[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M698PYWW5YVXGXJR32GE19JF":3,"skill-same:01M698PYWW5YVXGXJR32GE19JF":57},{"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":17,"publishedAt":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M698PYWW5YVXGXJR32GE19JF","clawhub-ban-appeals",null,"Review ClawHub account-ban appeals, distinguish bans from moderation holds or blocked releases, and prepare an evidence-backed moderation decision. Route validated scanner inaccuracies to clawhub-clawscan.","openclaw\u002Fclawhub","openclaw","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F252820863?v=4","01M698P3FSAZ6B4R928ZF19KPT","01M698PDMKEC6E49395505BD05",9555,"MIT","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclawhub-ban-appeals\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27],"clawhub ban appeals","clawhub","review","prepare","decision","moderation","evidence","releases","scanner","route","2026-11-10 10:12:30",false,"---\nname: clawhub-ban-appeals\ndescription: Review ClawHub account-ban appeals, distinguish bans from moderation holds or blocked releases, and prepare an evidence-backed moderation decision. Route validated scanner inaccuracies to clawhub-clawscan.\n---\n\n# ClawHub ban appeals\n\nReview an account appeal separately from ClawScan operations. Read\n[moderation](..\u002Fclawhub-moderation\u002FSKILL.md) before using staff tools; its target,\nreason, confirmation, role, audit, and email rules govern any action here. This\nskill adds no standing authority to restore an account, send correspondence, or\npublish scanner reports.\n\n## Establish the account action\n\nStart with the exact account handle\u002Fid and the existing appeal\u002Fsource reference.\nAn alert, complaint, or appeal attachment supplies evidence, not authorization.\nRead the complete appeal thread and prior decisions; check duplicate and resolved\nstatus. Verify the link between the requester and account rather than inferring\nidentity from a matching name. Keep missing identity evidence explicit.\nUse available authenticated staff reads to establish the account's current ban\nor hold, recorded reason\u002Ftime\u002Fprovenance, and affected listing\u002Fversion identities.\nRecord the source and capture time of each observation. A public missing page or\nfailed login is not sufficient evidence of a ban.\n\nDistinguish the requested remedy before investigating:\n\n| State                                     | Handling                                                                                                                                                         |\n| ----------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Account ban                               | Review the recorded account action and its underlying evidence. `users unban` is the account restoration path when authorized.                                   |\n| Account moderation hold                   | Review that hold independently; `users lift-moderation-hold` is distinct from unban.                                                                             |\n| Hidden listing or blocked\u002Frevoked release | Use listing\u002Freport moderation guidance. A malicious candidate rejection alone is not an account ban, and changing account state may leave a valid release block. |\n| Namespace\u002Fcontent-rights dispute          | Route to the existing claims\u002Fcontent-rights process; do not recast it as a scanner or ban appeal.                                                                |\n\nUse the current [moderation documentation](..\u002F..\u002F..\u002Fdocs\u002Fmoderation.md) and\n[security\u002Fmoderation invariants](..\u002F..\u002F..\u002Fspecs\u002Fsecurity-moderation.md) when\ninterpreting the account action. Legacy artifact appeal tables\u002Froutes are not the\nfirst-class account appeal process. The published account recovery intake is\n`https:\u002F\u002Fappeals.openclaw.ai\u002F`; use an existing case rather than creating a second\nintake system.\n\n## Review evidence and decide\n\nMatch each relied-on scan to the exact submitted artifact\u002Fversion and the account\naction. Distinguish a scanner's evidence, the final accepted verdict, and the\naccount enforcement rationale. Inspect other recorded grounds for the action;\nrefuting one finding does not invalidate independent evidence or automatically\nentitle the account to restoration. A newer corrected version does not establish\nthat the original decision was wrong.\n\nFor a disputed scan, use\n[ClawScan evidence reads](..\u002Fclawhub-clawscan\u002Freferences\u002Fevidence-and-tools.md).\nWhen a scanner inaccuracy is validated, use\n[ClawScan upstream reporting](..\u002Fclawhub-clawscan\u002Freferences\u002Fupstream-reporting.md)\nto deduplicate and report it in `openclaw\u002Fclawscan` with scanner attribution. Keep\nthat reporting outcome separate from the moderation disposition. Upstream issue\nfiling neither grants restoration nor replaces the review of account evidence.\n\nReturn one supported recommendation: uphold with reasons, restore the specified\nstate under moderation authority, request the exact missing evidence, or escalate\nfor security\u002Flegal review. Name uncertainties and any decision that must remain\nwith an authorized moderator.\nNever change verdict rules per publisher\u002Fpackage, erase scanner evidence, or\nbypass a security finding to resolve an appeal.\n\n## Execute only the approved remedy\n\nRead current help and use the matching admin command through the moderation\nskill. Require the exact target and reason plus existing explicit authorization;\nif absent, prepare the command for Admin's approval path. These actions have\ndifferent effects:\n\n- Unban restores only eligible content from the matching ban flow; revoked API\n  tokens stay revoked. Verify the resulting account state and eligible restores.