[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6R5PCSMR1CEWVG0PSAJTGGV":3,"skill-same:01M6R5PCSMR1CEWVG0PSAJTGGV":126},{"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":31,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":60,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M6R5PCSMR1CEWVG0PSAJTGGV","organic-growth",null,"Turn bounded search, analytics, site, and market evidence into an evidence-bound SEO and answer-engine growth brief with prioritized actions and a measurement plan, without claiming execution or guaranteed visibility.","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\u002Forganic-growth\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000019","营销推广","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000035","市场营销","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"growth","organic growth","organic","brief","execution","seo","plan","site","engine","analytics","evidence","Market","actions","with","answer","measurement","bounded","search","2026-11-10 10:12:30",false,"---\nname: organic-growth\ndescription: Turn bounded search, analytics, site, and market evidence into an evidence-bound SEO and answer-engine growth brief with prioritized actions and a measurement plan, without claiming execution or guaranteed visibility.\n---\n\n# Organic Growth\n\nUse this skill when an operator needs to decide what to improve on a site for\norganic discovery: technical search health, content demand, landing-page\nperformance, conversion quality, or the clarity and citeability that can help a\npage appear in answer engines.\n\nThe output is a decision packet, not a bag of SEO tips. It separates what the\nevidence shows from what the analyst infers, ranks the next actions by expected\nimpact, confidence, and effort, and says how each action should be measured. No\naction is executed by this skill.\n\n## Direct collection and reuse\n\nThe default `review` starts from an objective and the canonical site root. It\ncollects only missing evidence, then uses the same `analyze` phase as a composed\ngraph. Any supplied search, analytics or site evidence takes the reuse branch\nimmediately: no page fetch, measurement query or extra research turn runs.\nForward any prior `collection_notes` with those sources so access failures and\nmeasurement gaps survive the handoff.\nChoose `analyze` explicitly for a source-only graph that must never acquire data.\n\nWith no sources, the collection turn can use `web-fetch#web-fetch` for relevant\npublic pages and the read-only defaults `google-search-console#performance` or\n`google-analytics#report` on the operator's selected compatible bindings. Google\nis optional; no private report is required to inspect a public page. Supply known\nproperty\u002Fdate\u002Fmeasurement selectors or relevant page URLs in `source_context`.\nAsk when a private selector is ambiguous. A missing binding or unavailable\nreport means unavailable evidence, not zero traffic or no commercial demand.\n\nCollection returns actual reader packets and gaps, not a growth strategy. The\nexisting analysis owns priorities, causal caution and measurement. For public\npage text, pass the unchanged `provider_operation.data.result` from a successful\n`web-fetch` with `extract: text` into `site_evidence`; its final URL, full body\ndigest, extracted text and provenance survive the handoff. Preserve complete\nGoogle normalized evidence packets, including their request and coverage caveats.\nNever manufacture a digest, rewrite a report as live, or treat snippets as page\ncontent. Failed reads stay in `collection_notes`; they are not SEO observations.\n\nA long page yields a labelled bounded text view for analysis, while its original\nsource identity stays bound. Omitted content was not assessed. Focus another\nsource read only if the decision needs evidence outside that view; do not turn a\npresentation ceiling into a claim that the site itself is unsupported.\n\n## Composes\n\n\u003C!-- Generated from the native execution closure; run pnpm core-skills:composes:generate. -->\n\n- `google-analytics#report`\n- `google-search-console#performance`\n- `web-fetch#web-fetch`\n\n## Evidence comes first\n\nThe supplied-evidence `analyze` runner accepts a bounded objective, the site, optional\nbusiness constraints, and any combination of:\n\n- search-performance evidence, such as a sealed\n  `google-search-console` performance packet;\n- analytics evidence, such as a sealed `google-analytics` report packet;\n- site or market evidence with a SHA-256 source\u002Fcontent digest, source reference,\n  kind, and bounded extracted summary.