[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6K2ZCZKJW73QXCS7TGENCMD":3,"skill-same:01M6K2ZCZKJW73QXCS7TGENCMD":81},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6K2ZCZKJW73QXCS7TGENCMD","rudder-desktop-dev-recovery-maintainer",null,"Use when Rudder Desktop or its development shell will not launch, gets stuck at login\u002Faccount gate, has pending device approval or local-session exchange, returns 401 during update, points at the wrong instance, hits migration-journal\u002Fschema-history divergence, needs a backup or rollback decision, fails during update\u002Frestart, triggers macOS Keychain\u002FsafeStorage alerts, or differs between dev and packaged execution. Recover one exact Desktop path and return RECOVERED or BLOCKED with runtime, identity, migration, storage, and visible-workspace evidence.","Undertone0809\u002Frudder","Undertone0809","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F72488598?v=4","01M6K2XANP3QJEF503JX2C693T","Zeeland","01M6K2XATQXEYF7N2QG8KZVEEY",296,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmaintainer\u002Frudder-desktop-dev-recovery-maintainer\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"rudder desktop dev recovery maintainer","desktop","dev","recovery","evidence","macos keychain","path","at","login","journal","alerts","local","restart","macos","returns","decision","keychain","update","identity","storage","2026-11-10 10:12:30",false,"---\nname: rudder-desktop-dev-recovery-maintainer\ndescription: \"Use when Rudder Desktop or its development shell will not launch, gets stuck at login\u002Faccount gate, has pending device approval or local-session exchange, returns 401 during update, points at the wrong instance, hits migration-journal\u002Fschema-history divergence, needs a backup or rollback decision, fails during update\u002Frestart, triggers macOS Keychain\u002FsafeStorage alerts, or differs between dev and packaged execution. Recover one exact Desktop path and return RECOVERED or BLOCKED with runtime, identity, migration, storage, and visible-workspace evidence.\"\n---\n\n# Rudder Desktop Dev Recovery Maintainer\n\nRecover the exact Desktop path the user named. API health alone is not Desktop\nhealth, and a healthy server belonging to another checkout is not evidence.\n\n## Exclusive Outcome\n\n- `RECOVERED`: the named Desktop path opened and its runtime identity plus\n  requested behavior were observed.\n- `BLOCKED`: the failing layer and remaining external decision or dependency are\n  proven.\n\nDo not claim recovery from code inspection, typecheck, a dry run, or an\nunrelated healthy server.\n\n## Classify The Target Before Resolving Runtime Identity\n\n### Development or worktree target\n\n1. Inspect the current checkout's `.rudder\u002Fconfig.json` and safe keys from\n   `.rudder\u002F.env`.\n2. Follow `scripts\u002Fdev-local-env.mjs` to resolve the effective Rudder home,\n   instance, port, and descriptor.\n3. Read that instance's `runtime\u002Fserver.json`; use its `apiUrl`.\n4. Only fall back to shared `3100\u002Fdev` after proving the checkout has no\n   isolation configuration.\n\nTypical current commands:\n\n```bash\npnpm dev\npnpm dev:watch\npnpm --filter @rudderhq\u002Fdesktop dev\npnpm --filter @rudderhq\u002Fdesktop smoke\n```\n\n### Packaged or prod-local target\n\nDo not infer packaged identity from the current checkout's dev configuration.\nUse installed-app boot evidence and the prod-local runtime. Unless an explicit\noverride or boot record proves otherwise, expect:\n\n- `RUDDER_LOCAL_ENV=prod_local`\n- instance `default`\n- descriptor `~\u002F.rudder\u002Finstances\u002Fdefault\u002Fruntime\u002Fserver.json`\n\nFor package-sensitive changes, the required proof path is:\n\n```bash\npnpm desktop:verify\n```\n\nIn either mode, verify that health matches the expected `instanceId`,\n`localEnv`, and `runtimeOwnerKind` before inspecting product data.\n\n## Migration-History Recovery Route\n\nUse this route whenever startup, update, or recovery mentions pending\nmigrations, the migration journal, schema history, a backup, rollback, or a\ncandidate built from another history. Before inspecting or changing a\nnon-empty instance, read `references\u002Fmigration-history-recovery.md`. It defines\nthe manifest\u002Flive-journal comparison, `forward-known`\u002F`unknown`\u002F\n`checksum-mismatch`\u002F`fork` classifications, verified backup and free-space\ngates, isolated forward validation, installed-app and same-workspace proof, and\nthe boundary between `RECOVERED` and candidate-only or backup-only evidence.\n\nMigration history is append-only: never delete journal rows, edit published SQL\nor `_journal.json` in place, or downgrade the original data directory. A named\ncandidate must explicitly recognize the live prefix before any forward path is\nconsidered.