[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ET11WCKYWP8X26YA70YWEW":3,"skill-same:01M7ET11WCKYWP8X26YA70YWEW":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},"01M7ET11WCKYWP8X26YA70YWEW","software-agent-sdk",null,"Router for using and maintaining the OpenHands Software Agent SDK, including local agents, tools, AgentSkills, agent-server runtimes, GitHub automation, and repository development workflows.","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\u002F04-安全渗透\u002Fsoftware-agent-sdk\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: software-agent-sdk\ndescription: \"Router for using and maintaining the OpenHands Software Agent SDK,\n  including local agents, tools, AgentSkills, agent-server runtimes, GitHub\n  automation, and repository development workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# OpenHands Software Agent SDK\n\nUse this repo skill when a task involves the OpenHands `software-agent-sdk` packages or source repository: building code agents, selecting built-in tools, loading AgentSkills\u002Fplugins\u002Fhooks\u002FMCP, running local or remote conversations, using the agent-server and workspace backends, automating GitHub workflows, or maintaining this monorepo.\n\nThe runtime packages are:\n\n- `openhands-sdk`: core agent, LLM, conversation, settings, skills, MCP, hooks, plugins, and workspace interfaces.\n- `openhands-tools`: built-in tool implementations and default presets.\n- `openhands-workspace`: Docker, Apptainer, cloud, and runtime-API remote workspace implementations.\n- `openhands-agent-server`: FastAPI REST\u002FWebSocket server for remote conversations, workspace routes, deferred init, and local\u002Fhosted runtimes.\n\n## First checks\n\nFor an installed package environment:\n\n```bash\npython -m pip install openhands-sdk openhands-tools openhands-workspace openhands-agent-server\npython - \u003C\u003C'PY'\nimport openhands.sdk, openhands.tools, openhands.workspace, openhands.agent_server\nprint(\"OpenHands SDK packages import successfully\")\nPY\npython -m openhands.agent_server --help\n```\n\nFor a source checkout, run `make build` before package tests. Use `uv run pytest ...` and `uv run pre-commit run --files \u003Cchanged-file>` for focused validation.\n\nRun [`scripts\u002Fcheck_env.py`](scripts\u002Fcheck_env.py) for a safe import\u002Ftool\u002Fserver capability report.\n\n## Route map\n\n### `agent-core`\nUse [`sub-skills\u002Fagent-core\u002FSKILL.md`](sub-skills\u002Fagent-core\u002FSKILL.md) for local SDK agent construction, LLM configuration, `Agent`, `Conversation`, `LocalConversation`, `RemoteConversation`, callbacks, async\u002Fsync execution, persistence, interruption, condensation, settings, security analyzers, and title generation.\n\nRead it when the request mentions `LLM`, `Agent`, `Conversation`, `AgentContext` as prompt context rather than skill loading mechanics, local runs, remote conversation factory routing, events, metrics, cancellation, or model\u002Fprovider behavior.\n\n### `extensions`\nUse [`sub-skills\u002Fextensions\u002FSKILL.md`](sub-skills\u002Fextensions\u002FSKILL.md) for AgentSkills, project\u002Fuser\u002Fpublic skill loading, plugins and marketplaces, hooks, MCP server maps, memory, secrets, prompt suffixes, and other extension points.\n\nRead it when the request mentions `SKILL.md`, `.agents\u002Fskills`, `.openhands\u002Fskills`, `AGENTS.md`, `load_project_skills`, `registered_marketplaces`, `.mcp.json`, `HookConfig`, `LookupSecret`, or plugin lazy loading.\n\n### `built-in-tools`\nUse [`sub-skills\u002Fbuilt-in-tools\u002FSKILL.md`](sub-skills\u002Fbuilt-in-tools\u002FSKILL.md) for `openhands-tools`, default tool presets, tool registration, usable-tool filtering, terminal\u002Ffile-editor\u002Fbrowser\u002Ftask\u002Fworkflow\u002Fgrep\u002Fglob\u002Fplanning\u002Fdelegate\u002FTOM tools, custom tool classes, and sub-agent tool wiring.\n\nRead it when the request asks which tool names to use, how to register or resolve tools, how browser availability is detected, how workflow scripts work, or why a tool is missing from `\u002Fserver_info`.\n\n### `remote-runtime`\nUse [`sub-skills\u002Fremote-runtime\u002FSKILL.md`](sub-skills\u002Fremote-runtime\u002FSKILL.md) for `openhands-agent-server`, REST\u002FWebSocket routes, `RemoteWorkspace`, `Workspace(host=...)`, Docker\u002FApptainer\u002FAPI\u002Fcloud workspaces, deferred init, session API keys, custom tool import modules, and local server helpers.\n\nRead it when the request mentions `python -m openhands.agent_server`, `\u002Fapi\u002Fconversations`, `\u002Fapi\u002Finit`, `X-Session-API-Key`, WebSockets, Docker workspace images, `OH_EXTRA_PYTHON_PATH`, or warm-pool\u002Fdormant server behavior.\n\n### `github-automation`\nUse [`sub-skills\u002Fgithub-automation\u002FSKILL.md`](sub-skills\u002Fgithub-automation\u002FSKILL.md) for SDK-powered GitHub Actions examples, prompt-driven task runners, TODO scanning, examples-report rendering, and automation scripts that run agents from CI.