\n\nGoogle is optional. The canonical workflow depends on evidence contracts, not a\nprovider, connector, credential store, or hosted tenant. A local crawler,\nself-hosted analytics service, another search provider, third-party connector,\nor Runx-hosted connector can supply evidence when its packet has a stable digest\nand useful provenance. Connector ids, credential handles, URLs, and tenant\nconfiguration never belong in this skill.\n\nThe admission step rejects invalid packet schemas, failed validation, missing\ndigests, and unbounded evidence. It gives the analysis agent the rows, metadata,\ncaveats, and business context needed for judgment, capped to an explicit analysis\nview. The complete source packet remains bound by digest; the model must not\npretend a bounded view is exhaustive.\n\nEvery material claim and recommended action must cite one or more admitted source\ndigests. Runx's native evidence verifier rejects invented references, changed\nobjective\u002Fsite identity, empty claims, missing decision fields, and unsupported\nexternal-effect claims. A failure becomes `needs_more_evidence`, not a polished\nguess.\n\n## Reading the combined signal\n\nSearch evidence explains discovery: queries, pages, impressions, clicks, CTR,\nposition, freshness, and coverage. Analytics explains behavior and business\noutcomes under the property's measurement model. Site evidence explains what is\nactually published, crawlable, structured, internally linked, and supportable.\n\nUse their disagreement. Rising impressions with weak CTR can justify inspecting\nsnippet fit, intent, brand recognition, or SERP composition. Strong clicks with\nweak engagement can justify checking landing-page promise, speed, navigation,\nor measurement. Analytics decline without a matching Search Console decline can\npoint toward tagging, channel classification, consent, conversion configuration,\nor non-Google traffic. These are hypotheses until the relevant evidence is\ncollected.\n\nCompare identical date windows, page identities, search types, dimensions,\ntimezone assumptions, and definitions. Preserve incomplete Search Console data,\nGA4 thresholding, sampling, `(other)`-row loss, pagination, and imported-source\nstatus as caveats. Do not convert correlation into causation.\n\n## SEO and answer-engine work\n\nTechnical SEO recommendations require site evidence. Check indexability,\ncanonicalization, robots rules, sitemap membership, status codes, rendering,\nstructured data eligibility, internal discovery paths, and page duplication\nbefore prescribing a fix. Search Console URL inspection is a point observation,\nnot authority to mutate the site or request indexing.\n\nContent recommendations should connect a demonstrated audience need to a page,\nbusiness outcome, and information gap. Avoid producing pages merely because a\nkeyword exists. Consolidation, deletion, template repair, internal linking, or a\nbetter primary answer may beat another article.\n\nFor answer-engine or \"GEO\" work, optimize the underlying source quality:\nunambiguous entities, direct answers, original evidence, clear authorship and\ndates, machine-readable structure, stable URLs, strong internal context, and\nclaims that another system can verify. There is no reliable switch for AI\ncitations and no basis for guaranteeing inclusion. Treat answer-engine\nvisibility as an observed channel that needs its own evidence, not as a mystical\nranking score.\n\n## Action packet\n\nA ready packet contains:\n\n- an executive summary and bounded analysis scope;\n- evidence-bound observations and explicit hypotheses;\n- prioritized opportunities;\n- recommended actions with rationale, source digests, owner type, effort,\n  confidence, expected signal, stop condition, and verification method;\n- a dedicated answer-engine review where evidence supports it;\n- a measurement plan with baselines, leading and business outcomes, comparison\n  windows, and rollback or reconsideration triggers;\n- risks, missing evidence, and the authoritative source inventory.\n\nThe action list remains `external_status: not_executed`. Route implementation\nto the owning repository or business workflow. Content changes may move through\na governed content pipeline; code and template work belongs in the site's\nrepository workflow; publication and provider mutations keep their own approval\nand readback gates.\n\n## A useful operating loop\n\nRun a narrow baseline, choose one evidence-bound action, make the change through\nits owner, wait for an appropriate observation window, then rerun the same\nqueries. Preserve the original packet digests. Change several variables together\nonly when the operator accepts that attribution will be weaker.