\n\n## Identity Continuity Route\n\nUse this route whenever the symptom mentions login, account gate, device\napproval, session exchange, a local `401`, Keychain\u002FsafeStorage, or a packaged\nrestart. A healthy API is only one stage in the path:\n\nBefore acting on one of these identity, session, or storage cases, read\n`references\u002Fidentity-continuity.md` for the non-secret state ledger and\nevidence boundaries.\n\n```text\ntarget identity\n-> API health\n-> runtime identity\n   +-> applicable auth\u002Fsession branch -+\n   +-> packaged storage\u002Fcodesign prerequisite -+\n-> first usable workspace\n-> restart persistence\n```\n\nUse a conditional ledger, not a mandatory linear login script. For an existing\ndurable session, verify the session's renderer and main-process use without\nforcing a fresh device approval. For a fresh account flow, require account\nauthorization, device approval, server exchange, and local claim only when that\ntarget actually uses them. A fixture, OAuth, email, or dev-bypass flow may have\ndifferent transitions. Storage\u002Fcodesign can fail before the account gate, so\nprobe it as a packaged startup prerequisite. Report the first missing\napplicable transition. A device authorization that is still pending or has\nexpired is a blocked login, not a recovered Desktop. Never request, print,\nexpose, or persist secrets. When a transcript is available, inspect tool-call\narguments and outputs for secret-bearing values; any exposure is a safety\nfailure.\n\nFor ordinary development use, `RUDDER_DESKTOP_AUTH_BYPASS=1 pnpm dev` is a\ndev-only usability route. Report it as an auth bypass and do not use it as\nevidence that real login, device approval, exchange, or claim works.\n\nFor update or blocker checks, separate runtime readiness from account-session\nreadiness. A healthy `\u002Fapi\u002Fhealth` from the resolved target plus a protected\n`\u002Fapi\u002Forgs` 401 means the runtime is healthy but the protected account-session\npath failed. Cookie reuse is only one hypothesis; also check session expiry,\nElectron partition, cookie scope, claim\u002Freadiness, and account or organization\npermission. Verify the actual main-process authenticated request before\nblaming the runtime or assuming a fetch injection is the fix.\n\nFor macOS storage symptoms, inspect the exact packaged artifact's signing\nidentity (`codesign -dvv`) and the compiled policy before launching it. An\nad-hoc\u002Funsigned packaged app is not equivalent to a signed package. If the\npolicy is memory-only, report the restart\u002Flogin persistence consequence. A\nrenderer screenshot, API health check, dev smoke, or synthetic Chromium fixture\ncannot prove that a native Keychain NSAlert did not appear. For that claim,\nrebuild the candidate, repeat packaged launches, and observe the native dialog\nsurface with an available system\u002FUI observation path; otherwise return\n`BLOCKED` with the missing proof.\n\n## Failure Layers\n\nClassify the first failing boundary:\n\n1. launcher, command, or port allocation;\n2. API process and health;\n3. embedded PostgreSQL and migrations;\n4. UI build\u002Fdev middleware;\n5. Electron main process and visible window;\n6. profile, instance, base URL, and organization data;\n7. packaged boot\u002Fresources;\n8. update download, replacement, progress pipe, restart, and relaunch;\n9. resource exhaustion or stale producer processes.\n\nTest one boundary at a time. Preserve unrelated dirty files and user data.\nNever reset or delete `~\u002F.rudder` as a diagnostic shortcut.\n\n## Recovery Loop\n\n1. Capture exact command, checkout, target mode, logs, and current processes.\n2. Resolve the correct descriptor and health payload.\n3. If the symptom is identity-related, record each continuity transition and\n   diagnose the first missing applicable transition.\n4. Find the first failing layer.\n5. Apply a scoped recovery. A request to fix or restore Desktop authorizes\n   necessary source repairs and verification; no second \"fix\" instruction is\n   needed. A diagnosis-only request remains read-only. Preserve user data and\n   use the packaged verification path when the repair affects installed behavior.\n6. Restart the same target path.\n7. Observe the Electron window or installed application.\n8. Verify runtime identity, the original symptom, and the first usable\n   post-login workspace when login was in scope.\n9. If persistence was in scope, perform a controlled restart and report what\n   survived. Do not infer persistence from an in-process success.\n\nFor update failures, reconstruct download, replacement, old-app exit,\nprogress-pipe behavior, and relaunch. Treat `EPIPE` as benign only when\nlifecycle evidence proves the reader exited normally and the new app reopened.