[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7565770A9SEQVTC42WM0EY2":3,"skill-same:01M7565770A9SEQVTC42WM0EY2":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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7565770A9SEQVTC42WM0EY2","cursor-agent",null,"When the user wants the local cursor-agent CLI run, its installation or login changed, its connected tools changed, or a Cursor worker started.","prathamdby\u002Fskills","prathamdby","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F134331217?v=4","01M7564WRST5Q4T0H867V2D7FM","Pratham Dubey","01M7564WSKSG53RFP8B1K7KA21",6,"MIT","https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fcursor-agent\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: cursor-agent\ndescription: >\n  When the user wants the local cursor-agent CLI run, its installation or login changed, its connected tools changed, or a Cursor worker started.\n---\n\n# Cursor Agent\n\n## Options and boundaries\n\nDefault: `cursor-agent --print --trust --yolo --workspace \u003Cabs-dir> \"\u003Cprompt>\"`,\nmode\u002Fmodel omitted, text output, parent wait 15m. Calling this skill authorizes\nthat run: pass `--trust` and `--yolo` without asking. Print alone can write.\n\"Plan\" \u002F \"read-only plan\" adds `--plan` and omits `--yolo`. \"Ask\" \u002F \"Q&A\" adds\n`--mode ask` and omits `--yolo`. Both stay read-only, still pass `--trust`, and\nwait until exit. \"Use \u003Cmodel>\" adds `--model`. \"Interactive\" \u002F \"TUI\" omits\nprint, `--trust`, and `--yolo`; the user owns that dialog.\n\"Resume \u003Cid>\" adds `--resume`; \"continue\" adds `--continue`; both wait until\nexit and keep the same trust\u002Fyolo choice as the selected mode.\n\"Worktree [name]\" adds `--worktree [name]`; record the printed path.\n\"JSON\" \u002F \"stream-json\" selects that print format. Ambiguity is `BLOCKED`.\n\nAdd sandbox disabled, approve-mcps, or a worker desktop\u002Fcredential flag only\nwhen the user names that control. Auto-review is explicit opt-in. Do not stop\nto confirm trust or yolo, and do not add those extra flags after a failure.\n\n## 1. Resolve\n\nFix workspace, prompt, mode, session\u002Fworktree, output, and wait.\nCheck binary and `cursor-agent status --format json` without exposing secrets.\nMissing binary → follow `references\u002Finstall.md`; missing auth → `BLOCKED`\nunless login was requested.\nRecord `cmd | workspace | mode | session | worktree | wait | evidence | terminal`.\nDone when target, binary, auth, and the trust\u002Fyolo choice are fixed.\n\n## 2. Run\n\nBuild argv and quote the prompt literally. Text\u002Fjson may be quiet until\nexit; silence is not a hang. Wait until exit or the recorded deadline;\nkill only this run's PID at that deadline. Nonzero exit: capture stderr,\ninspect the tree, report `BLOCKED`. On `Workspace Trust Required` for a\nprint run, rerun that argv with `--trust` if it was missing. Leave a TUI\non its user-owned dialog. Do not ask the user and do not add sandbox, MCP,\nor worker flags.\n\nFor JSON\u002Fstream output, follow `references\u002Fstreaming.md`.\nFor resume, continue, or persist, follow `references\u002Fsessions.md`.\nFor worktrees\u002Fparallel runs, follow `references\u002Fworktrees.md`.\nFor a TUI or other command syntax, follow `references\u002Fmanagement.md`.\nFor login, MCP, plugins, workers, or Bedrock, apply the matching branch in\n`references\u002Fintegrations.md`. On rejected syntax, use scoped `--help`.\nDone when the process exits, an intended live session is recorded, or a\nfailure is reported.\n\n## 3. Verify and report\n\nInspect status and diff; CLI text is unverified. Run the narrowest covering\ntests for edited executable code. Plan\u002Fask must leave the tree unchanged.\nCheck each worktree and any integrated tree. Clean up only sessions and clean\nworktrees this run created unless kept; preserve shell integration, MCP,\nplugins, and workers. Report command, mode, session\u002Fworktree, wait, and\noutcome evidence. Done when each outcome is observed or blocked with evidence.\n\nTerminals: `SUCCESS`, `NO_CHANGES`, `BLOCKED`.\n","# Cursor Agent\n\n## Options and boundaries\n\nDefault: `cursor-agent --print --trust --yolo --workspace \u003Cabs-dir> \"\u003Cprompt>\"`,\nmode\u002Fmodel omitted, text output, parent wait 15m. Calling this skill authorizes\nthat run: pass `--trust` and `--yolo` without asking. Print alone can write.\n\"Plan\" \u002F \"read-only plan\" adds `--plan` and omits `--yolo`. \"Ask\" \u002F \"Q&A\" adds\n`--mode ask` and omits `--yolo`. Both stay read-only, still pass `--trust`, and\nwait until exit. \"Use \u003Cmodel>\" adds `--model`. \"Interactive\" \u002F \"TUI\" omits\nprint, `--trust`, and `--yolo`; the user owns that dialog.\n\"Resume \u003Cid>\" adds `--resume`; \"continue\" adds `--continue`; both wait until\nexit and keep the same trust\u002Fyolo choice as the selected mode.\n\"Worktree [name]\" adds `--worktree [name]`; record the printed path.\n\"JSON\" \u002F \"stream-json\" selects that print format. Ambiguity is `BLOCKED`.\n\nAdd sandbox disabled, approve-mcps, or a worker desktop\u002Fcredential flag only\nwhen the user names that control. Auto-review is explicit opt-in. Do not stop\nto confirm trust or yolo, and do not add those extra flags after a failure.\n\n## 1. Resolve\n\nFix workspace, prompt, mode, session\u002Fworktree, output, and wait.