[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M698RM0PA5ZM69GGT4ABAV92":3,"skill-same:01M698RM0PA5ZM69GGT4ABAV92":58},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M698RM0PA5ZM69GGT4ABAV92","handoff",null,"Clipboard-ready handoff prompt for another agent to investigate or continue a task.","openclaw\u002Fagent-skills","openclaw","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F252820863?v=4","01M698P3FSAZ6B4R928ZF19KPT","01M698R9TBKA3SKB6WVC50J9NJ",1119,"MIT","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,23,24,25,26,27,28,29],"investigate","continue","prompt","ready","clipboard","task","for","2026-11-10 10:12:30",false,"---\nname: handoff\ndescription: \"Clipboard-ready handoff prompt for another agent to investigate or continue a task.\"\n---\n\n# Handoff\n\nWrite a clipboard-ready prompt for another agent to investigate, discuss, or work\non a specific task.\n\nUse when the user asks for `handoff \u003Ctask>`, \"write a handoff\", \"delegate this\",\nor wants a prompt for another agent.\n\n## Workflow\n\n1. Identify the task from the user text. If the user gives only a short label,\n   infer from the current repo, recent discussion, branch name, linked issue\u002FPR,\n   docs, and obvious nearby context.\n2. Gather enough context to write a useful handoff: repo\u002Fproduct identity,\n   relevant issue\u002FPR\u002Fbranch names, likely modules, constraints, and known\n   symptoms. Do not perform the receiving agent's full independent review or\n   decide the final technical direction for them.\n3. Write a standalone prompt preserving the requested mode, existing authority,\n   accepted decisions, completed proof, remaining work, and completion condition.\n4. Copy the full prompt to the clipboard.\n5. Final reply: terse confirmation with the task title. Do not paste the full\n   prompt unless the user asks.\n\n## Handoff Prompt Rules\n\nThe prompt must:\n\n- Preserve the user's requested mode: investigation, discussion, or execution.\n- Carry existing authorization and its limits without granting new authority.\n- Ask the receiving agent to verify live state and unresolved assumptions.\n  Size independent review to the remaining uncertainty and repository requirements.\n- Preserve accepted decisions and completed work unless new evidence invalidates\n  them. An execution handoff must not reset the task to a proposal.\n- Assume the agent starts in the repo, a parent directory, a workspace directory,\n  or a home directory and can find the repo itself.\n- Avoid filesystem paths. No absolute paths, home-directory paths, checkout\n  names, or repo-relative file paths unless the user explicitly requests them.\n- Use portable anchors instead: repo owner\u002Fname, product\u002Fmodule names, issue\u002FPR\n  URLs, branch names, package\u002Fplugin names, public symbols, command names, config\n  keys, exact error text, docs titles, and search terms.\n- Include enough context for the receiving agent to get the right repo, boundary,\n  and desired outcome.\n- Include constraints, non-goals, validation expectations, and the desired\n  output shape.\n- Tell the receiving agent to re-check live repo\u002FGitHub\u002FCI state where relevant.\n- Tell the receiving agent not to push, merge, close issues\u002FPRs, label, or post\n  public comments unless the handoff explicitly asks for it.\n\n## Prompt Template\n\nAdapt this shape to the requested mode:\n\n```text\n\u003CInvestigate, discuss, or continue execution of>: \u003Cshort task title>\n\nContext:\n- \u003Cportable repo\u002Fproduct context>\n- \u003Cwhat triggered this task>\n- \u003Cknown current state, branch\u002Fissue\u002FPR names or URLs if relevant>\n- \u003Cimportant constraints and ownership boundaries>\n- \u003Cexisting authority, accepted decisions, completed work, and remaining gaps>\n\nResume:\n- Find the right repository from the current directory, a parent directory, or the usual workspace.\n- Read the local agent\u002Frepo instructions.\n- Inspect the relevant code, docs, tests, recent commits, and linked issue\u002FPR state.\n- Verify unresolved assumptions without repeating completed work or reopening settled decisions absent new evidence.\n- Call out stale assumptions, hidden risks, and anything that should stop the work.\n\nTask:\n- \u003Cnext investigation or already-authorized implementation>\n- \u003Cexpected behavior or decision criteria>\n- \u003Cnon-goals>\n- \u003Ccompletion condition and concrete stop conditions>\n\nValidation:\n- \u003Cfocused tests\u002Fchecks\u002Flive proof expected>\n- \u003Cwhat evidence should be included>\n- \u003Cwhat is explicitly not required>\n\nOutput:\n- For investigation, report findings and recommendation.\n- For execution, complete the authorized work and report the result or precise blocker.