\n\nStop when no source is admitted, page\u002Fproperty identity cannot be aligned, the\ndate windows are incomparable, privacy or pagination caveats defeat the claim,\nthe requested recommendation needs technical\u002Fcontent evidence that is absent,\nthe agent cites a source outside the admitted set, or the objective asks for\nguaranteed ranking, mass low-value content, deceptive markup, or unapproved\npublication.\n\nThe deterministic module only admits and bounds organic-growth domain evidence.\nIt does not hash evidence, call providers, or implement generic verification.\nRunx owns native digest provenance, evidence verification, agent receipts, and\nall downstream effect gates.\n\n## Agent task contract\n\n### `organic-growth-analyze`\n\nReturn `growth_candidate` with `decision: ready`, the exact objective and\nsite_url, executive_summary, observations, hypotheses, opportunities,\nrecommended_actions, geo_review, measurement_plan, claims, risks,\nmissing_evidence, and `external_status: not_executed`.\n\nEach claim requires a non-empty `claim` and admitted `source_digests`. Every\nrecommended action requires non-empty `source_digests` plus a rationale,\npriority, confidence, effort, expected_signal, verification, and stop_condition.\nMark statements as observed, inferred, or hypothesized. Preserve source caveats,\ndo not invent metrics or causes, and do not claim a change, publication,\nprovider call, ranking result, or AI citation occurred.\n\n### `organic-growth-collect`\n\nAcquire relevant missing evidence for the exact objective\u002Fsite, using the named\nread-only skill defaults and native asks if a genuine selector is missing. Do\nnot submit sitemaps, alter analytics, publish, crawl unrelated sites or invent\nmissing metrics. Use the returned tool schemas. Google sources are optional.\nRead a useful relevant public page if no source was supplied. Fetch explicit\npage URLs directly; avoid redundant reads and broad speculative crawling.\n\nReturn exactly `search_evidence`, `analytics_evidence`, `site_evidence` and\n`collection_notes`. Use empty objects\u002Farray for absent sources. Forward actual\nnormalized Google packet data unchanged. For a text page, forward the unchanged\n`provider_operation.data.result` as an individual site-evidence record, never\nthe provider packet wrapper. Preserve final URL, digest, text and provenance.\nRecord inaccessible sources, actual read errors and missing measurement context\nas notes. Do not perform synthesis; the next analysis turn owns it. No source\nmeans honest missing evidence. Do not claim a provider call you did not make.\n","# Organic Growth\n\nUse this skill when an operator needs to decide what to improve on a site for\norganic discovery: technical search health, content demand, landing-page\nperformance, conversion quality, or the clarity and citeability that can help a\npage appear in answer engines.\n\nThe output is a decision packet, not a bag of SEO tips. It separates what the\nevidence shows from what the analyst infers, ranks the next actions by expected\nimpact, confidence, and effort, and says how each action should be measured. No\naction is executed by this skill.\n\n## Direct collection and reuse\n\nThe default `review` starts from an objective and the canonical site root. It\ncollects only missing evidence, then uses the same `analyze` phase as a composed\ngraph. Any supplied search, analytics or site evidence takes the reuse branch\nimmediately: no page fetch, measurement query or extra research turn runs.\nForward any prior `collection_notes` with those sources so access failures and\nmeasurement gaps survive the handoff.\nChoose `analyze` explicitly for a source-only graph that must never acquire data.\n\nWith no sources, the collection turn can use `web-fetch#web-fetch` for relevant\npublic pages and the read-only defaults `google-search-console#performance` or\n`google-analytics#report` on the operator's selected compatible bindings. Google\nis optional; no private report is required to inspect a public page. Supply known\nproperty\u002Fdate\u002Fmeasurement selectors or relevant page URLs in `source_context`.\nAsk when a private selector is ambiguous. A missing binding or unavailable\nreport means unavailable evidence, not zero traffic or no commercial demand.