[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6R5V4282J3QNZMDKZXCP2F4":3,"skill-same:01M6R5V4282J3QNZMDKZXCP2F4":135},{"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":26,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":45,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M6R5V4282J3QNZMDKZXCP2F4","research",null,"Produce bounded, source-backed research packets for product, ecosystem, and operator decisions.","runxhq\u002Frunx","runxhq","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F278566904?v=4","01M6R54JKTWZNT4VQZ0K0DZ7V2","runx","01M6R54JRGDE4MDVDDR0E9MN0K",103,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[5,27,28,29,30,31,32,33,34],"ecosystem","for","produce","decisions","product","operator","source","bounded","2026-11-10 10:12:30",false,"---\nname: research\ndescription: Produce bounded, source-backed research packets for product, ecosystem, and operator decisions.\n---\n\n# Research\n\nAnswer one practical question with enough evidence to change a decision. This\nskill is for applied research: which issue is worth tackling, whether a proposal\nis grounded, what changed in an ecosystem, or which claims a public artifact can\nsafely make. It is not an open-ended browsing session or a summary for its own\nsake.\n\nThe result should make the operator's posture clearer: build, write, avoid,\ndefer, compare, or gather a named missing fact. Prefer a small number of\nwell-supported findings over a broad report whose conclusions cannot be traced.\n\n## Composes\n\n\u003C!-- Generated from the native closure; run pnpm core-skills:composes:generate. -->\n\n- `web-fetch#web-fetch`\n- `web-search#search`\n\n## Where it fits\n\nThe default `investigate` method accepts the question and optional `urls`,\n`paths` or existing `source_packets`. Supplied packets bypass acquisition.\nOtherwise the host works a governed acquisition turn over native local reads\nand the existing `web-fetch`\u002F`web-search` skills; the workflow then runs the same\nresearch analysis and verifier. Explicit URLs and paths do not require a search.\nUse `research` explicitly for already collected source packets, or `local-files`\nfor a wholly declarative read of known UTF-8 files. All routes converge on the\nsame source and content-digest index. URLs, paths, model memory, operator context, and target\nnames do not become evidence merely because they were supplied.\n\nThe packet is a reusable primitive for `research-brief`, `content-package`,\n`ghostwrite`, product planning, and other decision workflows.\nIt does not publish, notify, or mutate a provider. Those later operations keep\ntheir own authority, approval, and readback boundary.\n\n## How it works\n\n1. State a bounded objective and the decision the research should inform.\n2. Reuse the supplied readback packets, or acquire only the evidence missing\n   for the objective through actual declared reader calls. Runx indexes their\n   provenance, observation times, source digests, and content digests before\n   synthesis.\n3. Synthesis separates verified facts from inference, explains relevance,\n   records confidence, and carries open questions rather than filling gaps with\n   plausible prose.\n4. Every material claim cites an admitted source digest. Every recommended\n   option cites the evidence on which its rationale depends.\n5. The deterministic verifier rejects unknown citations, digest drift, and\n   unsupported decision support before the packet is released.\n\nReturn `needs_more_evidence` when the admitted sources cannot support the\ndecision. Return `not_worth_publishing` when a finding is sound but irrelevant\nto the stated deliverable. Neither state is a failure; both prevent weak\nevidence from turning into confident downstream content.\n\n## Inputs and result\n\n- `objective` is the exact question to answer.\n- `source_packets` are bounded provider or fetch readback packets with stable\n  provenance and content digests. `local-files` instead accepts contained paths\n  and never requires HTTP or a hosted connector.\n- `domain`, `deliverable`, `operator_context`, and `target_entities` narrow the\n  analysis. They are interpretation context, never source evidence.\n\nThe research packet contains the bounded brief, evidence log, decision options,\nrisks, open questions, admitted source evidence, and deterministic validation.\nConsumers should carry the packet and its digest forward rather than rewriting\nits findings into an untraceable summary.\n\n## Stop conditions\n\n- Stop when no valid source packet was supplied, evidence is stale for the\n  decision, or source identity cannot be verified.\n- Never cite an unknown source digest or treat a URL as proof that it was read.