[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M698RB8FQQW9VNVDCYGNE05C":3,"skill-same:01M698RB8FQQW9VNVDCYGNE05C":76},{"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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M698RB8FQQW9VNVDCYGNE05C","agent-transcript",null,"Requested GitHub PR\u002Fissue agent transcripts: redact, trim, preview, and insert safely.","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\u002Fagent-transcript\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31],"agent transcript","transcript","github","pr","issue","github pr","preview","transcripts","trim","2026-11-10 10:12:30",false,"---\nname: agent-transcript\ndescription: \"Requested GitHub PR\u002Fissue agent transcripts: redact, trim, preview, and insert safely.\"\n---\n\n# Agent Transcript\n\nUse only when the user explicitly requests a transcript or preview. Omit by\ndefault; never offer one or ask whether to include one during ordinary PR work.\nA preview request alone does not authorize publication.\n\nFor a session hosted at `*.openclaw.ai`, use native session sharing when sharing\nis requested; export a separate transcript only when the user explicitly asks\nfor that copy. Identify hosting from the current session URL, not a repository\nURL or deployment\u002Ftest target. Do not offer separate exports.\n\n## Prepare Locally\n\nDefault file discovery\u002Frendering reads local Codex, Claude, Pi, and OpenClaw\nlogs without network calls. Never upload raw logs.\n\nResolve `TRANSCRIPT_SKILL_DIR` to the directory containing this `SKILL.md`.\nInvoke that installation without changing the consumer's working directory.\n\n```bash\n\"$TRANSCRIPT_SKILL_DIR\u002Fscripts\u002Fagent-transcript\" find \\\n  --query \"$PR_TITLE $BRANCH_OR_PR_URL\" --cwd \"$PWD\" --since-days 14\n\"$TRANSCRIPT_SKILL_DIR\u002Fscripts\u002Fagent-transcript\" render \\\n  --session \"$SESSION_JSONL\" --out \u002Ftmp\u002Fagent-transcript.md\n```\n\n`find` scans the newest 400 matching logs by default; `--max-files N` widens\nlocal discovery. Treat matches as candidates, not proof of scope.\n`find` and `html` count up to 20,000 JSONL files across all roots, including old\nfiles, and fail when another exceeds the cap. `--max-discovery-files N` accepts\na positive integer override; prefer narrowing roots before raising it.\n\nFile rendering reads at most 8 MiB per session from its head and tail and parses\nat most 12,000 lines. `--max-read-bytes N` changes the byte limit. Preserve the\nvisible partial-transcript notice and `sourceTruncated` stats through trimming,\npreview, and insertion; omitted source must never be described as complete.\nThese are file-read limits, not limits on the separate app-server rendering mode.\nShort filesystem reads are retried. Unexpected EOF stops rendering or discovery\ninstead of treating incomplete input as a complete session.\n\nAutomatically trim the rendered Markdown **before showing, previewing, or\ninserting it**. Keep only task-relevant user prompts, visible decisions, terse\ntool summaries, and proof outcomes. Use the PR\u002Fissue goal, branch, and changed\nfiles to remove unrelated earlier\u002Flater turns. Drop system\u002Fdeveloper prompts,\nreasoning, raw tool output, environment data, local paths, credentials,\nbrowser\u002Fsession\u002Fcookie details, and auth URLs. Inspect the trimmed result;\nhelper redaction is not sufficient disclosure review. Unresolved sensitive\ncontent means omit the transcript.\n\n## Preview And Insert\n\nShow the trimmed Markdown for a requested preview. If HTML is requested, build\nthe local preview from that trimmed content. The helper's `preview`, `html`, and\n`append-body` modes render the session again; they do not consume an edited\nMarkdown file and can reintroduce removed turns. Do not use their untrimmed\noutput as the approved artifact.\n\nInsert only the inspected, scoped text when the user's authorization specifically\ncovers publishing that transcript to the named PR\u002Fissue. Generating or previewing\na transcript does not authorize publication, even when ordinary PR creation or\nediting is already approved. If that scope is missing, show the trimmed result\nand obtain publication authorization before insertion. Existing explicit\nauthorization covering transcript publication needs no repeat confirmation.