[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6R5GG5BBCQFW8AQMPTKKKPV":3,"skill-same:01M6R5GG5BBCQFW8AQMPTKKKPV":129},{"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":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},"01M6R5GG5BBCQFW8AQMPTKKKPV","diagnose-skill-run",null,"Diagnose a failed or suspicious Runx skill execution from receipts and test evidence, then propose the smallest bounded improvement without replaying the failed operation.","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\u002Fdiagnose-skill-run\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,12,33,34],"diagnose","run","diagnose skill run","harness","evidence","improvement","execution","operation","suspicious","receipts","bounded","2026-11-10 10:12:30",false,"---\nname: diagnose-skill-run\ndescription: Diagnose a failed or suspicious Runx skill execution from receipts and test evidence, then propose the smallest bounded improvement without replaying the failed operation.\n---\n\n# Diagnose Skill Run\n\nDiagnose what went wrong in a skill or workflow execution and propose the\nsmallest change that fixes it.\n\nThe default resolves an exact `receipt_id` through native `receipt-query#read`, then combines its\nredacted receipt detail with the supplied failure summary or test output.\nThe native detail is authoritative for status, verification, authority, acts,\ndecisions, criterion status, references, and seal posture. It deliberately\nexcludes raw execution bodies, stdout, stderr, credential values and context\nbodies. When a retained declared output matters, use the offered native\n`receipt.prove`\u002F`receipt.read` tools to follow verified child references and read\nonly the exact relevant claim or JSON pointer. Read permitted source and\nexplicitly supplied ordinary logs with bounded `fs.read_bundle`\u002F`fs.search`.\nThose tools retain the existing workspace and private-path guards. A denied,\nunretained or omitted diagnostic is an evidence gap, not permission to inspect\nprivate runtime files or reconstruct the failed operation. Raw transport logs\nare not exposed by the claim reader; request the specific bounded sanitized\nmaterial if it is needed.\n\nDistinguish root cause from symptoms. A workflow may report failure at step 4,\nbut the root cause may be bad output from step 2 that propagated through\ncontext passing. Trace data flow backward through context edges to find\nwhere the problem originated.\n\nClassify the failure:\n\n- **Input error** — required input missing or malformed. Fix: input\n  validation or input resolution.\n- **Scope denial** — step requested scopes outside the workflow grant.\n  Fix: correct an overbroad request or the intended binding under operator\n  authority; never silently widen the grant.\n- **Tool failure** — CLI tool or adapter returned an error. Fix: tool\n  invocation (args, env, cwd) or the tool itself.\n- **Schema mismatch** — step output did not match expected shape for\n  downstream context. Fix: output parsing or artifact contract.\n- **Timeout** — step exceeded time budget. Fix: increase timeout,\n  reduce unnecessary work or preserve progress across bounded pages. Inspect\n  the owning operation before increasing a timeout or imposing a product cap.\n- **Policy denial** — transition gate blocked the step. Fix: gate\n  conditions or upstream output.\n- **Review rejection** — adversarial review found blocking issues.\n  Fix: the code or spec, not the review process.\n- **Test assertion** — fixture expectations did not match actual\n  output. Fix: skill logic or stale fixture expectations.\n\n## Composes\n\n\u003C!-- Generated from the native closure; run pnpm core-skills:composes:generate. -->\n\n- `receipt-query#read`\n\n## Agent-mediated suspension is not a failure\n\nA receipt sealed with reason `needs_agent`, or whose workflow status is `deferred`, denotes a healthy\nagent-mediated suspension, not a defect. The runtime yielded to the\ncaller for missing agent or human input.\nThis is a normal part of workflow execution, not one of the failure\nclasses above. When the only evidence is `needs_agent` without\nany exit code, scope denial, schema mismatch, or other concrete\nfailure signal, return `verdict: pass` with an empty\n`improvement_proposals` array and note that the workflow is paused as\ndesigned.\n\nA ledger answer of `needs_agent` because no audit question was supplied is not\nproof that a different run is paused. Check the actual run\u002Freceipt state; do not\nclassify from a matching word in a summary. Separate observed failure facts,\ncausal interpretation and hypotheses. If the required body or diagnostic is\nunavailable, return `blocked` with the exact next evidence instead of a plausible\nroot cause. Do not equate valid receipt signatures with provider or test truth.\n\nOne failure, one fix. Propose the smallest change that addresses the root\ncause. Do not bundle unrelated improvements.\n\n\n## Output\n\nThe stable failure packet, `runx\u002Fdiagnose-skill-run.diagnosis.v1`, is consumed directly by\n`skill-build improve`. Agents should self-validate before returning, and\ndownstream consumers (notably the `skill-build improve` method) may validate on\nreceipt.