\n- Label inference as inference and lower confidence when evidence conflicts.\n- Do not manufacture balance by inventing an opposing claim with no source.\n- Keep source content out of public artifacts unless the downstream skill is\n  allowed to use it and respects quotation and privacy constraints.\n- Keep source acquisition inside its reader capability; publishing, messaging\n  and mutations still require their own skill and authority.\n\n## Example\n\nAn operator asks whether a proposed integration belongs in the next release and\nsupplies a changelog readback, an issue snapshot, and an official API document.\nThe packet can compare the evidence, state which user problem is verified, and\nrecommend build, defer, or investigate. It cannot cite a remembered forum post\nor operator hunch as verified demand, and it should name the missing evidence if\nthat gap changes the recommendation.\n\n\n## Agent task: research-acquire\n\nAcquire evidence for the stated question, not an answer from memory. Read the\nprovided URLs or local paths directly. For local paths use fs_read_bundle with\nthe current workspace as root, bounded bytes and on_missing: report; do not\ncrawl unrelated directories. For a public URL call the offered web-fetch skill\nwith text extraction. If source discovery is actually missing, use web-search\nfor a focused query, choose relevant primary sources and fetch the selected\npages. Search result snippets are candidates, not fetched source content.\nUse the exact offered tool names and schemas from native turn status.\n\nFor `fs_read_bundle`, take the unchanged entries in\n`output.file_read_bundle.files` as the individual source packets. The\nouter bundle groups files and missing-path reports; it is not itself a source.\nKeep each file entry's path, contents, byte count, content_digest and truncation\nmetadata. Inspect `missing` before proceeding; when a missing source prevents\nthe question being answered, ask for it or return no sources so the existing\nevidence stop remains explicit. Do not imply that every requested path was read.\n\nKeep every original source packet, including its contents\u002Fextracted text,\nsource identity, content digest and observation metadata. Return only\nsource_packets containing those actual outputs. Do not invent a digest,\nprovider response or read; do not rewrite text into a fabricated source. Carry\nprovider failures and coverage limits as missing evidence, never a negative\nfinding. If no valid source can be obtained, return an empty list and let the\nexisting analysis produce its evidence stop. Ask for missing scope through the\nnative ask tool when it would change which sources are relevant.\n\nDo not synthesize the final research in this acquisition turn. The workflow's\nexisting research phase owns that single synthesis and source verification.\nNative connector authority and charge limits still apply to search\u002Fread calls;\na result count is not a dollar cap. Preserve a pending approval or uncertain\ncharged call rather than starting another lookup. Reuse a completed call by\nits stable call ID and retain receipt lineage. Acquisition never publishes or\nchanges provider state.\n\nFor composition, call research with source_packets or local-files with known\npaths. Their contracts and result packet are unchanged. The investigate default\nalso bypasses acquisition when packets are supplied, so continuing from prior\nevidence never requires another discovery turn.\n","# Research\n\nAnswer one practical question with enough evidence to change a decision. This\nskill is for applied research: which issue is worth tackling, whether a proposal\nis grounded, what changed in an ecosystem, or which claims a public artifact can\nsafely make. It is not an open-ended browsing session or a summary for its own\nsake.\n\nThe result should make the operator's posture clearer: build, write, avoid,\ndefer, compare, or gather a named missing fact. Prefer a small number of\nwell-supported findings over a broad report whose conclusions cannot be traced.\n\n## Composes\n\n\u003C!-- Generated from the native closure; run pnpm core-skills:composes:generate. -->\n\n- `web-fetch#web-fetch`\n- `web-search#search`\n\n## Where it fits\n\nThe default `investigate` method accepts the question and optional `urls`,\n`paths` or existing `source_packets`. Supplied packets bypass acquisition.\nOtherwise the host works a governed acquisition turn over native local reads\nand the existing `web-fetch`\u002F`web-search` skills; the workflow then runs the same\nresearch analysis and verifier. Explicit URLs and paths do not require a search.