\n- If you edit code, keep changes scoped and report exact proof run.\n- Do not push, merge, close issues\u002FPRs, label, or post public comments unless explicitly told.\n```\n\n## Clipboard\n\nOn macOS:\n\n```sh\npbcopy \u003C \u002Ftmp\u002Fhandoff-prompt.txt\n```\n\nUse a temp file or pipe. Avoid inline shell quoting for prompts containing\nbackticks, `$`, quotes, or user text.\n\nIf `pbcopy` is unavailable, use the obvious platform clipboard tool (`wl-copy`,\n`xclip`, `clip.exe`) or print the prompt and say clipboard copy was unavailable.\n\n## Quality Bar\n\n- No invented facts. Mark reviewed facts as such only after checking them.\n- No path leakage. Rewrite any accidental path as a symbol, module, command,\n  issue\u002FPR URL, or search term.\n- Enough context for a fresh agent to orient; no giant brain dump.\n- A fresh agent can continue in the requested mode without inventing authority\n  or losing existing authorization.\n","# Handoff\n\nWrite a clipboard-ready prompt for another agent to investigate, discuss, or work\non a specific task.\n\nUse when the user asks for `handoff \u003Ctask>`, \"write a handoff\", \"delegate this\",\nor wants a prompt for another agent.\n\n## Workflow\n\n1. Identify the task from the user text. If the user gives only a short label,\n   infer from the current repo, recent discussion, branch name, linked issue\u002FPR,\n   docs, and obvious nearby context.\n2. Gather enough context to write a useful handoff: repo\u002Fproduct identity,\n   relevant issue\u002FPR\u002Fbranch names, likely modules, constraints, and known\n   symptoms. Do not perform the receiving agent's full independent review or\n   decide the final technical direction for them.\n3. Write a standalone prompt preserving the requested mode, existing authority,\n   accepted decisions, completed proof, remaining work, and completion condition.\n4. Copy the full prompt to the clipboard.\n5. Final reply: terse confirmation with the task title. Do not paste the full\n   prompt unless the user asks.\n\n## Handoff Prompt Rules\n\nThe prompt must:\n\n- Preserve the user's requested mode: investigation, discussion, or execution.\n- Carry existing authorization and its limits without granting new authority.\n- Ask the receiving agent to verify live state and unresolved assumptions.\n  Size independent review to the remaining uncertainty and repository requirements.\n- Preserve accepted decisions and completed work unless new evidence invalidates\n  them. An execution handoff must not reset the task to a proposal.\n- Assume the agent starts in the repo, a parent directory, a workspace directory,\n  or a home directory and can find the repo itself.\n- Avoid filesystem paths. No absolute paths, home-directory paths, checkout\n  names, or repo-relative file paths unless the user explicitly requests them.\n- Use portable anchors instead: repo owner\u002Fname, product\u002Fmodule names, issue\u002FPR\n  URLs, branch names, package\u002Fplugin names, public symbols, command names, config\n  keys, exact error text, docs titles, and search terms.\n- Include enough context for the receiving agent to get the right repo, boundary,\n  and desired outcome.\n- Include constraints, non-goals, validation expectations, and the desired\n  output shape.\n- Tell the receiving agent to re-check live repo\u002FGitHub\u002FCI state where relevant.\n- Tell the receiving agent not to push, merge, close issues\u002FPRs, label, or post\n  public comments unless the handoff explicitly asks for it.\n\n## Prompt Template\n\nAdapt this shape to the requested mode:\n\n```text\n\u003CInvestigate, discuss, or continue execution of>: \u003Cshort task title>\n\nContext:\n- \u003Cportable repo\u002Fproduct context>\n- \u003Cwhat triggered this task>\n- \u003Cknown current state, branch\u002Fissue\u002FPR names or URLs if relevant>\n- \u003Cimportant constraints and ownership boundaries>\n- \u003Cexisting authority, accepted decisions, completed work, and remaining gaps>\n\nResume:\n- Find the right repository from the current directory, a parent directory, or the usual workspace.\n- Read the local agent\u002Frepo instructions.\n- Inspect the relevant code, docs, tests, recent commits, and linked issue\u002FPR state.\n- Verify unresolved assumptions without repeating completed work or reopening settled decisions absent new evidence.\n- Call out stale assumptions, hidden risks, and anything that should stop the work.\n\nTask:\n- \u003Cnext investigation or already-authorized implementation>\n- \u003Cexpected behavior or decision criteria>\n- \u003Cnon-goals>\n- \u003Ccompletion condition and concrete stop conditions>\n\nValidation:\n- \u003Cfocused tests\u002Fchecks\u002Flive proof expected>\n- \u003Cwhat evidence should be included>\n- \u003Cwhat is explicitly not required>\n\nOutput:\n- For investigation, report findings and recommendation.