\n\n- `verdict`: `pass`, `needs_update`, or `blocked`.\n- `failure_summary`: which step, which failure class, what root cause.\n  One to three sentences.\n- `improvement_proposals`: array of bounded changes. Each:\n  - `target`: what to change (SKILL.md, execution profile, workflow step, input, fixture)\n  - `change`: what specifically to change\n  - `rationale`: why this fixes the root cause\n  - `risk`: what could go wrong\n- `next_test_checks`: replayable checks that should pass after the fix.\n\n## Inputs\n\nSupply whichever evidence is available. Without a receipt ID, the default does\nnot scan the ledger: it diagnoses only the bounded supplemental material. A\ncompleted `receipt_evidence` packet skips lookup; `from-evidence` accepts it\nexplicitly for a workflow. Preserve the source receipt and its verification\nposture; reuse is not independent verification in this phase. Neither path\nreplays the failed work.\n\n\n- `receipt_id`: exact receipt id to inspect.\n- `receipt_evidence`: completed `runx\u002Freceipt-query.answer.v1` to reuse.\n- `receipt_summary`: sanitized receipt or test summary.\n- `receipt_details`: native redacted receipt projections for deterministic\n  replay only; live runs resolve them from `receipt_id`.\n- `test_output`: failed test output or assertion text.\n- `skill_path`: path to the skill being improved.\n- `receipt_rows`: native-projection rows for deterministic replay only; live\n  runs resolve `receipt_id` from the configured receipt store.\n\n## Agent task: diagnose-skill-run\n\nReturn a `diagnosis` object with verdict, failure_summary, improvement_proposals\nand next_test_checks. Optional `evidence` entries are exact source references;\nthey are reviewer references, not self-authenticating proof. The deterministic\nfinish preserves the existing diagnosis packet and its evidence posture.\n\nDiagnose one failure from native redacted receipt detail plus the supplied summary or test\noutput. Treat needs_agent or a deferred receipt as a healthy suspension unless another concrete\nfailure signal exists. Ground authority, acts, decisions, criteria, and seal posture in\nreceipt_evidence.receipt_details; treat caller summaries as supplemental evidence, never as a\nreplacement for native facts. Distinguish input, scope, tool, schema, timeout, policy, review,\nand test failures. If receipt_id was supplied but native evidence did not match it, return\nblocked unless the supplied test output alone proves the defect. Return verdict, a concise\nfailure_summary, at most three bounded improvement_proposals, and replayable\nnext_test_checks. Each proposal must name target, change, rationale, and risk. Do not write\nfiles or weaken a refusal.\n\nRead only what the question requires. Do not echo secret values from a retained\nclaim or supplied log. Report a sensitive field\u002Flocator and the required handling\nwithout claiming the entire omitted log is secret-free. If the fault is in caller\ninputs, a stale fixture or an owning native boundary, name that owner; do not add\na compatibility alias or weaken the skill to make the bad invocation pass.\n","# Diagnose Skill Run\n\nDiagnose what went wrong in a skill or workflow execution and propose the\nsmallest change that fixes it.\n\nThe default resolves an exact `receipt_id` through native `receipt-query#read`, then combines its\nredacted receipt detail with the supplied failure summary or test output.\nThe native detail is authoritative for status, verification, authority, acts,\ndecisions, criterion status, references, and seal posture. It deliberately\nexcludes raw execution bodies, stdout, stderr, credential values and context\nbodies. When a retained declared output matters, use the offered native\n`receipt.prove`\u002F`receipt.read` tools to follow verified child references and read\nonly the exact relevant claim or JSON pointer. Read permitted source and\nexplicitly supplied ordinary logs with bounded `fs.read_bundle`\u002F`fs.search`.\nThose tools retain the existing workspace and private-path guards. A denied,\nunretained or omitted diagnostic is an evidence gap, not permission to inspect\nprivate runtime files or reconstruct the failed operation. Raw transport logs\nare not exposed by the claim reader; request the specific bounded sanitized\nmaterial if it is needed.\n\nDistinguish root cause from symptoms. A workflow may report failure at step 4,\nbut the root cause may be bad output from step 2 that propagated through\ncontext passing. Trace data flow backward through context edges to find\nwhere the problem originated.\n\nClassify the failure:\n\n- **Input error** — required input missing or malformed. Fix: input\n  validation or input resolution.\n- **Scope denial** — step requested scopes outside the workflow grant.\n  Fix: correct an overbroad request or the intended binding under operator\n  authority; never silently widen the grant.\n- **Tool failure** — CLI tool or adapter returned an error. Fix: tool\n  invocation (args, env, cwd) or the tool itself.\n- **Schema mismatch** — step output did not match expected shape for\n  downstream context. Fix: output parsing or artifact contract.