\nCheck binary and `cursor-agent status --format json` without exposing secrets.\nMissing binary → follow `references\u002Finstall.md`; missing auth → `BLOCKED`\nunless login was requested.\nRecord `cmd | workspace | mode | session | worktree | wait | evidence | terminal`.\nDone when target, binary, auth, and the trust\u002Fyolo choice are fixed.\n\n## 2. Run\n\nBuild argv and quote the prompt literally. Text\u002Fjson may be quiet until\nexit; silence is not a hang. Wait until exit or the recorded deadline;\nkill only this run's PID at that deadline. Nonzero exit: capture stderr,\ninspect the tree, report `BLOCKED`. On `Workspace Trust Required` for a\nprint run, rerun that argv with `--trust` if it was missing. Leave a TUI\non its user-owned dialog. Do not ask the user and do not add sandbox, MCP,\nor worker flags.\n\nFor JSON\u002Fstream output, follow `references\u002Fstreaming.md`.\nFor resume, continue, or persist, follow `references\u002Fsessions.md`.\nFor worktrees\u002Fparallel runs, follow `references\u002Fworktrees.md`.\nFor a TUI or other command syntax, follow `references\u002Fmanagement.md`.\nFor login, MCP, plugins, workers, or Bedrock, apply the matching branch in\n`references\u002Fintegrations.md`. On rejected syntax, use scoped `--help`.\nDone when the process exits, an intended live session is recorded, or a\nfailure is reported.\n\n## 3. Verify and report\n\nInspect status and diff; CLI text is unverified. Run the narrowest covering\ntests for edited executable code. Plan\u002Fask must leave the tree unchanged.\nCheck each worktree and any integrated tree. Clean up only sessions and clean\nworktrees this run created unless kept; preserve shell integration, MCP,\nplugins, and workers. Report command, mode, session\u002Fworktree, wait, and\noutcome evidence. Done when each outcome is observed or blocked with evidence.\n\nTerminals: `SUCCESS`, `NO_CHANGES`, `BLOCKED`.\n",{"name":5,"description":7},"main","7e02cfa05508af59db423ab0b55cbeccca47227f","skills\u002Fengineering\u002Fcursor-agent",0,"https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills","https:\u002F\u002Fgithub.com\u002Fprathamdby","2026-11-10 11:05:05",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add prathamdby\u002Fskills --skill cursor-agent",{"tool":37,"command":38},"bunx","bunx skills add prathamdby\u002Fskills --skill cursor-agent",{"tool":40,"command":41},"pnpm","pnpm dlx skills add prathamdby\u002Fskills --skill cursor-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fcursor-agent\u002FSKILL.md",true,[45,51,55,59,63,67],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Finstall.md","REFERENCE","参考文档",643,"https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fcursor-agent\u002Freferences\u002Finstall.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fintegrations.md",2411,"https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fcursor-agent\u002Freferences\u002Fintegrations.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fmanagement.md",665,"https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fcursor-agent\u002Freferences\u002Fmanagement.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fsessions.md",737,"https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fcursor-agent\u002Freferences\u002Fsessions.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fstreaming.md",928,"https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fcursor-agent\u002Freferences\u002Fstreaming.md",{"path":68,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fworktrees.md",766,"https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fcursor-agent\u002Freferences\u002Fworktrees.md",[72,79,86,93,100,107],{"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":19},"01M75665C5GFXW5791HNM7YV1Q","use-skill","When the user gives a GitHub link to a skill and wants it run without installing it.","https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fuse-skill\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},"01M75663VH2BD43GZXF6WEKMY7","todoist-task","When the user wants a Todoist task created, or shown before it is created.","https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Ftodoist-task\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},"01M75660YWCZ0C2MEJ29KX4JP9","restate","When the user wants the last reply said again in plain words, wants a catch-up since their last message, or wants the decision they need to make.","https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Frestate\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},"01M7565Z2VG522XQYJQJ9TAPXB","upfront-design","When the user wants a design agreed before coding, a draft resumed, or an approved milestone checked.","https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fupfront-design\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},"01M7565W4RGPHW61XMRY4MREM8","recon","When the user wants this repository's saved map read, created, or refreshed.","https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Frecon\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7565SSBG3854X0DD6FAQQQQ","prath-mode","When the user wants a goal sent to one skill or one delivery chain.","https:\u002F\u002Fgithub.com\u002Fprathamdby\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fprath-mode\u002FSKILL.md",[],[]]