\n\nRead it when the request involves GitHub workflow YAML, `PROMPT_STRING`, prompt files\u002FURLs, `LLM_API_KEY`, automated TODO management, routine maintenance actions, PR automation, or example-run summaries.\n\n### `repo-development`\nUse [`sub-skills\u002Frepo-development\u002FSKILL.md`](sub-skills\u002Frepo-development\u002FSKILL.md) for maintaining this monorepo: package boundaries, import rules, tool registration linting, settings compatibility, SDK\u002FREST API deprecation policy, test selection, examples runner, release PR checks, pre-commit, and CI workflows.\n\nRead it when editing source code, tests, examples, settings models, public APIs, REST routes, tools, workspace backends, Docker image publishing, or repository automation.\n\n## Cross-cutting references\n\n- [`references\u002Fpackage-overview.md`](references\u002Fpackage-overview.md): package surfaces, versions, public imports, and capability ownership.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md): install\u002Fimport, credentials, optional browser\u002Fruntime, server, workspace, and maintenance failure patterns.\n- [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md): source snapshot and evidence paths used to create this skill; read before deciding whether a skill refresh is needed.\n- [`references\u002Frepo-routing-metadata.json`](references\u002Frepo-routing-metadata.json): structured metadata consumed by the managed repo-skills-router import flow.\n\n## Boundary rules for future agents\n\n- Use this skill as operating guidance; do not import it into live router state unless a user explicitly approves managed import.\n- Runtime guidance is self-contained in this skill tree. Do not require access to the original generation checkout to use it.\n- When maintaining a fresh checkout of `software-agent-sdk`, confirm current code and nearby `AGENTS.md` files before editing because repo policies may have changed after the provenance snapshot.\n- Use generated scripts from this skill tree for diagnostics and helper workflows; when editing a live checkout, run that checkout's native tests and scripts from its repository root.\n","# OpenHands Software Agent SDK\n\nUse this repo skill when a task involves the OpenHands `software-agent-sdk` packages or source repository: building code agents, selecting built-in tools, loading AgentSkills\u002Fplugins\u002Fhooks\u002FMCP, running local or remote conversations, using the agent-server and workspace backends, automating GitHub workflows, or maintaining this monorepo.\n\nThe runtime packages are:\n\n- `openhands-sdk`: core agent, LLM, conversation, settings, skills, MCP, hooks, plugins, and workspace interfaces.\n- `openhands-tools`: built-in tool implementations and default presets.\n- `openhands-workspace`: Docker, Apptainer, cloud, and runtime-API remote workspace implementations.\n- `openhands-agent-server`: FastAPI REST\u002FWebSocket server for remote conversations, workspace routes, deferred init, and local\u002Fhosted runtimes.\n\n## First checks\n\nFor an installed package environment:\n\n```bash\npython -m pip install openhands-sdk openhands-tools openhands-workspace openhands-agent-server\npython - \u003C\u003C'PY'\nimport openhands.sdk, openhands.tools, openhands.workspace, openhands.agent_server\nprint(\"OpenHands SDK packages import successfully\")\nPY\npython -m openhands.agent_server --help\n```\n\nFor a source checkout, run `make build` before package tests. Use `uv run pytest ...` and `uv run pre-commit run --files \u003Cchanged-file>` for focused validation.\n\nRun [`scripts\u002Fcheck_env.py`](scripts\u002Fcheck_env.py) for a safe import\u002Ftool\u002Fserver capability report.\n\n## Route map\n\n### `agent-core`\nUse [`sub-skills\u002Fagent-core\u002FSKILL.md`](sub-skills\u002Fagent-core\u002FSKILL.md) for local SDK agent construction, LLM configuration, `Agent`, `Conversation`, `LocalConversation`, `RemoteConversation`, callbacks, async\u002Fsync execution, persistence, interruption, condensation, settings, security analyzers, and title generation.\n\nRead it when the request mentions `LLM`, `Agent`, `Conversation`, `AgentContext` as prompt context rather than skill loading mechanics, local runs, remote conversation factory routing, events, metrics, cancellation, or model\u002Fprovider behavior.\n\n### `extensions`\nUse [`sub-skills\u002Fextensions\u002FSKILL.md`](sub-skills\u002Fextensions\u002FSKILL.md) for AgentSkills, project\u002Fuser\u002Fpublic skill loading, plugins and marketplaces, hooks, MCP server maps, memory, secrets, prompt suffixes, and other extension points.\n\nRead it when the request mentions `SKILL.md`, `.agents\u002Fskills`, `.openhands\u002Fskills`, `AGENTS.md`, `load_project_skills`, `registered_marketplaces`, `.mcp.json`, `HookConfig`, `LookupSecret`, or plugin lazy loading.\n\n### `built-in-tools`\nUse [`sub-skills\u002Fbuilt-in-tools\u002FSKILL.md`](sub-skills\u002Fbuilt-in-tools\u002FSKILL.md) for `openhands-tools`, default tool presets, tool registration, usable-tool filtering, terminal\u002Ffile-editor\u002Fbrowser\u002Ftask\u002Fworkflow\u002Fgrep\u002Fglob\u002Fplanning\u002Fdelegate\u002FTOM tools, custom tool classes, and sub-agent tool wiring.