\n\nCollection returns actual reader packets and gaps, not a growth strategy. The\nexisting analysis owns priorities, causal caution and measurement. For public\npage text, pass the unchanged `provider_operation.data.result` from a successful\n`web-fetch` with `extract: text` into `site_evidence`; its final URL, full body\ndigest, extracted text and provenance survive the handoff. Preserve complete\nGoogle normalized evidence packets, including their request and coverage caveats.\nNever manufacture a digest, rewrite a report as live, or treat snippets as page\ncontent. Failed reads stay in `collection_notes`; they are not SEO observations.\n\nA long page yields a labelled bounded text view for analysis, while its original\nsource identity stays bound. Omitted content was not assessed. Focus another\nsource read only if the decision needs evidence outside that view; do not turn a\npresentation ceiling into a claim that the site itself is unsupported.\n\n## Composes\n\n\u003C!-- Generated from the native execution closure; run pnpm core-skills:composes:generate. -->\n\n- `google-analytics#report`\n- `google-search-console#performance`\n- `web-fetch#web-fetch`\n\n## Evidence comes first\n\nThe supplied-evidence `analyze` runner accepts a bounded objective, the site, optional\nbusiness constraints, and any combination of:\n\n- search-performance evidence, such as a sealed\n  `google-search-console` performance packet;\n- analytics evidence, such as a sealed `google-analytics` report packet;\n- site or market evidence with a SHA-256 source\u002Fcontent digest, source reference,\n  kind, and bounded extracted summary.\n\nGoogle is optional. The canonical workflow depends on evidence contracts, not a\nprovider, connector, credential store, or hosted tenant. A local crawler,\nself-hosted analytics service, another search provider, third-party connector,\nor Runx-hosted connector can supply evidence when its packet has a stable digest\nand useful provenance. Connector ids, credential handles, URLs, and tenant\nconfiguration never belong in this skill.\n\nThe admission step rejects invalid packet schemas, failed validation, missing\ndigests, and unbounded evidence. It gives the analysis agent the rows, metadata,\ncaveats, and business context needed for judgment, capped to an explicit analysis\nview. The complete source packet remains bound by digest; the model must not\npretend a bounded view is exhaustive.\n\nEvery material claim and recommended action must cite one or more admitted source\ndigests. Runx's native evidence verifier rejects invented references, changed\nobjective\u002Fsite identity, empty claims, missing decision fields, and unsupported\nexternal-effect claims. A failure becomes `needs_more_evidence`, not a polished\nguess.\n\n## Reading the combined signal\n\nSearch evidence explains discovery: queries, pages, impressions, clicks, CTR,\nposition, freshness, and coverage. Analytics explains behavior and business\noutcomes under the property's measurement model. Site evidence explains what is\nactually published, crawlable, structured, internally linked, and supportable.\n\nUse their disagreement. Rising impressions with weak CTR can justify inspecting\nsnippet fit, intent, brand recognition, or SERP composition. Strong clicks with\nweak engagement can justify checking landing-page promise, speed, navigation,\nor measurement. Analytics decline without a matching Search Console decline can\npoint toward tagging, channel classification, consent, conversion configuration,\nor non-Google traffic. These are hypotheses until the relevant evidence is\ncollected.\n\nCompare identical date windows, page identities, search types, dimensions,\ntimezone assumptions, and definitions. Preserve incomplete Search Console data,\nGA4 thresholding, sampling, `(other)`-row loss, pagination, and imported-source\nstatus as caveats. Do not convert correlation into causation.\n\n## SEO and answer-engine work\n\nTechnical SEO recommendations require site evidence. Check indexability,\ncanonicalization, robots rules, sitemap membership, status codes, rendering,\nstructured data eligibility, internal discovery paths, and page duplication\nbefore prescribing a fix. Search Console URL inspection is a point observation,\nnot authority to mutate the site or request indexing.\n\nContent recommendations should connect a demonstrated audience need to a page,\nbusiness outcome, and information gap. Avoid producing pages merely because a\nkeyword exists. Consolidation, deletion, template repair, internal linking, or a\nbetter primary answer may beat another article.