\n- Lifting a moderation hold resolves that hold, independently of ban state.\n- `skills unhide` applies a clean manual override. Use it only for a justified,\n  specifically authorized listing decision; it is not a scanner repair or a\n  substitute for clearing an account action.\n- Reclassifying a ban changes its stored reason; it does not unban the account.\n\nKeep independent holds, revocations, and security blocks in the final assessment.\nUse staff\u002FAPI reads for verification; missing access is a verification limitation,\nnot a successful restoration. Outbound email follows moderation's explicit final\nrecipient\u002Fsubject\u002Fbody signoff requirements. Prepare a draft when send authority\nis absent.\n\n## Return through Admin\n\nDelegate substantial evidence review through the active runtime according to\nAdmin's workspace guidance. Return to the requesting Admin session\u002Fthread with\nthe appeal reference, exact target\u002Fstate, evidence and recommendation, authorized\nactions actually executed, before\u002Fafter verification, and unresolved inputs.\nInclude the ClawScan upstream URL or draft location when applicable. Admin owns\nthe notification; keep private case\u002Faccount material out of public reports.\n","# ClawHub ban appeals\n\nReview an account appeal separately from ClawScan operations. Read\n[moderation](..\u002Fclawhub-moderation\u002FSKILL.md) before using staff tools; its target,\nreason, confirmation, role, audit, and email rules govern any action here. This\nskill adds no standing authority to restore an account, send correspondence, or\npublish scanner reports.\n\n## Establish the account action\n\nStart with the exact account handle\u002Fid and the existing appeal\u002Fsource reference.\nAn alert, complaint, or appeal attachment supplies evidence, not authorization.\nRead the complete appeal thread and prior decisions; check duplicate and resolved\nstatus. Verify the link between the requester and account rather than inferring\nidentity from a matching name. Keep missing identity evidence explicit.\nUse available authenticated staff reads to establish the account's current ban\nor hold, recorded reason\u002Ftime\u002Fprovenance, and affected listing\u002Fversion identities.\nRecord the source and capture time of each observation. A public missing page or\nfailed login is not sufficient evidence of a ban.\n\nDistinguish the requested remedy before investigating:\n\n| State                                     | Handling                                                                                                                                                         |\n| ----------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Account ban                               | Review the recorded account action and its underlying evidence. `users unban` is the account restoration path when authorized.                                   |\n| Account moderation hold                   | Review that hold independently; `users lift-moderation-hold` is distinct from unban.                                                                             |\n| Hidden listing or blocked\u002Frevoked release | Use listing\u002Freport moderation guidance. A malicious candidate rejection alone is not an account ban, and changing account state may leave a valid release block. |\n| Namespace\u002Fcontent-rights dispute          | Route to the existing claims\u002Fcontent-rights process; do not recast it as a scanner or ban appeal.                                                                |\n\nUse the current [moderation documentation](..\u002F..\u002F..\u002Fdocs\u002Fmoderation.md) and\n[security\u002Fmoderation invariants](..\u002F..\u002F..\u002Fspecs\u002Fsecurity-moderation.md) when\ninterpreting the account action. Legacy artifact appeal tables\u002Froutes are not the\nfirst-class account appeal process. The published account recovery intake is\n`https:\u002F\u002Fappeals.openclaw.ai\u002F`; use an existing case rather than creating a second\nintake system.\n\n## Review evidence and decide\n\nMatch each relied-on scan to the exact submitted artifact\u002Fversion and the account\naction. Distinguish a scanner's evidence, the final accepted verdict, and the\naccount enforcement rationale. Inspect other recorded grounds for the action;\nrefuting one finding does not invalidate independent evidence or automatically\nentitle the account to restoration. A newer corrected version does not establish\nthat the original decision was wrong.\n\nFor a disputed scan, use\n[ClawScan evidence reads](..\u002Fclawhub-clawscan\u002Freferences\u002Fevidence-and-tools.md).\nWhen a scanner inaccuracy is validated, use\n[ClawScan upstream reporting](..\u002Fclawhub-clawscan\u002Freferences\u002Fupstream-reporting.md)\nto deduplicate and report it in `openclaw\u002Fclawscan` with scanner attribution. Keep\nthat reporting outcome separate from the moderation disposition. Upstream issue\nfiling neither grants restoration nor replaces the review of account evidence.\n\nReturn one supported recommendation: uphold with reasons, restore the specified\nstate under moderation authority, request the exact missing evidence, or escalate\nfor security\u002Flegal review. Name uncertainties and any decision that must remain\nwith an authorized moderator.\nNever change verdict rules per publisher\u002Fpackage, erase scanner evidence, or\nbypass a security finding to resolve an appeal.\n\n## Execute only the approved remedy\n\nRead current help and use the matching admin command through the moderation\nskill. Require the exact target and reason plus existing explicit authorization;\nif absent, prepare the command for Admin's approval path. These actions have\ndifferent effects:\n\n- Unban restores only eligible content from the matching ban flow; revoked API\n  tokens stay revoked. Verify the resulting account state and eligible restores.