[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EZ62PCXX75F2KZFJSWJE9T":3,"skill-same:01M7EZ62PCXX75F2KZFJSWJE9T":50},{"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":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7EZ62PCXX75F2KZFJSWJE9T","discover-agentic",null,"Automatically discover agentic workflow skills when building AI agents, implementing tool use patterns, managing context windows, decomposing complex tasks, or designing multi-step autonomous workflows. Activates for agentic AI development.","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\u002Fdiscover-agentic\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: discover-agentic\ndescription: Automatically discover agentic workflow skills when building AI agents, implementing tool use patterns, managing context windows, decomposing complex tasks, or designing multi-step autonomous workflows. Activates for agentic AI development.\nlicense: MIT\nmetadata:\n  author: rand\n  version: \"4.0\"\ncompatibility: Designed for Claude Code. Compatible with any agent supporting the Agent Skills format.\n---\n\n# Agentic Workflow Skills Discovery\n\nProvides automatic access to skills for building autonomous AI agents, managing tool use, and orchestrating multi-step workflows.\n\n## When This Skill Activates\n\nThis skill auto-activates when you're working with:\n- AI agent development and autonomous workflows\n- Task decomposition for LLM agents\n- Function calling and tool use patterns\n- Context window management and summarization\n- Working memory, scratchpads, and state tracking\n- Long-term memory and persistence patterns\n- Multi-step reasoning and planning\n- Failure recovery and re-planning strategies\n- Parallel vs sequential execution decisions\n\n## Available Skills\n\n### Quick Reference\n\nThe Agentic category contains 3 specialized skills:\n\n1. **agentic-task-decomposition** - Breaking complex goals into agent-executable steps, dependency graphs, re-planning\n2. **agentic-tool-use** - Function calling patterns, parallel tool use, error handling, tool selection heuristics\n3. **agentic-memory** - Context window management, working memory, long-term persistence, summarization\n\n### Load Full Category Details\n\nFor complete descriptions and workflows:\n\nRead ..\u002Fagentic\u002FINDEX.md\n\n\nThis loads the full Agentic category index with:\n- Detailed skill descriptions\n- Usage triggers for each skill\n- Common workflow combinations\n- Cross-references to related skills\n\n### Load Specific Skills\n\nLoad individual skills as needed:\n\n\n# Task planning and decomposition\nRead ..\u002Fagentic\u002Fagentic-task-decomposition.md\n\n# Tool calling and execution\nRead ..\u002Fagentic\u002Fagentic-tool-use.md\n\n# Context and memory management\nRead ..\u002Fagentic\u002Fagentic-memory.md\n\n\n## Common Workflows\n\n### Building an Agent from Scratch\n**Sequence**: Decomposition -> Tool Use -> Memory\n\nRead ..\u002Fagentic\u002Fagentic-task-decomposition.md  # Plan the agent's task handling\nRead ..\u002Fagentic\u002Fagentic-tool-use.md            # Implement tool execution\nRead ..\u002Fagentic\u002Fagentic-memory.md              # Add context management\n\n\n### Adding Tool Use to an Agent\n**Sequence**: Tool Use -> Decomposition\n\nRead ..\u002Fagentic\u002Fagentic-tool-use.md            # Tool calling patterns\nRead ..\u002Fagentic\u002Fagentic-task-decomposition.md  # Multi-tool task planning\n\n\n### Scaling Agent Sessions\n**Sequence**: Memory -> Decomposition\n\nRead ..\u002Fagentic\u002Fagentic-memory.md              # Context management\nRead ..\u002Fagentic\u002Fagentic-task-decomposition.md  # Context-bounded task sizing\n\n\n### Complete Agentic Stack\n**Full implementation**:\n\n\n# 1. Planning layer\nRead ..\u002Fagentic\u002Fagentic-task-decomposition.md\n\n# 2. Execution layer\nRead ..\u002Fagentic\u002Fagentic-tool-use.md\n\n# 3. Memory layer\nRead ..