\n\nFor answer-engine or \"GEO\" work, optimize the underlying source quality:\nunambiguous entities, direct answers, original evidence, clear authorship and\ndates, machine-readable structure, stable URLs, strong internal context, and\nclaims that another system can verify. There is no reliable switch for AI\ncitations and no basis for guaranteeing inclusion. Treat answer-engine\nvisibility as an observed channel that needs its own evidence, not as a mystical\nranking score.\n\n## Action packet\n\nA ready packet contains:\n\n- an executive summary and bounded analysis scope;\n- evidence-bound observations and explicit hypotheses;\n- prioritized opportunities;\n- recommended actions with rationale, source digests, owner type, effort,\n  confidence, expected signal, stop condition, and verification method;\n- a dedicated answer-engine review where evidence supports it;\n- a measurement plan with baselines, leading and business outcomes, comparison\n  windows, and rollback or reconsideration triggers;\n- risks, missing evidence, and the authoritative source inventory.\n\nThe action list remains `external_status: not_executed`. Route implementation\nto the owning repository or business workflow. Content changes may move through\na governed content pipeline; code and template work belongs in the site's\nrepository workflow; publication and provider mutations keep their own approval\nand readback gates.\n\n## A useful operating loop\n\nRun a narrow baseline, choose one evidence-bound action, make the change through\nits owner, wait for an appropriate observation window, then rerun the same\nqueries. Preserve the original packet digests. Change several variables together\nonly when the operator accepts that attribution will be weaker.\n\nStop when no source is admitted, page\u002Fproperty identity cannot be aligned, the\ndate windows are incomparable, privacy or pagination caveats defeat the claim,\nthe requested recommendation needs technical\u002Fcontent evidence that is absent,\nthe agent cites a source outside the admitted set, or the objective asks for\nguaranteed ranking, mass low-value content, deceptive markup, or unapproved\npublication.\n\nThe deterministic module only admits and bounds organic-growth domain evidence.\nIt does not hash evidence, call providers, or implement generic verification.\nRunx owns native digest provenance, evidence verification, agent receipts, and\nall downstream effect gates.\n\n## Agent task contract\n\n### `organic-growth-analyze`\n\nReturn `growth_candidate` with `decision: ready`, the exact objective and\nsite_url, executive_summary, observations, hypotheses, opportunities,\nrecommended_actions, geo_review, measurement_plan, claims, risks,\nmissing_evidence, and `external_status: not_executed`.\n\nEach claim requires a non-empty `claim` and admitted `source_digests`. Every\nrecommended action requires non-empty `source_digests` plus a rationale,\npriority, confidence, effort, expected_signal, verification, and stop_condition.\nMark statements as observed, inferred, or hypothesized. Preserve source caveats,\ndo not invent metrics or causes, and do not claim a change, publication,\nprovider call, ranking result, or AI citation occurred.\n\n### `organic-growth-collect`\n\nAcquire relevant missing evidence for the exact objective\u002Fsite, using the named\nread-only skill defaults and native asks if a genuine selector is missing. Do\nnot submit sitemaps, alter analytics, publish, crawl unrelated sites or invent\nmissing metrics. Use the returned tool schemas. Google sources are optional.\nRead a useful relevant public page if no source was supplied. Fetch explicit\npage URLs directly; avoid redundant reads and broad speculative crawling.\n\nReturn exactly `search_evidence`, `analytics_evidence`, `site_evidence` and\n`collection_notes`. Use empty objects\u002Farray for absent sources. Forward actual\nnormalized Google packet data unchanged. For a text page, forward the unchanged\n`provider_operation.data.result` as an individual site-evidence record, never\nthe provider packet wrapper. Preserve final URL, digest, text and provenance.\nRecord inaccessible sources, actual read errors and missing measurement context\nas notes. Do not perform synthesis; the next analysis turn owns it. No source\nmeans honest missing evidence. Do not claim a provider call you did not make.