[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HYAVMPM4SBDV60R2B5HPV8":3,"skill-same:01M6HYAVMPM4SBDV60R2B5HPV8":71},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":6,"updatedAt":50,"install":51,"resources":64},"01M6HYAVMPM4SBDV60R2B5HPV8","skill-discovery",null,"Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.","HKUDS\u002FAgentPilot","HKUDS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F118165258?v=4","01M6HW8VRNZP64G0P4MVJW2KKQ","✨Data Intelligence Lab@HKU✨","01M6HW8VWZVHBRHYH3T330PFWV",7996,"MIT","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fhost_skills\u002Fskill-discovery\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],"discovery","skill discovery","packages","help","capabilities","search","cloud","Tools","browse","reliability","reusable","tokens","step by step","openspace","2026-11-10 10:12:30",false,"---\nname: skill-discovery\ndescription: Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.\n---\n\n# Skill Discovery\n\nDiscover and browse skills from OpenSpace's local registry and cloud skill library.\n\n## When to use\n\n- User asks \"what skills are available?\" or \"is there a skill for X?\"\n- You encounter an unfamiliar task — a proven skill can save significant tokens over trial-and-error\n- You need to decide: handle a task yourself, or delegate to OpenSpace\n\n## Cloud access\n\n`search_skills` is local-only. If the user wants cloud results, or a cloud operation reports a missing\u002Finvalid key, set up cloud access first and use `cloud_browse_skills`.\n\nAsk for `email` and `agent_name`. Ask for `password` only through secure secret input; it must be 8 to 72 characters. Do not ask for passcode\u002FOTP because `cloud_auth_flow` does not accept one.\n\n```\ncloud_auth_flow(action=\"bootstrap_agent_key\", email=\"user@example.com\", password=\"\u003Csecure-password>\", agent_name=\"openspace-local-agent\")\n```\n\nIf secure password input is not available, ask the user to run:\n\n```bash\nopenspace-cloud-auth bootstrap-agent-key --email user@example.com --agent-name openspace-local-agent\n```\n\nAfter setup, use `cloud_browse_skills`.\n\n## search_skills\n\n```\nsearch_skills(query=\"automated deployment with rollback\")\n```\n\n| Parameter | Required | Default | Description |\n|-----------|----------|---------|-------------|\n| `query` | yes | — | Natural language or keywords |\n| `limit` | no | `20` | Max results |\n\n## cloud_browse_skills\n\nUse this single cloud tool when local search is not enough. Continue calling\nthe same tool with the returned `next_actions[].action`.\n\n```\ncloud_browse_skills(action=\"search_skills\", query=\"automated deployment with rollback\")\ncloud_browse_skills(action=\"local_placement\", query=\"automated deployment with rollback\")\ncloud_browse_skills(action=\"local_placement\", local_category_path=\"technology\u002Fcomputing\u002Fdeployment\")\ncloud_browse_skills(action=\"import_skill\", cloud_skill_id=\"\u003Ccloud_skill_id>\", local_category_path=\"technology\u002Fcomputing\u002Fdeployment\u002Frollback\")\n```\n\nUse `recall` and `pull_projection` only when you need package discovery or\npackage outlines before choosing a skill. Concrete skill search should start\nwith `search_skills`.\n\nChoose `local_category_path` for the user's local package taxonomy. It uses the\nsame shape as cloud package paths, but is stored independently and may be more\nspecific than the current cloud tree. Use `local_placement` to inspect existing\npaths and create a nearby child path before importing.\n\n## After search\n\nResults are returned to you (not executed). Cloud imports return a `local_path` after `cloud_browse_skills(action=\"import_skill\", ...)`.\n\n```\nFound a matching skill?\n├── YES, and I can follow it myself\n│     → read SKILL.md at local_path, follow the instructions\n├── YES, but I lack the capability\n│     → delegate via execute_task (see delegate-task skill)\n└── NO match\n      → handle it yourself, or delegate via execute_task\n```\n\n## Notes\n\n- This is for **discovery** — you see results and decide. For direct execution, use `execute_task` from the `delegate-task` skill.\n- Cloud skills have been evolved through real use — more reliable than skills written from scratch.\n- Always tell the user what you found (or didn't find) and what you recommend.\n","# Skill Discovery\n\nDiscover and browse skills from OpenSpace's local registry and cloud skill library.\n\n## When to use\n\n- User asks \"what skills are available?\" or \"is there a skill for X?\"\n- You encounter an unfamiliar task — a proven skill can save significant tokens over trial-and-error\n- You need to decide: handle a task yourself, or delegate to OpenSpace\n\n## Cloud access\n\n`search_skills` is local-only. If the user wants cloud results, or a cloud operation reports a missing\u002Finvalid key, set up cloud access first and use `cloud_browse_skills`.\n\nAsk for `email` and `agent_name`. Ask for `password` only through secure secret input; it must be 8 to 72 characters. Do not ask for passcode\u002FOTP because `cloud_auth_flow` does not accept one.\n\n```\ncloud_auth_flow(action=\"bootstrap_agent_key\", email=\"user@example.com\", password=\"\u003Csecure-password>\", agent_name=\"openspace-local-agent\")\n```\n\nIf secure password input is not available, ask the user to run:\n\n```bash\nopenspace-cloud-auth bootstrap-agent-key --email user@example.com --agent-name openspace-local-agent\n```\n\nAfter setup, use `cloud_browse_skills`.\n\n## search_skills\n\n```\nsearch_skills(query=\"automated deployment with rollback\")\n```\n\n| Parameter | Required | Default | Description |\n|-----------|----------|---------|-------------|\n| `query` | yes | — | Natural language or keywords |\n| `limit` | no | `20` | Max results |\n\n## cloud_browse_skills\n\nUse this single cloud tool when local search is not enough. Continue calling\nthe same tool with the returned `next_actions[].action`.