\u002Fagentic\u002Fagentic-memory.md\n\n\n## Skill Selection Guide\n\n**Choose task decomposition when:**\n- Complex goal needs breaking into steps\n- Tasks have dependencies or ordering constraints\n- Need to handle ambiguous requirements\n- Building a planning layer for an agent\n\n**Choose tool use when:**\n- Implementing function calling in an LLM agent\n- Debugging tool call failures or inefficiency\n- Designing tool schemas and structured outputs\n- Optimizing multi-tool workflows\n\n**Choose memory when:**\n- Agent sessions are hitting context limits\n- Need to persist state across turns or sessions\n- Building multi-turn conversational agents\n- Implementing retrieval-augmented generation\n\n## Integration with Other Skills\n\nAgentic skills commonly combine with:\n\n**API skills** (`discover-api`):\n- Agents that call REST\u002FGraphQL APIs\n- Tool schemas for API endpoints\n- Authentication handling in agent workflows\n\n**Testing skills** (`discover-testing`):\n- Testing agent behaviors and tool use\n- Autonomous test generation\n- Verifying agent task completion\n\n**Database skills** (`discover-database`):\n- Database-backed agent memory\n- Agents that query and modify data\n- Persistent state management\n\n**Infrastructure skills** (`discover-infra`, `discover-cloud`):\n- Deploying agent systems\n- Scaling agent workloads\n- Cost optimization for LLM calls\n\n## Usage Instructions\n\n1. **Auto-activation**: This skill loads automatically when Claude Code detects agentic workflow tasks\n2. **Browse skills**: Run `Read ..\u002Fagentic\u002FINDEX.md` for full category overview\n3. **Load specific skills**: Use commands above to load individual skills\n4. **Follow workflows**: Use recommended sequences for common agentic patterns\n5. **Combine skills**: Load multiple skills for comprehensive coverage\n\n## Progressive Loading\n\nThis gateway skill (~200 lines, ~2K tokens) enables progressive loading:\n- **Level 1**: Gateway loads automatically (you're here now)\n- **Level 2**: Load category INDEX.md (~3K tokens) for full overview\n- **Level 3**: Load specific skills (~2-3K tokens each) as needed\n\nTotal context: 2K + 3K + skill(s) = 5-10K tokens vs 12K+ for entire category.\n\n## Quick Start Examples\n\n**\"Build an autonomous coding agent\"**:\nRead ..\u002Fagentic\u002Fagentic-task-decomposition.md\n\n\n**\"How should my agent call tools?\"**:\nRead ..\u002Fagentic\u002Fagentic-tool-use.md\n\n\n**\"My agent is running out of context\"**:\nRead ..\u002Fagentic\u002Fagentic-memory.md\n\n\n\n**Next Steps**: Run `Read ..\u002Fagentic\u002FINDEX.md` to see full category details, or load specific skills using the commands above.\n","# Agentic Workflow Skills Discovery\n\nProvides automatic access to skills for building autonomous AI agents, managing tool use, and orchestrating multi-step workflows.\n\n## When This Skill Activates\n\nThis skill auto-activates when you're working with:\n- AI agent development and autonomous workflows\n- Task decomposition for LLM agents\n- Function calling and tool use patterns\n- Context window management and summarization\n- Working memory, scratchpads, and state tracking\n- Long-term memory and persistence patterns\n- Multi-step reasoning and planning\n- Failure recovery and re-planning strategies\n- Parallel vs sequential execution decisions\n\n## Available Skills\n\n### Quick Reference\n\nThe Agentic category contains 3 specialized skills:\n\n1. **agentic-task-decomposition** - Breaking complex goals into agent-executable steps, dependency graphs, re-planning\n2. **agentic-tool-use** - Function calling patterns, parallel tool use, error handling, tool selection heuristics\n3. **agentic-memory** - Context window management, working memory, long-term persistence, summarization\n\n### Load Full Category Details\n\nFor complete descriptions and workflows:\n\nRead ..\u002Fagentic\u002FINDEX.md\n\n\nThis loads the full Agentic category index with:\n- Detailed skill descriptions\n- Usage triggers for each skill\n- Common workflow combinations\n- Cross-references to related skills\n\n### Load Specific Skills\n\nLoad individual skills as needed:\n\n\n# Task planning and decomposition\nRead ..\u002Fagentic\u002Fagentic-task-decomposition.md\n\n# Tool calling and execution\nRead ..\u002Fagentic\u002Fagentic-tool-use.md\n\n# Context and memory management\nRead ..\u002Fagentic\u002Fagentic-memory.md\n\n\n## Common Workflows\n\n### Building an Agent from Scratch\n**Sequence**: Decomposition -> Tool Use -> Memory\n\nRead ..\u002Fagentic\u002Fagentic-task-decomposition.md  # Plan the agent's task handling\nRead ..\u002Fagentic\u002Fagentic-tool-use.md            # Implement tool execution\nRead ..\u002Fagentic\u002Fagentic-memory.md              # Add context management\n\n\n### Adding Tool Use to an Agent\n**Sequence**: Tool Use -> Decomposition\n\nRead ..\u002Fagentic\u002Fagentic-tool-use.md            # Tool calling patterns\nRead ..\u002Fagentic\u002Fagentic-task-decomposition.md  # Multi-tool task planning\n\n\n### Scaling Agent Sessions\n**Sequence**: Memory -> Decomposition\n\nRead ..