\n",{"name":5,"description":7},"main","e05cdf515dab5eb262dd9357ac85f923b4cb21b1","skills\u002Forganic-growth",108,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx","https:\u002F\u002Frunx.ai","https:\u002F\u002Fgithub.com\u002Frunxhq","the governed runtime for agent skills","2026-11-09 02:24:51",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add runxhq\u002Frunx --skill organic-growth",{"tool":70,"command":71},"bunx","bunx skills add runxhq\u002Frunx --skill organic-growth",{"tool":73,"command":74},"pnpm","pnpm dlx skills add runxhq\u002Frunx --skill organic-growth","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Forganic-growth\u002FSKILL.md",true,[78,84,88,92,98,104,110,114,118,122],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"fixtures\u002Fcomposes-in-graph.yaml","REFERENCE","参考文档",4364,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Forganic-growth\u002Ffixtures\u002Fcomposes-in-graph.yaml",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"fixtures\u002Fdefault-opens-collection.yaml",427,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Forganic-growth\u002Ffixtures\u002Fdefault-opens-collection.yaml",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"fixtures\u002Fdefault-reuses-sources.yaml",8496,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Forganic-growth\u002Ffixtures\u002Fdefault-reuses-sources.yaml",{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"fixtures\u002Fsupport\u002Fcomposed.graph","OTHER","其他",2780,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Forganic-growth\u002Ffixtures\u002Fsupport\u002Fcomposed.graph",{"path":99,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":102,"sourceHtmlUrl":103},"mark.svg","ASSET","资产文件",337,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Forganic-growth\u002Fmark.svg",{"path":105,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":108,"sourceHtmlUrl":109},"organic-growth.mjs","SCRIPT","脚本",10546,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Forganic-growth\u002Forganic-growth.mjs",{"path":111,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":112,"sourceHtmlUrl":113},"organic-growth.test.mjs",2046,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Forganic-growth\u002Forganic-growth.test.mjs",{"path":115,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Fcatalog.md",154,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Forganic-growth\u002Freferences\u002Fcatalog.md",{"path":119,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":120,"sourceHtmlUrl":121},"references\u002Fmark-license.md",3208,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Forganic-growth\u002Freferences\u002Fmark-license.md",{"path":123,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":124,"sourceHtmlUrl":125},"run.yaml",27755,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Forganic-growth\u002Frun.yaml",[127,151,172,188,207,224],{"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":50},"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",[133],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[135,136,137,138,139,12,140,141,142,143,45,144,145,146,147,148,36,149,150],"webhook handoff","webhook","handoff","workflow","receiver","deliver","catch","acknowledgement","hook","zapier","n8n","payload","approval","context","cloud","validate",{"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":157,"publishedAt":50},"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",[],[158,49,159,160,48,161,162,163,164,165,166,167,168,42,169,170,171],"web search","web","cost","preserve","source","for","fresh","discover","query","selection","provider","SET","prepare","research",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":178,"publishedAt":50},"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",[],[179,180,159,162,181,182,45,183,184,185,186,187],"fetch","web fetch","hosts","content","full","digest","extract","public","provenance",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":195,"publishedAt":50},"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",[194],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[196,197,198,199,200,201,161,202,203,204,205,206],"vuln triage","triage","prioritize","vulnerability","remediation","coverage","unknown","advisory","draft","practical","coordinate",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":214,"publishedAt":50},"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",[213],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[209,215,163,45,216,217,218,219,220,221,168,42,147,222,223,36],"live","hygiene","posting","plans","act","gated","three","work","timeline",{"skillNo":225,"name":226,"nameZh":6,"description":227,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":228,"categories":229,"keywords":231,"publishedAt":50},"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",[230],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[232,233,234,148,235,236,222,48,237,238,45,162],"team delegate","delegate","team","across","operator","scope","acceptance"]