\n\n## Report Format\n\n```text\nRESULT: RECOVERED | BLOCKED\nTarget mode:\nRuntime identity:\nIdentity continuity:\nFirst failing layer:\nAction:\nObserved Desktop proof:\nRestart\u002Fpersistence proof:\nRemaining blocker:\n```\n","# Rudder Desktop Dev Recovery Maintainer\n\nRecover the exact Desktop path the user named. API health alone is not Desktop\nhealth, and a healthy server belonging to another checkout is not evidence.\n\n## Exclusive Outcome\n\n- `RECOVERED`: the named Desktop path opened and its runtime identity plus\n  requested behavior were observed.\n- `BLOCKED`: the failing layer and remaining external decision or dependency are\n  proven.\n\nDo not claim recovery from code inspection, typecheck, a dry run, or an\nunrelated healthy server.\n\n## Classify The Target Before Resolving Runtime Identity\n\n### Development or worktree target\n\n1. Inspect the current checkout's `.rudder\u002Fconfig.json` and safe keys from\n   `.rudder\u002F.env`.\n2. Follow `scripts\u002Fdev-local-env.mjs` to resolve the effective Rudder home,\n   instance, port, and descriptor.\n3. Read that instance's `runtime\u002Fserver.json`; use its `apiUrl`.\n4. Only fall back to shared `3100\u002Fdev` after proving the checkout has no\n   isolation configuration.\n\nTypical current commands:\n\n```bash\npnpm dev\npnpm dev:watch\npnpm --filter @rudderhq\u002Fdesktop dev\npnpm --filter @rudderhq\u002Fdesktop smoke\n```\n\n### Packaged or prod-local target\n\nDo not infer packaged identity from the current checkout's dev configuration.\nUse installed-app boot evidence and the prod-local runtime. Unless an explicit\noverride or boot record proves otherwise, expect:\n\n- `RUDDER_LOCAL_ENV=prod_local`\n- instance `default`\n- descriptor `~\u002F.rudder\u002Finstances\u002Fdefault\u002Fruntime\u002Fserver.json`\n\nFor package-sensitive changes, the required proof path is:\n\n```bash\npnpm desktop:verify\n```\n\nIn either mode, verify that health matches the expected `instanceId`,\n`localEnv`, and `runtimeOwnerKind` before inspecting product data.\n\n## Migration-History Recovery Route\n\nUse this route whenever startup, update, or recovery mentions pending\nmigrations, the migration journal, schema history, a backup, rollback, or a\ncandidate built from another history. Before inspecting or changing a\nnon-empty instance, read `references\u002Fmigration-history-recovery.md`. It defines\nthe manifest\u002Flive-journal comparison, `forward-known`\u002F`unknown`\u002F\n`checksum-mismatch`\u002F`fork` classifications, verified backup and free-space\ngates, isolated forward validation, installed-app and same-workspace proof, and\nthe boundary between `RECOVERED` and candidate-only or backup-only evidence.\n\nMigration history is append-only: never delete journal rows, edit published SQL\nor `_journal.json` in place, or downgrade the original data directory. A named\ncandidate must explicitly recognize the live prefix before any forward path is\nconsidered.\n\n## Identity Continuity Route\n\nUse this route whenever the symptom mentions login, account gate, device\napproval, session exchange, a local `401`, Keychain\u002FsafeStorage, or a packaged\nrestart. A healthy API is only one stage in the path:\n\nBefore acting on one of these identity, session, or storage cases, read\n`references\u002Fidentity-continuity.md` for the non-secret state ledger and\nevidence boundaries.\n\n```text\ntarget identity\n-> API health\n-> runtime identity\n   +-> applicable auth\u002Fsession branch -+\n   +-> packaged storage\u002Fcodesign prerequisite -+\n-> first usable workspace\n-> restart persistence\n```\n\nUse a conditional ledger, not a mandatory linear login script. For an existing\ndurable session, verify the session's renderer and main-process use without\nforcing a fresh device approval. For a fresh account flow, require account\nauthorization, device approval, server exchange, and local claim only when that\ntarget actually uses them. A fixture, OAuth, email, or dev-bypass flow may have\ndifferent transitions. Storage\u002Fcodesign can fail before the account gate, so\nprobe it as a packaged startup prerequisite. Report the first missing\napplicable transition. A device authorization that is still pending or has\nexpired is a blocked login, not a recovered Desktop. Never request, print,\nexpose, or persist secrets. When a transcript is available, inspect tool-call\narguments and outputs for secret-bearing values; any exposure is a safety\nfailure.\n\nFor ordinary development use, `RUDDER_DESKTOP_AUTH_BYPASS=1 pnpm dev` is a\ndev-only usability route. Report it as an auth bypass and do not use it as\nevidence that real login, device approval, exchange, or claim works.