\n\n## Read First\n\n- [references\u002Fworkflows.md](references\u002Fworkflows.md) for workflow types, seed\n  names, and execution flow.\n- [references\u002Fprompt-and-output-parsing.md](references\u002Fprompt-and-output-parsing.md)\n  for prompt builders, parser signatures, and output-shape expectations.\n- [references\u002Fexecution-loop.md](references\u002Fexecution-loop.md) for the agent,\n  job, and Celery loop from config to execution step.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for parser,\n  tool-selection, queue, permission, and scheduling failures.\n- [scripts\u002Fvalidate_agent_payload.py](scripts\u002Fvalidate_agent_payload.py) for a\n  safe structural check of agent\u002Frun payloads.\n\n## Core Concepts\n\n- **Goal-based workflow:** a single-step prompt loop that keeps selecting the\n  next tool until completion.\n- **Dynamic task workflow:** a task-analysis and task-prioritization loop that\n  revisits the task queue.\n- **Fixed task workflow:** a task queue that follows a fixed schedule of\n  initialization and queue steps.\n- **Tool workflow steps:** tool steps, wait steps, task-queue steps, and\n  permission-gated steps are all represented in the workflow models.\n- **Execution loop:** `superagi.worker` and `superagi.jobs.agent_executor`\n  coordinate scheduled agents, waiting workflows, resource summaries, and\n  webhook callbacks.\n\n## Typical Questions This Sub-skill Answers\n\n- Which workflow name should I assign to an agent template?\n- Why did the agent choose the wrong tool or produce invalid JSON?\n- Why is a task queue empty, repeated, or not advancing?\n- How do permission checkpoints and wait steps change execution?\n- Which Celery task or workflow seed owns a given behavior?\n\n## Safe Workflow\n\n1. Route by workflow family: agent templates and workflow names belong here,\n   not in API or toolkit sub-skills.\n2. Read prompt and parser references before changing or validating outputs.\n3. If the user provides a payload, use the validator script for a structural\n   check before thinking about execution.\n4. For real execution, remember that workflow code depends on Redis, a database,\n   and in many cases an LLM provider. Only run live execution when authorized.\n\n## Boundary Notes\n\n- HTTP route and model schema questions belong to `api-service`.\n- Tool implementation and toolkit registration belong to `toolkits-integrations`.\n- Provider, resource, and vector-store setup that a workflow merely consumes\n  belongs to `models-resources-vector`.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fsuper-agi\u002Fsub-skills\u002Fagents-workflows",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill agents-workflows",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill agents-workflows",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill agents-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsuper-agi\u002Fsub-skills\u002Fagents-workflows\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fexecution-loop.md","REFERENCE","参考文档",1808,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsuper-agi\u002Fsub-skills\u002Fagents-workflows\u002Freferences\u002Fexecution-loop.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fprompt-and-output-parsing.md",1928,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsuper-agi\u002Fsub-skills\u002Fagents-workflows\u002Freferences\u002Fprompt-and-output-parsing.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Ftroubleshooting.md",1441,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsuper-agi\u002Fsub-skills\u002Fagents-workflows\u002Freferences\u002Ftroubleshooting.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fworkflows.md",2028,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsuper-agi\u002Fsub-skills\u002Fagents-workflows\u002Freferences\u002Fworkflows.md",[67,74,79,86,93,100],{"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},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":75,"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":76,"categories":77,"keywords":78,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]