\n\nRead it when the request asks which tool names to use, how to register or resolve tools, how browser availability is detected, how workflow scripts work, or why a tool is missing from `\u002Fserver_info`.\n\n### `remote-runtime`\nUse [`sub-skills\u002Fremote-runtime\u002FSKILL.md`](sub-skills\u002Fremote-runtime\u002FSKILL.md) for `openhands-agent-server`, REST\u002FWebSocket routes, `RemoteWorkspace`, `Workspace(host=...)`, Docker\u002FApptainer\u002FAPI\u002Fcloud workspaces, deferred init, session API keys, custom tool import modules, and local server helpers.\n\nRead it when the request mentions `python -m openhands.agent_server`, `\u002Fapi\u002Fconversations`, `\u002Fapi\u002Finit`, `X-Session-API-Key`, WebSockets, Docker workspace images, `OH_EXTRA_PYTHON_PATH`, or warm-pool\u002Fdormant server behavior.\n\n### `github-automation`\nUse [`sub-skills\u002Fgithub-automation\u002FSKILL.md`](sub-skills\u002Fgithub-automation\u002FSKILL.md) for SDK-powered GitHub Actions examples, prompt-driven task runners, TODO scanning, examples-report rendering, and automation scripts that run agents from CI.\n\nRead it when the request involves GitHub workflow YAML, `PROMPT_STRING`, prompt files\u002FURLs, `LLM_API_KEY`, automated TODO management, routine maintenance actions, PR automation, or example-run summaries.\n\n### `repo-development`\nUse [`sub-skills\u002Frepo-development\u002FSKILL.md`](sub-skills\u002Frepo-development\u002FSKILL.md) for maintaining this monorepo: package boundaries, import rules, tool registration linting, settings compatibility, SDK\u002FREST API deprecation policy, test selection, examples runner, release PR checks, pre-commit, and CI workflows.\n\nRead it when editing source code, tests, examples, settings models, public APIs, REST routes, tools, workspace backends, Docker image publishing, or repository automation.\n\n## Cross-cutting references\n\n- [`references\u002Fpackage-overview.md`](references\u002Fpackage-overview.md): package surfaces, versions, public imports, and capability ownership.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md): install\u002Fimport, credentials, optional browser\u002Fruntime, server, workspace, and maintenance failure patterns.\n- [`references\u002Frepo-provenance.md`](references\u002Frepo-provenance.md): source snapshot and evidence paths used to create this skill; read before deciding whether a skill refresh is needed.\n- [`references\u002Frepo-routing-metadata.json`](references\u002Frepo-routing-metadata.json): structured metadata consumed by the managed repo-skills-router import flow.\n\n## Boundary rules for future agents\n\n- Use this skill as operating guidance; do not import it into live router state unless a user explicitly approves managed import.\n- Runtime guidance is self-contained in this skill tree. Do not require access to the original generation checkout to use it.\n- When maintaining a fresh checkout of `software-agent-sdk`, confirm current code and nearby `AGENTS.md` files before editing because repo policies may have changed after the provenance snapshot.\n- Use generated scripts from this skill tree for diagnostics and helper workflows; when editing a live checkout, run that checkout's native tests and scripts from its repository root.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fsoftware-agent-sdk",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 software-agent-sdk",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill software-agent-sdk",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill software-agent-sdk","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fsoftware-agent-sdk\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fpackage-overview.md","REFERENCE","参考文档",5166,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fsoftware-agent-sdk\u002Freferences\u002Fpackage-overview.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Frepo-provenance.md",4128,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fsoftware-agent-sdk\u002Freferences\u002Frepo-provenance.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Frepo-routing-metadata.json",512,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fsoftware-agent-sdk\u002Freferences\u002Frepo-routing-metadata.json",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Ftroubleshooting.md",6868,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fsoftware-agent-sdk\u002Freferences\u002Ftroubleshooting.md",[67,75,80,87,94,101],{"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":74},"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",[],[],"2026-11-16 10:05:34",{"skillNo":76,"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":77,"categories":78,"keywords":79,"publishedAt":74},"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":74},"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":74},"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":74},"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":74},"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",[],[]]