\n\nFor update or blocker checks, separate runtime readiness from account-session\nreadiness. A healthy `\u002Fapi\u002Fhealth` from the resolved target plus a protected\n`\u002Fapi\u002Forgs` 401 means the runtime is healthy but the protected account-session\npath failed. Cookie reuse is only one hypothesis; also check session expiry,\nElectron partition, cookie scope, claim\u002Freadiness, and account or organization\npermission. Verify the actual main-process authenticated request before\nblaming the runtime or assuming a fetch injection is the fix.\n\nFor macOS storage symptoms, inspect the exact packaged artifact's signing\nidentity (`codesign -dvv`) and the compiled policy before launching it. An\nad-hoc\u002Funsigned packaged app is not equivalent to a signed package. If the\npolicy is memory-only, report the restart\u002Flogin persistence consequence. A\nrenderer screenshot, API health check, dev smoke, or synthetic Chromium fixture\ncannot prove that a native Keychain NSAlert did not appear. For that claim,\nrebuild the candidate, repeat packaged launches, and observe the native dialog\nsurface with an available system\u002FUI observation path; otherwise return\n`BLOCKED` with the missing proof.\n\n## Failure Layers\n\nClassify the first failing boundary:\n\n1. launcher, command, or port allocation;\n2. API process and health;\n3. embedded PostgreSQL and migrations;\n4. UI build\u002Fdev middleware;\n5. Electron main process and visible window;\n6. profile, instance, base URL, and organization data;\n7. packaged boot\u002Fresources;\n8. update download, replacement, progress pipe, restart, and relaunch;\n9. resource exhaustion or stale producer processes.\n\nTest one boundary at a time. Preserve unrelated dirty files and user data.\nNever reset or delete `~\u002F.rudder` as a diagnostic shortcut.\n\n## Recovery Loop\n\n1. Capture exact command, checkout, target mode, logs, and current processes.\n2. Resolve the correct descriptor and health payload.\n3. If the symptom is identity-related, record each continuity transition and\n   diagnose the first missing applicable transition.\n4. Find the first failing layer.\n5. Apply a scoped recovery. A request to fix or restore Desktop authorizes\n   necessary source repairs and verification; no second \"fix\" instruction is\n   needed. A diagnosis-only request remains read-only. Preserve user data and\n   use the packaged verification path when the repair affects installed behavior.\n6. Restart the same target path.\n7. Observe the Electron window or installed application.\n8. Verify runtime identity, the original symptom, and the first usable\n   post-login workspace when login was in scope.\n9. If persistence was in scope, perform a controlled restart and report what\n   survived. Do not infer persistence from an in-process success.\n\nFor update failures, reconstruct download, replacement, old-app exit,\nprogress-pipe behavior, and relaunch. Treat `EPIPE` as benign only when\nlifecycle evidence proves the reader exited normally and the new app reopened.\n\n## Report Format\n\n```text\nRESULT: RECOVERED | BLOCKED\nTarget mode:\nRuntime identity:\nIdentity continuity:\nFirst failing layer:\nAction:\nObserved Desktop proof:\nRestart\u002Fpersistence proof:\nRemaining blocker:\n```\n",{"name":5,"description":7},"main","26d5d68bcbc55caeac1dc6a266d973e8c3831f1c",".agents\u002Fskills\u002Fmaintainer\u002Frudder-desktop-dev-recovery-maintainer",31,"https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder","https:\u002F\u002Frudderhq.dev","https:\u002F\u002Fgithub.com\u002FUndertone0809","Creator of Rudder, Spark Lab. I design SDKs, infra and software for human and the NEW WORLD.","2026-11-08 00:09:15",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add Undertone0809\u002Frudder --skill rudder-desktop-dev-recovery-maintainer",{"tool":59,"command":60},"bunx","bunx skills add Undertone0809\u002Frudder --skill rudder-desktop-dev-recovery-maintainer",{"tool":62,"command":63},"pnpm","pnpm dlx skills add Undertone0809\u002Frudder --skill rudder-desktop-dev-recovery-maintainer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmaintainer\u002Frudder-desktop-dev-recovery-maintainer\u002FSKILL.md",true,[67,73,77],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"evals\u002Fevals.json","REFERENCE","参考文档",11727,"https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmaintainer\u002Frudder-desktop-dev-recovery-maintainer\u002Fevals\u002Fevals.json",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fidentity-continuity.md",4381,"https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmaintainer\u002Frudder-desktop-dev-recovery-maintainer\u002Freferences\u002Fidentity-continuity.md",{"path":78,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fmigration-history-recovery.md",6704,"https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmaintainer\u002Frudder-desktop-dev-recovery-maintainer\u002Freferences\u002Fmigration-history-recovery.md",[82,94,107,133,162,189],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":39},"01M6K33ZG45BN249F4DZRCCSJN","Source