\u002Fagentic\u002Fagentic-memory.md              # Context management\nRead ..\u002Fagentic\u002Fagentic-task-decomposition.md  # Context-bounded task sizing\n\n\n### Complete Agentic Stack\n**Full implementation**:\n\n\n# 1. Planning layer\nRead ..\u002Fagentic\u002Fagentic-task-decomposition.md\n\n# 2. Execution layer\nRead ..\u002Fagentic\u002Fagentic-tool-use.md\n\n# 3. Memory layer\nRead ..\u002Fagentic\u002Fagentic-memory.md\n\n\n## Skill Selection Guide\n\n**Choose task decomposition when:**\n- Complex goal needs breaking into steps\n- Tasks have dependencies or ordering constraints\n- Need to handle ambiguous requirements\n- Building a planning layer for an agent\n\n**Choose tool use when:**\n- Implementing function calling in an LLM agent\n- Debugging tool call failures or inefficiency\n- Designing tool schemas and structured outputs\n- Optimizing multi-tool workflows\n\n**Choose memory when:**\n- Agent sessions are hitting context limits\n- Need to persist state across turns or sessions\n- Building multi-turn conversational agents\n- Implementing retrieval-augmented generation\n\n## Integration with Other Skills\n\nAgentic skills commonly combine with:\n\n**API skills** (`discover-api`):\n- Agents that call REST\u002FGraphQL APIs\n- Tool schemas for API endpoints\n- Authentication handling in agent workflows\n\n**Testing skills** (`discover-testing`):\n- Testing agent behaviors and tool use\n- Autonomous test generation\n- Verifying agent task completion\n\n**Database skills** (`discover-database`):\n- Database-backed agent memory\n- Agents that query and modify data\n- Persistent state management\n\n**Infrastructure skills** (`discover-infra`, `discover-cloud`):\n- Deploying agent systems\n- Scaling agent workloads\n- Cost optimization for LLM calls\n\n## Usage Instructions\n\n1. **Auto-activation**: This skill loads automatically when Claude Code detects agentic workflow tasks\n2. **Browse skills**: Run `Read ..\u002Fagentic\u002FINDEX.md` for full category overview\n3. **Load specific skills**: Use commands above to load individual skills\n4. **Follow workflows**: Use recommended sequences for common agentic patterns\n5. **Combine skills**: Load multiple skills for comprehensive coverage\n\n## Progressive Loading\n\nThis gateway skill (~200 lines, ~2K tokens) enables progressive loading:\n- **Level 1**: Gateway loads automatically (you're here now)\n- **Level 2**: Load category INDEX.md (~3K tokens) for full overview\n- **Level 3**: Load specific skills (~2-3K tokens each) as needed\n\nTotal context: 2K + 3K + skill(s) = 5-10K tokens vs 12K+ for entire category.\n\n## Quick Start Examples\n\n**\"Build an autonomous coding agent\"**:\nRead ..\u002Fagentic\u002Fagentic-task-decomposition.md\n\n\n**\"How should my agent call tools?\"**:\nRead ..\u002Fagentic\u002Fagentic-tool-use.md\n\n\n**\"My agent is running out of context\"**:\nRead ..\u002Fagentic\u002Fagentic-memory.md\n\n\n\n**Next Steps**: Run `Read ..\u002Fagentic\u002FINDEX.md` to see full category details, or load specific skills using the commands above.\n",{"name":5,"license":15,"metadata":24,"description":7,"compatibility":27},{"author":25,"version":26},"rand","4.0","Designed for Claude Code. Compatible with any agent supporting the Agent Skills format.","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fdiscover-agentic",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":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill discover-agentic",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill discover-agentic",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill discover-agentic","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\u002Fdiscover-agentic\u002FSKILL.md",true,[],[51,58,63,70,77,84],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"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":59,"name":53,"nameZh":6,"description":54,"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},"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":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},"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":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},"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":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},"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":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},"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",[],[]]