\nKeep the collapsed `\u003Cdetails>` section and replace existing transcript markers\ninstead of duplicating them. No safe match means continue the PR work without\ntranscript or placeholder; explain the omission when it prevents the explicitly\nrequested transcript. Do not promote transcript inclusion as a review priority\nrequirement.\n\n## Validate Helper Changes\n\n```bash\nnode --test skills\u002Fagent-transcript\u002Fscripts\u002Fagent-transcript.test.mjs\n```\n\nFor a downstream `.agents\u002Fskills` copy, run that test command from `.agents\u002F`\nso the test's relative helper path resolves. Use synthetic logs and isolated\ndiscovery roots; never discover real user logs just to validate this skill.\n","# Agent Transcript\n\nUse only when the user explicitly requests a transcript or preview. Omit by\ndefault; never offer one or ask whether to include one during ordinary PR work.\nA preview request alone does not authorize publication.\n\nFor a session hosted at `*.openclaw.ai`, use native session sharing when sharing\nis requested; export a separate transcript only when the user explicitly asks\nfor that copy. Identify hosting from the current session URL, not a repository\nURL or deployment\u002Ftest target. Do not offer separate exports.\n\n## Prepare Locally\n\nDefault file discovery\u002Frendering reads local Codex, Claude, Pi, and OpenClaw\nlogs without network calls. Never upload raw logs.\n\nResolve `TRANSCRIPT_SKILL_DIR` to the directory containing this `SKILL.md`.\nInvoke that installation without changing the consumer's working directory.\n\n```bash\n\"$TRANSCRIPT_SKILL_DIR\u002Fscripts\u002Fagent-transcript\" find \\\n  --query \"$PR_TITLE $BRANCH_OR_PR_URL\" --cwd \"$PWD\" --since-days 14\n\"$TRANSCRIPT_SKILL_DIR\u002Fscripts\u002Fagent-transcript\" render \\\n  --session \"$SESSION_JSONL\" --out \u002Ftmp\u002Fagent-transcript.md\n```\n\n`find` scans the newest 400 matching logs by default; `--max-files N` widens\nlocal discovery. Treat matches as candidates, not proof of scope.\n`find` and `html` count up to 20,000 JSONL files across all roots, including old\nfiles, and fail when another exceeds the cap. `--max-discovery-files N` accepts\na positive integer override; prefer narrowing roots before raising it.\n\nFile rendering reads at most 8 MiB per session from its head and tail and parses\nat most 12,000 lines. `--max-read-bytes N` changes the byte limit. Preserve the\nvisible partial-transcript notice and `sourceTruncated` stats through trimming,\npreview, and insertion; omitted source must never be described as complete.\nThese are file-read limits, not limits on the separate app-server rendering mode.\nShort filesystem reads are retried. Unexpected EOF stops rendering or discovery\ninstead of treating incomplete input as a complete session.\n\nAutomatically trim the rendered Markdown **before showing, previewing, or\ninserting it**. Keep only task-relevant user prompts, visible decisions, terse\ntool summaries, and proof outcomes. Use the PR\u002Fissue goal, branch, and changed\nfiles to remove unrelated earlier\u002Flater turns. Drop system\u002Fdeveloper prompts,\nreasoning, raw tool output, environment data, local paths, credentials,\nbrowser\u002Fsession\u002Fcookie details, and auth URLs. Inspect the trimmed result;\nhelper redaction is not sufficient disclosure review. Unresolved sensitive\ncontent means omit the transcript.\n\n## Preview And Insert\n\nShow the trimmed Markdown for a requested preview. If HTML is requested, build\nthe local preview from that trimmed content. The helper's `preview`, `html`, and\n`append-body` modes render the session again; they do not consume an edited\nMarkdown file and can reintroduce removed turns. Do not use their untrimmed\noutput as the approved artifact.\n\nInsert only the inspected, scoped text when the user's authorization specifically\ncovers publishing that transcript to the named PR\u002Fissue. Generating or previewing\na transcript does not authorize publication, even when ordinary PR creation or\nediting is already approved. If that scope is missing, show the trimmed result\nand obtain publication authorization before insertion. Existing explicit\nauthorization covering transcript publication needs no repeat confirmation.