Synthesis","Synthesize evidence into a concise conclusion.","https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002Ftests\u002Fe2e\u002Ffixtures\u002Fcodex-plugin-research\u002Fskills\u002Fsynthesis\u002FSKILL.md",[],[89,90,91,92,93,23],"Synthesis","source","source synthesis","concise","synthesize",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":105,"publishedAt":39},"01M6K33XMZXRM31H2SG618C37F","Evidence Research","Gather and cite evidence before reaching a conclusion.","https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002Ftests\u002Fe2e\u002Ffixtures\u002Fcodex-plugin-research\u002Fskills\u002Fevidence\u002FSKILL.md",[100],{"categoryNo":101,"categoryName":102,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[106,23,96],"research",{"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":114,"publishedAt":39},"01M6K33RHAPNGPCM2FGPWTZQ8G","deep-research","Conducts enterprise-grade research with multi-source synthesis, citation tracking, and verification. Produces citation-backed reports through a structured pipeline with source credibility scoring, and grounds abstract findings in concrete examples, cases, counterexamples, or mini-scenarios when helpful. Triggers on \"deep research\", \"comprehensive analysis\", \"research report\", \"compare X vs Y\", \"analyze trends\", or \"state of the art\". Not for simple lookups, debugging, or questions answerable with 1-2 searches.","https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002Fserver\u002Fresources\u002Fcommunity-skills\u002Fdeep-research\u002FSKILL.md",[113],{"categoryNo":101,"categoryName":102,"taxonomyType":103,"taxonomyTypeDesc":104},[115,116,106,117,118,119,91,120,121,122,123,124,125,126,127,128,129,130,131,132],"deep research","deep","state","debugging","triggers","for","with","multi","compare","verification","scoring","Art","reports","analyze","analysis","pipeline","Enterprise","examples",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":142,"publishedAt":39},"01M6K33JPMYXHY9E4WR0K9EK0V","visualize","Create safe inline visual explanations in Rudder Chat. Use when asked for a chart, plot, diagram, timeline, comparison, static map, simulator, scenario view, or compact visual that materially improves understanding. Prefer Mermaid for static node-and-edge structures; use Rudder's runtime-neutral HTML\u002FSVG\u002FCSS message envelope for custom geometry. Rudder visuals are declarative and scriptless: convert simulator requests to static scenarios or disclosure-based comparisons and never rely on JavaScript, network access, or external assets.","https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002Fserver\u002Fresources\u002Fbundled-skills\u002Fvisualize\u002FSKILL.md",[139],{"categoryNo":140,"categoryName":141,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000009","前端开发",[135,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161],"static","inline","chart","scenario","access","geometry","map","message","compact","back","never","node","mermaid","network","create","diagram","safe","css","markdown",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":171,"publishedAt":39},"01M6K339S5PWH9RTZZA71CPD32","skill-creator","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002Fserver\u002Fresources\u002Fbundled-skills\u002Fskill-creator\u002FSKILL.md",[168],{"categoryNo":169,"categoryName":170,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000023","Skill与智能体开发",[172,173,174,175,176,177,178,179,120,180,181,182,183,184,185,186,129,187,188,157],"skill creator","creator","run evals","performance","variance analysis","existing skill","Existing","accuracy","From Scratch","users","optimize","evals","use","edit","improve","benchmark","run",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":195,"publishedAt":39},"01M6K333T855082YFXZ4FW0SE7","rudder-docs","Use when the user asks how Rudder works; needs current Rudder docs, exact behavior, commands, contracts, APIs, or source evidence; asks to create, hire, or configure Rudder agents; or asks to scaffold, develop, or verify Rudder plugins. For explicit creation requests, verify the current interface before acting within existing authorization. Do not use for greetings, ordinary work merely running inside Rudder, routine actions already clear from the active context and typed tools, non-Rudder plugin work, or general coding and research tasks that do not ask about Rudder.","https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002Fserver\u002Fresources\u002Fbundled-skills\u002Frudder-docs\u002FSKILL.md",[],[196,197,198,90,199,200,201,202,203,204,205,206,207,208,209,210,211,212,157,213],"rudder docs","docs","context","interface","hire","creation","commands","active","do","contracts","ask","work","coding","configure","how","Tools","actions","tasks"]