\n- For execution, complete the authorized work and report the result or precise blocker.\n- If you edit code, keep changes scoped and report exact proof run.\n- Do not push, merge, close issues\u002FPRs, label, or post public comments unless explicitly told.\n```\n\n## Clipboard\n\nOn macOS:\n\n```sh\npbcopy \u003C \u002Ftmp\u002Fhandoff-prompt.txt\n```\n\nUse a temp file or pipe. Avoid inline shell quoting for prompts containing\nbackticks, `$`, quotes, or user text.\n\nIf `pbcopy` is unavailable, use the obvious platform clipboard tool (`wl-copy`,\n`xclip`, `clip.exe`) or print the prompt and say clipboard copy was unavailable.\n\n## Quality Bar\n\n- No invented facts. Mark reviewed facts as such only after checking them.\n- No path leakage. Rewrite any accidental path as a symbol, module, command,\n  issue\u002FPR URL, or search term.\n- Enough context for a fresh agent to orient; no giant brain dump.\n- A fresh agent can continue in the requested mode without inventing authority\n  or losing existing authorization.\n",{"name":5,"description":7},"main","c7cde4a7bc4b419f3f3869390a5e06c341fae07b","skills\u002Fhandoff",123,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills","https:\u002F\u002Fgithub.com\u002Fopenclaw","https:\u002F\u002Fopenclaw.ai","Your personal, open source AI assistant.","2026-11-12 21:54:01",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add openclaw\u002Fagent-skills --skill handoff",{"tool":50,"command":51},"bunx","bunx skills add openclaw\u002Fagent-skills --skill handoff",{"tool":53,"command":54},"pnpm","pnpm dlx skills add openclaw\u002Fagent-skills --skill handoff","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002FSKILL.md",true,[],[59,82,101,118,139,161],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":30},"01M698RR7FCM03FP4QX4D38ECP","team-handoff","Hand local work to a shared OpenClaw Gateway: start a worktree session there as yourself in one request, seeded with a handoff, and get the session URL back.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fteam-handoff\u002FSKILL.md",[],[66,5,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,9],"team","team handoff","work","request","hand","URL","start","local","session","worktree","get","as","with","gateway","back","shared",{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":30},"01M698RP6WVCYC38YPEECMADB5","session-viewer","Render Codex, Claude Code, OpenClaw, or Pi session JSONL transcripts as a searchable, shareable single-file HTML viewer.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsession-viewer\u002FSKILL.md",[],[74,89,90,91,92,93,94,95,96,77,97,9,98,99,100],"session viewer","viewer","file","transcripts","render","pi","codex","single-file","jsonl","code","single","html",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":30},"01M698RN1Q9WRY11XB9CBEY6JN","readme-standard","House README standard: structure, badge row, tone, per-archetype templates, and verification gates for steipete\u002Fopenclaw repos.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Freadme-standard\u002FSKILL.md",[],[108,109,110,111,112,113,114,115,29,116,9,117],"readme standard","README","standard","tone","gates","structure","templates","repos","verification","verification gates",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":30},"01M698RJKDRFJJT0755672M39N","crabbox","Crabbox\u002FTestbox remote proof: portable provider routing, untrusted isolation, Linux\u002FmacOS\u002FWindows\u002FWSL2, live E2E, diagnostics, cleanup.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fcrabbox\u002FSKILL.md",[],[120,125,126,127,128,129,130,131,132,133,134,135,136,137,138],"routing","macos","windows","diagnostics","provider routing","portable","isolation","live","proof","cleanup","e2e","remote","linux","provider",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":150,"publishedAt":30},"01M698RHA9XNH7TEX0BKY9SJ0E","behavior-validator","Source-blind user behavior validation against a prewritten contract for apps, CLIs, APIs, and generated artifacts.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbehavior-validator\u002FSKILL.md",[145],{"categoryNo":146,"categoryName":147,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[151,152,153,154,155,156,157,158,159,160,29],"validator","behavior","behavior validator","validation","user","artifacts","apps","source","generated","contract",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":30},"01M698RFQVT9KDH7HHBGCD6C50","beam","Share a redacted coding session or hand its logical conversation to an authenticated OpenClaw Gateway.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbeam\u002FSKILL.md",[],[163,168,70,9,169,79,170,74],"share","conversation","coding"]