\nKeep the collapsed `\u003Cdetails>` section and replace existing transcript markers\ninstead of duplicating them. No safe match means continue the PR work without\ntranscript or placeholder; explain the omission when it prevents the explicitly\nrequested transcript. Do not promote transcript inclusion as a review priority\nrequirement.\n\n## Validate Helper Changes\n\n```bash\nnode --test skills\u002Fagent-transcript\u002Fscripts\u002Fagent-transcript.test.mjs\n```\n\nFor a downstream `.agents\u002Fskills` copy, run that test command from `.agents\u002F`\nso the test's relative helper path resolves. Use synthetic logs and isolated\ndiscovery roots; never discover real user logs just to validate this skill.\n",{"name":5,"description":7},"main","c7cde4a7bc4b419f3f3869390a5e06c341fae07b","skills\u002Fagent-transcript",124,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills","https:\u002F\u002Fgithub.com\u002Fopenclaw","https:\u002F\u002Fopenclaw.ai","Your personal, open source AI assistant.","2026-11-14 16:54:37",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add openclaw\u002Fagent-skills --skill agent-transcript",{"tool":52,"command":53},"bunx","bunx skills add openclaw\u002Fagent-skills --skill agent-transcript",{"tool":55,"command":56},"pnpm","pnpm dlx skills add openclaw\u002Fagent-skills --skill agent-transcript","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fagent-transcript\u002FSKILL.md",true,[60,66,72],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"package.json","REFERENCE","参考文档",23,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fagent-transcript\u002Fpackage.json",{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"scripts\u002Fagent-transcript","SCRIPT","脚本",34195,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fagent-transcript\u002Fscripts\u002Fagent-transcript",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"scripts\u002Fagent-transcript.test.mjs",18190,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fagent-transcript\u002Fscripts\u002Fagent-transcript.test.mjs",[77,101,119,137,150,171],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":32},"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",[],[84,85,86,9,87,88,89,90,91,92,93,94,95,96,97,98,99,100],"handoff","team handoff","team","back","request","hand","URL","with","as","get","shared","local","session","work","start","gateway","worktree",{"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":32},"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",[],[108,109,96,110,111,92,112,113,114,115,116,9,30,117,118],"viewer","session viewer","single-file","code","render","html","pi","file","codex","single","jsonl",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":32},"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",[],[126,127,128,129,130,131,132,133,134,135,9,136],"standard","README","readme standard","for","verification gates","tone","structure","templates","verification","repos","gates",{"skillNo":138,"name":84,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":143,"publishedAt":32},"01M698RM0PA5ZM69GGT4ABAV92","Clipboard-ready handoff prompt for another agent to investigate or continue a task.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002FSKILL.md",[142],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[84,144,129,145,146,147,148,149],"clipboard","task","ready","prompt","continue","investigate",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":156,"publishedAt":32},"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",[],[152,157,158,159,160,161,162,163,164,165,166,167,168,169,170],"macos","live","provider","e2e","routing","cleanup","diagnostics","windows","linux","isolation","provider routing","portable","remote","proof",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":182,"publishedAt":32},"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",[177],{"categoryNo":178,"categoryName":179,"taxonomyType":180,"taxonomyTypeDesc":181},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[183,184,185,186,129,187,188,189,190,191,192],"behavior","behavior validator","validator","source","apps","contract","generated","user","artifacts","validation"]