\n\n```\ncloud_browse_skills(action=\"search_skills\", query=\"automated deployment with rollback\")\ncloud_browse_skills(action=\"local_placement\", query=\"automated deployment with rollback\")\ncloud_browse_skills(action=\"local_placement\", local_category_path=\"technology\u002Fcomputing\u002Fdeployment\")\ncloud_browse_skills(action=\"import_skill\", cloud_skill_id=\"\u003Ccloud_skill_id>\", local_category_path=\"technology\u002Fcomputing\u002Fdeployment\u002Frollback\")\n```\n\nUse `recall` and `pull_projection` only when you need package discovery or\npackage outlines before choosing a skill. Concrete skill search should start\nwith `search_skills`.\n\nChoose `local_category_path` for the user's local package taxonomy. It uses the\nsame shape as cloud package paths, but is stored independently and may be more\nspecific than the current cloud tree. Use `local_placement` to inspect existing\npaths and create a nearby child path before importing.\n\n## After search\n\nResults are returned to you (not executed). Cloud imports return a `local_path` after `cloud_browse_skills(action=\"import_skill\", ...)`.\n\n```\nFound a matching skill?\n├── YES, and I can follow it myself\n│     → read SKILL.md at local_path, follow the instructions\n├── YES, but I lack the capability\n│     → delegate via execute_task (see delegate-task skill)\n└── NO match\n      → handle it yourself, or delegate via execute_task\n```\n\n## Notes\n\n- This is for **discovery** — you see results and decide. For direct execution, use `execute_task` from the `delegate-task` skill.\n- Cloud skills have been evolved through real use — more reliable than skills written from scratch.\n- Always tell the user what you found (or didn't find) and what you recommend.\n",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Fopenspace\u002Fhost_skills\u002Fskill-discovery",941,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot","https:\u002F\u002Fgithub.com\u002FHKUDS","https:\u002F\u002Fsites.google.com\u002Fview\u002Fchaoh","2026-11-12 22:26:39",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add HKUDS\u002FAgentPilot --skill skill-discovery",{"tool":57,"command":58},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill skill-discovery",{"tool":60,"command":61},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill skill-discovery","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fhost_skills\u002Fskill-discovery\u002FSKILL.md",true,[65],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},".skill_id","OTHER","其他",30,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fhost_skills\u002Fskill-discovery\u002F.skill_id",[72,92,110,134,157,173],{"skillNo":73,"name":74,"nameZh":6,"description":75,"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":38},"01M6HYB297NDABRERJRVG0K8R0","agentpilot","Set up AgentPilot and use its single entry to prepare missing inputs and run configured RSI experiments. Use when the user requests AgentPilot installation or work with AgentPilot.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fplugins\u002Fagentpilot\u002Fskills\u002Fagentpilot\u002FSKILL.md",[],[74,79,80,81,82,83,84,85,86,87,88,89,90,91],"missing","rsi","with","requests","user","work","SET","run","up","prepare","experiments","installation","use",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":38},"01M6HYAYWXTTE1J7DJM0MFNQ4H","remember","Review auto-memory entries and propose promotions to OPENSPACE.md, OPENSPACE.local.md, or retained auto-memory topics; detect duplicates, stale facts, conflicts, and ambiguous entries before making changes.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fskills\u002Fremember\u002FSKILL.md",[],[94,99,100,101,102,37,103,104,105,106,107,108,109],"auto","memory","review","facts","changes","detect","entries","local","conflicts","stale","duplicates",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":117,"publishedAt":38},"01M6HYAR811B3RB0M50RBEDGN6","delegate-task","Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and skill library. Skills auto-improve through use, reducing token consumption over time. A cloud community lets agents share and collectively evolve reusable skills.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fhost_skills\u002Fdelegate-task\u002FSKILL.md",[116],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[118,119,120,121,37,122,123,91,124,125,126,34,99,127,128,129,130,131,132,133],"delegate","task","delegate task","worker","for","desktop automation","autonomous","time","community","tasks","stack","improve","share","automation","MCP","tool",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":38},"01M6HYAM9FSGV6E52AYENDQXYH","write-special-chars-ts-check","Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, plus a reliable TypeScript type-checking step that filters output to only the newly-written files to avoid being misled by pre-existing errors.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fshowcase\u002Fskills\u002Fwrite-special-chars-ts-check\u002FSKILL.md",[],[141,142,143,144,145,146,147,122,148,149,150,151,152,153,154,155,156],"write special chars ts check","write","check","typescript","errors","Existing","type-checking","script","output","type","files","filters","only","template","file","python",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":38},"01M6HYAH05HGV7SVWSVR8PJRQD","write-special-chars-readback","Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, with mandatory post-write verification via read_file and cleanup of \u002Ftmp helper scripts.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fshowcase\u002Fskills\u002Fwrite-special-chars-readback\u002FSKILL.md",[],[164,165,142,155,122,148,81,166,167,168,169,170,154,171,172,156],"write special chars readback","readback","helper","post","via","scripts","read","verification","cleanup",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":38},"01M6HYAE5C4BBYW27ZEBX4YR7A","write-special-chars-heredoc","Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) by using a Python heredoc script executed via shell.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fshowcase\u002Fskills\u002Fwrite-special-chars-heredoc\u002FSKILL.md",[],[180,142,122,148,168,154,181,155,156],"write special chars heredoc","shell"]