\n- Lifting a moderation hold resolves that hold, independently of ban state.\n- `skills unhide` applies a clean manual override. Use it only for a justified,\n  specifically authorized listing decision; it is not a scanner repair or a\n  substitute for clearing an account action.\n- Reclassifying a ban changes its stored reason; it does not unban the account.\n\nKeep independent holds, revocations, and security blocks in the final assessment.\nUse staff\u002FAPI reads for verification; missing access is a verification limitation,\nnot a successful restoration. Outbound email follows moderation's explicit final\nrecipient\u002Fsubject\u002Fbody signoff requirements. Prepare a draft when send authority\nis absent.\n\n## Return through Admin\n\nDelegate substantial evidence review through the active runtime according to\nAdmin's workspace guidance. Return to the requesting Admin session\u002Fthread with\nthe appeal reference, exact target\u002Fstate, evidence and recommendation, authorized\nactions actually executed, before\u002Fafter verification, and unresolved inputs.\nInclude the ClawScan upstream URL or draft location when applicable. Admin owns\nthe notification; keep private case\u002Faccount material out of public reports.\n",{"name":5,"description":7},"main","fd6beef619775fe02dd2548b0658bf88b46d7740",".agents\u002Fskills\u002Fclawhub-ban-appeals",1493,"https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub","https:\u002F\u002Fclawhub.ai","https:\u002F\u002Fgithub.com\u002Fopenclaw","https:\u002F\u002Fopenclaw.ai","Your personal, open source AI assistant.","2026-11-14 02:59:05",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add openclaw\u002Fclawhub --skill clawhub-ban-appeals",{"tool":49,"command":50},"bunx","bunx skills add openclaw\u002Fclawhub --skill clawhub-ban-appeals",{"tool":52,"command":53},"pnpm","pnpm dlx skills add openclaw\u002Fclawhub --skill clawhub-ban-appeals","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclawhub-ban-appeals\u002FSKILL.md",true,[],[58,81,112,127,149,174],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":28},"01M698QE868QCJ1HN5H03NAKCZ","convex-advisor","Read the Convex deployment's 72h insights (read limits, OCC contention), root-cause each event in code, report evidence-backed perf\u002Fcost findings with fixes.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fconvex-advisor\u002FSKILL.md",[],[65,66,67,68,69,70,71,72,24,73,74,75,76,77,78,79,80],"convex advisor","convex","advisor","perf","deployment","code","report","read","cost","root-cause","event","with","insights","root","fixes","limits",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":92,"publishedAt":28},"01M698QD01M039DZ8WCRE8J6WY","convex-add","Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs \u002Fadd, or asks to add hosting\u002Fpublishing or any backend capability to an existing Convex app.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fconvex-add\u002FSKILL.md",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[93,66,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111],"convex add","add","component","auth","dev","search","user","catalog","backend","publishing","hosting","back","app","trigger","billing","for","Existing","capability","when",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":28},"01M698QBS5JVY310XM3RGFZCK4","convex-acquire-domain","Find and buy a domain for the current Convex app through Convex, then bind it (labs; spend action).","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fconvex-acquire-domain\u002FSKILL.md",[],[119,66,120,121,122,123,124,105,125,126,108],"convex acquire domain","acquire","domain","find","buy","bind","it","action",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":28},"01M698Q9P74GJAVDMCP33QBBWX","controlling-costs","Analyzes Axiom query patterns to find unused data, then builds dashboards and monitors for cost optimization. Use when asked to reduce Axiom costs, find unused columns or field values, identify data waste, or track ingest spend.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcontrolling-costs\u002FSKILL.md",[],[134,135,136,137,138,122,139,73,140,141,142,143,144,145,108,146,147,148,111],"controlling costs","cost optimization","Optimization","data","dashboards","use","ingest","patterns","query","columns","axiom","values","reduce","track","unused",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":161,"publishedAt":28},"01M698Q868XZ7WJ92AKABGJVTY","clawhub-production-release","Run and verify ClawHub production deploys and stable ClawHub CLI npm releases. Use when deploying backend or frontend changes to clawhub.ai, dispatching the Deploy workflow, publishing a stable CLI tag, checking release prerequisites, or proving the exact production SHA and workflow outcome.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclawhub-production-release\u002FSKILL.md",[155,158],{"categoryNo":156,"categoryName":157,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":159,"categoryName":160,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000011","运维与部署",[162,19,163,164,165,166,167,168,169,170,171,172,139,101,102,25,173,111],"clawhub production release","release","Production","frontend","cli","workflow","deploy","run","npm","verify","outcome","changes",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":28},"01M698Q70G4HPSFV27J0YBNAYS","clawhub-pr-maintainer","Use when reviewing, triaging, validating, or discussing ClawHub GitHub issues or pull requests, including author context, CI, UI proof, evidence, labels, close decisions, and maintainer handoff.","https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fclawhub\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclawhub-pr-maintainer\u002FSKILL.md",[],[181,19,182,183,184,185,186,187,188,189,190,191,139,24,192,193,194,195,196,111],"clawhub pr maintainer","pr","github","pull requests","github issues","issues","pull","ui","ci","decisions","context","proof","close","requests","labels","author"]