[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6K2ZR34R245FVJW8RYRNJS5":3,"skill-same:01M6K2ZR34R245FVJW8RYRNJS5":102},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6K2ZR34R245FVJW8RYRNJS5","rudder-real-runtime-verifier-maintainer",null,"Use when verifying Rudder agent runtime behavior in a real local environment, especially MCP\u002Fnative Rudder tools across Codex, Claude, OpenCode, Pi, or user-named runtimes. Trigger for requests like 真是\u002F真实环境跑过吗, 排查所有 rudder tools, transcript\u002Ffallback verification, runtime MCP availability, provider matrix proof, or checking whether agents used Rudder tools instead of rudder CLI\u002FBash\u002Fcurl fallback.","Undertone0809\u002Frudder","Undertone0809","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F72488598?v=4","01M6K2XANP3QJEF503JX2C693T","Zeeland","01M6K2XATQXEYF7N2QG8KZVEEY",297,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmaintainer\u002Frudder-real-runtime-verifier-maintainer\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"rudder real runtime verifier maintainer","verifier","runtime","provider","for","runtimes","availability","trigger","local","across","MCP","use","environment","pi","Bash","agent runtime","verification","transcript","codex","cli","2026-11-10 10:12:30",false,"---\nname: rudder-real-runtime-verifier-maintainer\ndescription: \"Use when verifying Rudder agent runtime behavior in a real local environment, especially MCP\u002Fnative Rudder tools across Codex, Claude, OpenCode, Pi, or user-named runtimes. Trigger for requests like 真是\u002F真实环境跑过吗, 排查所有 rudder tools, transcript\u002Ffallback verification, runtime MCP availability, provider matrix proof, or checking whether agents used Rudder tools instead of rudder CLI\u002FBash\u002Fcurl fallback.\"\n---\n\n# Rudder Real Runtime Verifier Maintainer\n\nVerify Rudder agent runtime behavior on the user's real local Rudder instance.\nThis is a black-box runtime acceptance workflow, not an implementation or code\nreview workflow.\n\nDefault to Chinese when the user asks in Chinese. Put the current truth first:\nwhich runtimes passed, failed, or were blocked, and what transcript evidence\nproves it.\n\n## Role Boundary\n\nDefault to verification and diagnosis only:\n\n- Run real local runtime probes and inspect run transcripts, logs, API state,\n  issue state, comments, and run metadata.\n- Create disposable orgs, agents, issues, and runs when needed for proof.\n- Separate provider\u002Fmodel failure from Rudder adapter failure.\n- Report exact blockers and smallest likely fixes.\n- As an independent verifier, do not edit source, configs, Git state, or product\n  docs. Return findings to the implementer. The parent retains any existing\n  fix authority; verification does not require that authority to be repeated.\n\nIf the user asks to fix the issue, hand back to the lifecycle implementation\nroute or make the smallest explicit patch, then require this skill's real\nruntime proof again before claiming done.\n\n## When This Skill Wins\n\nUse this skill when the core question is whether an agent runtime actually did\nthe work through Rudder-managed tools in a real local run.\n\nTypical prompts:\n\n- \"你所有的 agent runtime 都本地测过跑过真实环境了吗?\"\n- \"OpenCode and Pi agent 你也测了吗?\"\n- \"看 transcript，别让它 fallback 用 rudder cli\"\n- \"排查所有 rudder tools，都试一遍\"\n- \"MCP tool 报 org id\u002Fauth 问题，正常 agent 调 tool 不该传 org\"\n- \"Codex\u002FClaude\u002FOpenCode\u002FPi 真实环境跑一下\"\n\nIf the user asks for general product acceptance that is not runtime\u002Ftool-call\nspecific, use `product-acceptance-verifier-maintainer` instead. If the user\nprovides only one failed run id and wants root cause, use\n`debug-run-transcript-maintainer` first, then return here for rerun proof after\na fix.\n\n## Runtime Matrix\n\nSelect the runtime matrix from the user's request and the changed integration.\nTest one runtime for a runtime-specific claim. Use the full supported matrix for\nan explicit all-runtime claim or a shared adapter\u002Ftool change that affects it:\n\n- Codex\n- Claude Code\n- Hermes\n- OpenCode\n- Pi\n- Cursor\n\nDo not treat a Codex pass as proof for another runtime.