\nUse `research` explicitly for already collected source packets, or `local-files`\nfor a wholly declarative read of known UTF-8 files. All routes converge on the\nsame source and content-digest index. URLs, paths, model memory, operator context, and target\nnames do not become evidence merely because they were supplied.\n\nThe packet is a reusable primitive for `research-brief`, `content-package`,\n`ghostwrite`, product planning, and other decision workflows.\nIt does not publish, notify, or mutate a provider. Those later operations keep\ntheir own authority, approval, and readback boundary.\n\n## How it works\n\n1. State a bounded objective and the decision the research should inform.\n2. Reuse the supplied readback packets, or acquire only the evidence missing\n   for the objective through actual declared reader calls. Runx indexes their\n   provenance, observation times, source digests, and content digests before\n   synthesis.\n3. Synthesis separates verified facts from inference, explains relevance,\n   records confidence, and carries open questions rather than filling gaps with\n   plausible prose.\n4. Every material claim cites an admitted source digest. Every recommended\n   option cites the evidence on which its rationale depends.\n5. The deterministic verifier rejects unknown citations, digest drift, and\n   unsupported decision support before the packet is released.\n\nReturn `needs_more_evidence` when the admitted sources cannot support the\ndecision. Return `not_worth_publishing` when a finding is sound but irrelevant\nto the stated deliverable. Neither state is a failure; both prevent weak\nevidence from turning into confident downstream content.\n\n## Inputs and result\n\n- `objective` is the exact question to answer.\n- `source_packets` are bounded provider or fetch readback packets with stable\n  provenance and content digests. `local-files` instead accepts contained paths\n  and never requires HTTP or a hosted connector.\n- `domain`, `deliverable`, `operator_context`, and `target_entities` narrow the\n  analysis. They are interpretation context, never source evidence.\n\nThe research packet contains the bounded brief, evidence log, decision options,\nrisks, open questions, admitted source evidence, and deterministic validation.\nConsumers should carry the packet and its digest forward rather than rewriting\nits findings into an untraceable summary.\n\n## Stop conditions\n\n- Stop when no valid source packet was supplied, evidence is stale for the\n  decision, or source identity cannot be verified.\n- Never cite an unknown source digest or treat a URL as proof that it was read.\n- Label inference as inference and lower confidence when evidence conflicts.\n- Do not manufacture balance by inventing an opposing claim with no source.\n- Keep source content out of public artifacts unless the downstream skill is\n  allowed to use it and respects quotation and privacy constraints.\n- Keep source acquisition inside its reader capability; publishing, messaging\n  and mutations still require their own skill and authority.\n\n## Example\n\nAn operator asks whether a proposed integration belongs in the next release and\nsupplies a changelog readback, an issue snapshot, and an official API document.\nThe packet can compare the evidence, state which user problem is verified, and\nrecommend build, defer, or investigate. It cannot cite a remembered forum post\nor operator hunch as verified demand, and it should name the missing evidence if\nthat gap changes the recommendation.\n\n\n## Agent task: research-acquire\n\nAcquire evidence for the stated question, not an answer from memory. Read the\nprovided URLs or local paths directly. For local paths use fs_read_bundle with\nthe current workspace as root, bounded bytes and on_missing: report; do not\ncrawl unrelated directories. For a public URL call the offered web-fetch skill\nwith text extraction. If source discovery is actually missing, use web-search\nfor a focused query, choose relevant primary sources and fetch the selected\npages. Search result snippets are candidates, not fetched source content.\nUse the exact offered tool names and schemas from native turn status.\n\nFor `fs_read_bundle`, take the unchanged entries in\n`output.file_read_bundle.files` as the individual source packets. The\nouter bundle groups files and missing-path reports; it is not itself a source.\nKeep each file entry's path, contents, byte count, content_digest and truncation\nmetadata. Inspect `missing` before proceeding; when a missing source prevents\nthe question being answered, ask for it or return no sources so the existing\nevidence stop remains explicit. Do not imply that every requested path was read.