\n\nRead only the relevant reference files:\n\n- `references\u002Fprobe-workflow.md`: real local setup, disposable data, probe\n  script expectations, and proof levels.\n- `references\u002Ftranscript-evidence.md`: how to prove tool use and reject CLI\n  fallback from logs.\n- `references\u002Fcodex.md`: Codex MCP transcript shape and known traps.\n- `references\u002Fclaude.md`: Claude MCP transcript shape and strict config traps.\n- `references\u002Fopencode.md`: OpenCode MCP transcript shape, provider\u002Fmodel\n  caveats, JSONL parser expectations, and final-text pitfalls.\n- `references\u002Fpi.md`: Pi native extension transcript shape, schema\u002Ferror\n  propagation traps, and 429\u002Fauth\u002Fprovider separation.\n- `references\u002Freporting.md`: verdict format, mutation ledger, and pass\u002Ffail\n  language.\n\n## Acceptance Standard\n\nA runtime passes only when all are true:\n\n1. The local Rudder source of truth is identified, usually\n   `GET \u002Fapi\u002Fhealth` on `http:\u002F\u002F127.0.0.1:3100`.\n2. A real local run was triggered for that runtime, or an existing real local\n   run was inspected with enough raw transcript\u002Flog evidence.\n3. The transcript shows the expected Rudder MCP\u002Fnative tool calls.\n4. There is no model-visible fallback to shell, Bash, curl, or `rudder` CLI for\n   Rudder work.\n5. Tool results are not internally failed (`isError`, structured error,\n   `rudder_cli_command_failed`, missing required argument, auth\u002Forg failure).\n6. The terminal product effect was read back: issue status, comments, run\n   status, final text, API result, or another requested surface.\n7. Provider\u002Fmodel blockers are separated from Rudder adapter\u002Ftool blockers.\n\nIf the user requires \"all tools\", do not only run a happy-path issue workflow.\nRun or request a manifest-driven coverage plan: list every exposed tool, verify\nschemas load, check runtime-managed identity is not model-provided, and execute\nrepresentative read\u002Fmutate\u002Ffile\u002Fimage\u002Fpagination\u002Ferror cases. Mark unexecuted\ntools as not covered.\n\n## Default Probe Ladder\n\nUse the smallest probe that answers the question, then escalate only as needed:\n\n1. **Tool availability probe**: call `rudder_agent_me`, require final answer\n   to say MCP\u002Ftool path and no fallback.\n2. **Issue workflow probe**: seed an issue, then require\n   `rudder_issue_context`, `rudder_issue_checkout`,\n   `rudder_issue_comment`, and `rudder_issue_done`; read back final issue\n   status and comments.\n3. **Representative matrix probe**: add read\u002Flist\u002Fpagination\u002Ffile\u002Fcomment\u002Fimage\n   examples such as `rudder_runs_errors`, `rudder_library_file_ref`,\n   inbox\u002Fcontext, review, chat, or automation.\n4. **Full manifest audit**: prove every exposed Rudder tool has a stable name,\n   schema, description, and handler classification; execute safe read-only\n   tools and representative mutating tools in disposable data.\n\n## Known Judgment Rules\n\n- A successful final answer is not enough. Inspect raw or parsed transcript.\n- A tool call name in prompt text is not evidence. Use structured tool-call\n  events or parsed run-intelligence entries.\n- A run can fail after completing the product effect. Report that separately:\n  `tool\u002Fproduct effect passed; runtime finalization failed`.\n- A provider 429\u002Fauth\u002Fmodel error before any tool call is not an MCP auth\u002Forg\n  bug. Mark it `blocked_provider`.\n- If a tool result contains `isError: true` but the runtime marks the tool call\n  completed, treat the runtime as failed or at least suspect until fixed.\n- Internal runtime-owned bridges may execute a server process. That is\n  acceptable only if the model-visible action is a typed Rudder tool and\n  runtime env owns identity. It is not acceptable if the model uses Bash\u002Fcurl or\n  runs `rudder ...` itself for Rudder work.\n\n## Output\n\nUse `references\u002Freporting.md` for the full shape. At minimum include:\n\n- overall verdict: `PASS`, `FAIL`, or `QUESTION` for the requested matrix;\n  observed required behavior failure yields `FAIL`; otherwise missing required\n  proof or provider access yields `QUESTION`; complete required proof yields `PASS`\n- verdict per runtime: `PASS`, `FAIL`, `BLOCKED_PROVIDER`, `PARTIAL`, or\n  `NOT_RUN`\n- run IDs, issue IDs, org IDs when disposable data was created\n- observed tool names\n- whether CLI\u002FBash\u002Fcurl fallback was observed\n- internal tool errors\n- terminal product effect\n- skipped coverage and why\n- mutation ledger\n\nDo not say \"all green\" if any runtime is blocked, substituted, partial, or only\ncovered by simple `agent_me`.\n","# Rudder Real Runtime Verifier Maintainer\n\nVerify Rudder agent runtime behavior on the user's real local Rudder instance.\nThis is a black-box runtime acceptance workflow, not an implementation or code\nreview workflow.\n\nDefault to Chinese when the user asks in Chinese. Put the current truth first:\nwhich runtimes passed, failed, or were blocked, and what transcript evidence\nproves it.\n\n## Role Boundary\n\nDefault to verification and diagnosis only:\n\n- Run real local runtime probes and inspect run transcripts, logs, API state,\n  issue state, comments, and run metadata.\n- Create disposable orgs, agents, issues, and runs when needed for proof.\n- Separate provider\u002Fmodel failure from Rudder adapter failure.\n- Report exact blockers and smallest likely fixes.\n- As an independent verifier, do not edit source, configs, Git state, or product\n  docs. Return findings to the implementer. The parent retains any existing\n  fix authority; verification does not require that authority to be repeated.\n\nIf the user asks to fix the issue, hand back to the lifecycle implementation\nroute or make the smallest explicit patch, then require this skill's real\nruntime proof again before claiming done.\n\n## When This Skill Wins\n\nUse this skill when the core question is whether an agent runtime actually did\nthe work through Rudder-managed tools in a real local run.\n\nTypical prompts:\n\n- \"你所有的 agent runtime 都本地测过跑过真实环境了吗?\"\n- \"OpenCode and Pi agent 你也测了吗?\"\n- \"看 transcript，别让它 fallback 用 rudder cli\"\n- \"排查所有 rudder tools，都试一遍\"\n- \"MCP tool 报 org id\u002Fauth 问题，正常 agent 调 tool 不该传 org\"\n- \"Codex\u002FClaude\u002FOpenCode\u002FPi 真实环境跑一下\"\n\nIf the user asks for general product acceptance that is not runtime\u002Ftool-call\nspecific, use `product-acceptance-verifier-maintainer` instead. If the user\nprovides only one failed run id and wants root cause, use\n`debug-run-transcript-maintainer` first, then return here for rerun proof after\na fix.\n\n## Runtime Matrix\n\nSelect the runtime matrix from the user's request and the changed integration.\nTest one runtime for a runtime-specific claim. Use the full supported matrix for\nan explicit all-runtime claim or a shared adapter\u002Ftool change that affects it:\n\n- Codex\n- Claude Code\n- Hermes\n- OpenCode\n- Pi\n- Cursor\n\nDo not treat a Codex pass as proof for another runtime.\n\nRead only the relevant reference files:\n\n- `references\u002Fprobe-workflow.md`: real local setup, disposable data, probe\n  script expectations, and proof levels.\n- `references\u002Ftranscript-evidence.md`: how to prove tool use and reject CLI\n  fallback from logs.\n- `references\u002Fcodex.md`: Codex MCP transcript shape and known traps.\n- `references\u002Fclaude.md`: Claude MCP transcript shape and strict config traps.\n- `references\u002Fopencode.md`: OpenCode MCP transcript shape, provider\u002Fmodel\n  caveats, JSONL parser expectations, and final-text pitfalls.\n- `references\u002Fpi.md`: Pi native extension transcript shape, schema\u002Ferror\n  propagation traps, and 429\u002Fauth\u002Fprovider separation.\n- `references\u002Freporting.md`: verdict format, mutation ledger, and pass\u002Ffail\n  language.\n\n## Acceptance Standard\n\nA runtime passes only when all are true:\n\n1. The local Rudder source of truth is identified, usually\n   `GET \u002Fapi\u002Fhealth` on `http:\u002F\u002F127.0.0.1:3100`.\n2. A real local run was triggered for that runtime, or an existing real local\n   run was inspected with enough raw transcript\u002Flog evidence.