\n\nKeep every original source packet, including its contents\u002Fextracted text,\nsource identity, content digest and observation metadata. Return only\nsource_packets containing those actual outputs. Do not invent a digest,\nprovider response or read; do not rewrite text into a fabricated source. Carry\nprovider failures and coverage limits as missing evidence, never a negative\nfinding. If no valid source can be obtained, return an empty list and let the\nexisting analysis produce its evidence stop. Ask for missing scope through the\nnative ask tool when it would change which sources are relevant.\n\nDo not synthesize the final research in this acquisition turn. The workflow's\nexisting research phase owns that single synthesis and source verification.\nNative connector authority and charge limits still apply to search\u002Fread calls;\na result count is not a dollar cap. Preserve a pending approval or uncertain\ncharged call rather than starting another lookup. Reuse a completed call by\nits stable call ID and retain receipt lineage. Acquisition never publishes or\nchanges provider state.\n\nFor composition, call research with source_packets or local-files with known\npaths. Their contracts and result packet are unchanged. The investigate default\nalso bypasses acquisition when packets are supplied, so continuing from prior\nevidence never requires another discovery turn.\n",{"name":5,"description":7},"main","14cf84bcc80d7abf0008335efac4d92aacfa682e","skills\u002Fresearch",108,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx","https:\u002F\u002Frunx.ai","https:\u002F\u002Fgithub.com\u002Frunxhq","the governed runtime for agent skills","2026-11-13 21:42:05",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add runxhq\u002Frunx --skill research",{"tool":55,"command":56},"bunx","bunx skills add runxhq\u002Frunx --skill research",{"tool":58,"command":59},"pnpm","pnpm dlx skills add runxhq\u002Frunx --skill research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002FSKILL.md",true,[63,69,73,77,81,85,91,95,99,103,107,111,115,119,123,127,131],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"eval_queries.json","REFERENCE","参考文档",2497,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Feval_queries.json",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"evals\u002Fevals.json",1818,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fevals\u002Fevals.json",{"path":74,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":75,"sourceHtmlUrl":76},"evals\u002Ffiles\u002Fadmitted-local-source.json",694,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fevals\u002Ffiles\u002Fadmitted-local-source.json",{"path":78,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":79,"sourceHtmlUrl":80},"evals\u002Ffiles\u002Fadmitted-source-packets.json",1389,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fevals\u002Ffiles\u002Fadmitted-source-packets.json",{"path":82,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":83,"sourceHtmlUrl":84},"fixtures\u002Flocal-architecture-evidence.txt",142,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Ffixtures\u002Flocal-architecture-evidence.txt",{"path":86,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":89,"sourceHtmlUrl":90},"mark.svg","ASSET","资产文件",417,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fmark.svg",{"path":92,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":93,"sourceHtmlUrl":94},"packets\u002Fpacket.v1.schema.json",2916,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fpackets\u002Fpacket.v1.schema.json",{"path":96,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Fcatalog.md",145,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Freferences\u002Fcatalog.md",{"path":100,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":101,"sourceHtmlUrl":102},"references\u002Fmark-license.md",3208,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Freferences\u002Fmark-license.md",{"path":104,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":105,"sourceHtmlUrl":106},"run.yaml",7673,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Frun.yaml",{"path":108,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":109,"sourceHtmlUrl":110},"tests\u002Fcomposes-in-workflow.yaml",1233,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Ftests\u002Fcomposes-in-workflow.yaml",{"path":112,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":113,"sourceHtmlUrl":114},"tests\u002Fdefault-opens-acquisition.yaml",207,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Ftests\u002Fdefault-opens-acquisition.yaml",{"path":116,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":117,"sourceHtmlUrl":118},"tests\u002Fdefault-reuses-evidence.yaml",3083,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Ftests\u002Fdefault-reuses-evidence.yaml",{"path":120,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":121,"sourceHtmlUrl":122},"tests\u002Fresearch-invented-citation.yaml",1832,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Ftests\u002Fresearch-invented-citation.yaml",{"path":124,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":125,"sourceHtmlUrl":126},"tests\u002Fresearch-native-local-files-use-the-shared-analysis-path.yaml",1878,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Ftests\u002Fresearch-native-local-files-use-the-shared-analysis-path.yaml",{"path":128,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":129,"sourceHtmlUrl":130},"tests\u002Fresearch-no-sources.yaml",463,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Ftests\u002Fresearch-no-sources.yaml",{"path":132,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":133,"sourceHtmlUrl":134},"tests\u002Fresearch-ready.yaml",3097,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Ftests\u002Fresearch-ready.yaml",[136,162,182,198,217,234],{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":143,"publishedAt":35},"01M6R60D2HHP5C47QZ7ZBYBHSM","webhook-handoff","Validate a runx execution context and deliver a governed payload once to an n8n Cloud workflow webhook or a Zapier Catch Hook, with exact approval and the receiver's acknowledgement receipted.","https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fwebhook-handoff\u002FSKILL.md",[142],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[144,145,146,147,148,149,12,150,151,152,153,154,155,156,157,158,159,160,161],"webhook","handoff","webhook handoff","approval","zapier","context","hook","cloud","payload","n8n","validate","catch","with","workflow","execution","acknowledgement","deliver","receiver",{"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":168,"publishedAt":35},"01M6R609BT4F4MFVK9M2YZPQTV","web-search","Discover a bounded set of fresh web source candidates from one explicit search query, preserve provider evidence and reported cost, and prepare source selection for fetching and research.","https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fweb-search\u002FSKILL.md",[],[169,170,171,172,173,174,175,176,28,177,178,179,180,34,181,33,5],"web","search","web search","fresh","preserve","query","selection","provider","discover","evidence","SET","cost","prepare",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":188,"publishedAt":35},"01M6R5ZV4Z3FK8AHATF7AARXYD","web-fetch","Fetch and extract one public web source, optionally restrict its hosts, and return the content by digest with full provenance.","https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fweb-fetch\u002FSKILL.md",[],[189,190,169,191,192,193,194,195,196,156,197,33],"fetch","web fetch","full","content","extract","public","digest","hosts","provenance",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":205,"publishedAt":35},"01M6R5ZPRJQZ1Y8CBPT3WHSWCB","vuln-triage","Prioritize actual exact-coordinate vulnerability findings, preserve unknown exposure and partial coverage, and return practical remediation or an unsent advisory draft.","https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fvuln-triage\u002FSKILL.md",[204],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[206,207,173,208,209,210,211,212,213,214,215,216],"triage","vuln triage","prioritize","remediation","draft","advisory","vulnerability","unknown","coordinate","practical","coverage",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":224,"publishedAt":35},"01M6R5Z9RR7V456TAW4J5AJG0R","twitter","Govern X (Twitter) account work through three lanes: evidence reads, typed act plans for posting and account hygiene, and gated execution with per-act provider evidence. Nothing reaches a live timeline or mutates an account without an explicit approval recorded in the receipt.","https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Ftwitter\u002FSKILL.md",[223],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[219,178,225,226,156,227,158,176,28,228,229,230,147,231,232,233],"gated","work","plans","three","posting","hygiene","timeline","live","act",{"skillNo":235,"name":236,"nameZh":6,"description":237,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":238,"categories":239,"keywords":241,"publishedAt":35},"01M6R5Z3XRVR0V5XTES05XJRV8","team-delegate","Divide bounded work across an operator-selected team and return exact member assignments with source context, scope ceilings and acceptance checks.","https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fteam-delegate\u002FSKILL.md",[240],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[242,243,244,34,149,33,32,226,156,245,246,247],"team","team delegate","delegate","across","acceptance","scope"]