\n3. The transcript shows the expected Rudder MCP\u002Fnative tool calls.\n4. There is no model-visible fallback to shell, Bash, curl, or `rudder` CLI for\n   Rudder work.\n5. Tool results are not internally failed (`isError`, structured error,\n   `rudder_cli_command_failed`, missing required argument, auth\u002Forg failure).\n6. The terminal product effect was read back: issue status, comments, run\n   status, final text, API result, or another requested surface.\n7. Provider\u002Fmodel blockers are separated from Rudder adapter\u002Ftool blockers.\n\nIf the user requires \"all tools\", do not only run a happy-path issue workflow.\nRun or request a manifest-driven coverage plan: list every exposed tool, verify\nschemas load, check runtime-managed identity is not model-provided, and execute\nrepresentative read\u002Fmutate\u002Ffile\u002Fimage\u002Fpagination\u002Ferror cases. Mark unexecuted\ntools as not covered.\n\n## Default Probe Ladder\n\nUse the smallest probe that answers the question, then escalate only as needed:\n\n1. **Tool availability probe**: call `rudder_agent_me`, require final answer\n   to say MCP\u002Ftool path and no fallback.\n2. **Issue workflow probe**: seed an issue, then require\n   `rudder_issue_context`, `rudder_issue_checkout`,\n   `rudder_issue_comment`, and `rudder_issue_done`; read back final issue\n   status and comments.\n3. **Representative matrix probe**: add read\u002Flist\u002Fpagination\u002Ffile\u002Fcomment\u002Fimage\n   examples such as `rudder_runs_errors`, `rudder_library_file_ref`,\n   inbox\u002Fcontext, review, chat, or automation.\n4. **Full manifest audit**: prove every exposed Rudder tool has a stable name,\n   schema, description, and handler classification; execute safe read-only\n   tools and representative mutating tools in disposable data.\n\n## Known Judgment Rules\n\n- A successful final answer is not enough. Inspect raw or parsed transcript.\n- A tool call name in prompt text is not evidence. Use structured tool-call\n  events or parsed run-intelligence entries.\n- A run can fail after completing the product effect. Report that separately:\n  `tool\u002Fproduct effect passed; runtime finalization failed`.\n- A provider 429\u002Fauth\u002Fmodel error before any tool call is not an MCP auth\u002Forg\n  bug. Mark it `blocked_provider`.\n- If a tool result contains `isError: true` but the runtime marks the tool call\n  completed, treat the runtime as failed or at least suspect until fixed.\n- Internal runtime-owned bridges may execute a server process. That is\n  acceptable only if the model-visible action is a typed Rudder tool and\n  runtime env owns identity. It is not acceptable if the model uses Bash\u002Fcurl or\n  runs `rudder ...` itself for Rudder work.\n\n## Output\n\nUse `references\u002Freporting.md` for the full shape. At minimum include:\n\n- overall verdict: `PASS`, `FAIL`, or `QUESTION` for the requested matrix;\n  observed required behavior failure yields `FAIL`; otherwise missing required\n  proof or provider access yields `QUESTION`; complete required proof yields `PASS`\n- verdict per runtime: `PASS`, `FAIL`, `BLOCKED_PROVIDER`, `PARTIAL`, or\n  `NOT_RUN`\n- run IDs, issue IDs, org IDs when disposable data was created\n- observed tool names\n- whether CLI\u002FBash\u002Fcurl fallback was observed\n- internal tool errors\n- terminal product effect\n- skipped coverage and why\n- mutation ledger\n\nDo not say \"all green\" if any runtime is blocked, substituted, partial, or only\ncovered by simple `agent_me`.\n",{"name":5,"description":7},"main","26d5d68bcbc55caeac1dc6a266d973e8c3831f1c",".agents\u002Fskills\u002Fmaintainer\u002Frudder-real-runtime-verifier-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":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add Undertone0809\u002Frudder --skill rudder-real-runtime-verifier-maintainer",{"tool":64,"command":65},"bunx","bunx skills add Undertone0809\u002Frudder --skill rudder-real-runtime-verifier-maintainer",{"tool":67,"command":68},"pnpm","pnpm dlx skills add Undertone0809\u002Frudder --skill rudder-real-runtime-verifier-maintainer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmaintainer\u002Frudder-real-runtime-verifier-maintainer\u002FSKILL.md",true,[72,78,82,86,90,94,98],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fclaude.md","REFERENCE","参考文档",1450,"https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmaintainer\u002Frudder-real-runtime-verifier-maintainer\u002Freferences\u002Fclaude.md",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fcodex.md",1186,"https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmaintainer\u002Frudder-real-runtime-verifier-maintainer\u002Freferences\u002Fcodex.md",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fopencode.md",1899,"https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmaintainer\u002Frudder-real-runtime-verifier-maintainer\u002Freferences\u002Fopencode.md",{"path":87,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fpi.md",1973,"https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmaintainer\u002Frudder-real-runtime-verifier-maintainer\u002Freferences\u002Fpi.md",{"path":91,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fprobe-workflow.md",2419,"https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmaintainer\u002Frudder-real-runtime-verifier-maintainer\u002Freferences\u002Fprobe-workflow.md",{"path":95,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Freporting.md",2655,"https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmaintainer\u002Frudder-real-runtime-verifier-maintainer\u002Freferences\u002Freporting.md",{"path":99,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Ftranscript-evidence.md",2144,"https:\u002F\u002Fgithub.com\u002FUndertone0809\u002Frudder\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmaintainer\u002Frudder-real-runtime-verifier-maintainer\u002Freferences\u002Ftranscript-evidence.md",[103,116,127,151,180,204],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":44},"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",[],[110,111,112,113,114,115],"Synthesis","source","source synthesis","concise","synthesize","evidence",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":125,"publishedAt":44},"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",[122],{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[126,115,118],"research",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":134,"publishedAt":44},"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",[133],{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},[135,136,126,137,138,139,112,28,140,141,142,40,143,144,145,146,147,148,149,150],"deep research","deep","state","debugging","triggers","with","multi","compare","scoring","Art","reports","analyze","analysis","pipeline","Enterprise","examples",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":160,"publishedAt":44},"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",[157],{"categoryNo":158,"categoryName":159,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[153,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179],"static","inline","chart","scenario","access","geometry","map","message","compact","back","never","node","mermaid","network","create","diagram","safe","css","markdown",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":187,"publishedAt":44},"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",[186],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[188,189,190,191,192,193,194,195,28,196,197,198,199,35,200,201,147,202,203,175],"skill creator","creator","run evals","performance","variance analysis","existing skill","Existing","accuracy","From Scratch","users","optimize","evals","edit","improve","benchmark","run",{"skillNo":205,"name":206,"nameZh":6,"description":207,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":208,"categories":209,"keywords":210,"publishedAt":44},"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",[],[211,212,213,111,214,215,216,217,218,219,220,221,222,223,224,225,226,227,175,228],"rudder docs","docs","context","interface","hire","creation","commands","active","do","contracts","ask","work","coding","configure","how","Tools","actions","tasks"]