\n- **Timeout** — step exceeded time budget. Fix: increase timeout,\n  reduce unnecessary work or preserve progress across bounded pages. Inspect\n  the owning operation before increasing a timeout or imposing a product cap.\n- **Policy denial** — transition gate blocked the step. Fix: gate\n  conditions or upstream output.\n- **Review rejection** — adversarial review found blocking issues.\n  Fix: the code or spec, not the review process.\n- **Test assertion** — fixture expectations did not match actual\n  output. Fix: skill logic or stale fixture expectations.\n\n## Composes\n\n\u003C!-- Generated from the native closure; run pnpm core-skills:composes:generate. -->\n\n- `receipt-query#read`\n\n## Agent-mediated suspension is not a failure\n\nA receipt sealed with reason `needs_agent`, or whose workflow status is `deferred`, denotes a healthy\nagent-mediated suspension, not a defect. The runtime yielded to the\ncaller for missing agent or human input.\nThis is a normal part of workflow execution, not one of the failure\nclasses above. When the only evidence is `needs_agent` without\nany exit code, scope denial, schema mismatch, or other concrete\nfailure signal, return `verdict: pass` with an empty\n`improvement_proposals` array and note that the workflow is paused as\ndesigned.\n\nA ledger answer of `needs_agent` because no audit question was supplied is not\nproof that a different run is paused. Check the actual run\u002Freceipt state; do not\nclassify from a matching word in a summary. Separate observed failure facts,\ncausal interpretation and hypotheses. If the required body or diagnostic is\nunavailable, return `blocked` with the exact next evidence instead of a plausible\nroot cause. Do not equate valid receipt signatures with provider or test truth.\n\nOne failure, one fix. Propose the smallest change that addresses the root\ncause. Do not bundle unrelated improvements.\n\n\n## Output\n\nThe stable failure packet, `runx\u002Fdiagnose-skill-run.diagnosis.v1`, is consumed directly by\n`skill-build improve`. Agents should self-validate before returning, and\ndownstream consumers (notably the `skill-build improve` method) may validate on\nreceipt.\n\n- `verdict`: `pass`, `needs_update`, or `blocked`.\n- `failure_summary`: which step, which failure class, what root cause.\n  One to three sentences.\n- `improvement_proposals`: array of bounded changes. Each:\n  - `target`: what to change (SKILL.md, execution profile, workflow step, input, fixture)\n  - `change`: what specifically to change\n  - `rationale`: why this fixes the root cause\n  - `risk`: what could go wrong\n- `next_test_checks`: replayable checks that should pass after the fix.\n\n## Inputs\n\nSupply whichever evidence is available. Without a receipt ID, the default does\nnot scan the ledger: it diagnoses only the bounded supplemental material. A\ncompleted `receipt_evidence` packet skips lookup; `from-evidence` accepts it\nexplicitly for a workflow. Preserve the source receipt and its verification\nposture; reuse is not independent verification in this phase. Neither path\nreplays the failed work.\n\n\n- `receipt_id`: exact receipt id to inspect.\n- `receipt_evidence`: completed `runx\u002Freceipt-query.answer.v1` to reuse.\n- `receipt_summary`: sanitized receipt or test summary.\n- `receipt_details`: native redacted receipt projections for deterministic\n  replay only; live runs resolve them from `receipt_id`.\n- `test_output`: failed test output or assertion text.\n- `skill_path`: path to the skill being improved.\n- `receipt_rows`: native-projection rows for deterministic replay only; live\n  runs resolve `receipt_id` from the configured receipt store.\n\n## Agent task: diagnose-skill-run\n\nReturn a `diagnosis` object with verdict, failure_summary, improvement_proposals\nand next_test_checks. Optional `evidence` entries are exact source references;\nthey are reviewer references, not self-authenticating proof. The deterministic\nfinish preserves the existing diagnosis packet and its evidence posture.\n\nDiagnose one failure from native redacted receipt detail plus the supplied summary or test\noutput. Treat needs_agent or a deferred receipt as a healthy suspension unless another concrete\nfailure signal exists. Ground authority, acts, decisions, criteria, and seal posture in\nreceipt_evidence.receipt_details; treat caller summaries as supplemental evidence, never as a\nreplacement for native facts. Distinguish input, scope, tool, schema, timeout, policy, review,\nand test failures. If receipt_id was supplied but native evidence did not match it, return\nblocked unless the supplied test output alone proves the defect. Return verdict, a concise\nfailure_summary, at most three bounded improvement_proposals, and replayable\nnext_test_checks. Each proposal must name target, change, rationale, and risk. Do not write\nfiles or weaken a refusal.\n\nRead only what the question requires. Do not echo secret values from a retained\nclaim or supplied log. Report a sensitive field\u002Flocator and the required handling\nwithout claiming the entire omitted log is secret-free. If the fault is in caller\ninputs, a stale fixture or an owning native boundary, name that owner; do not add\na compatibility alias or weaken the skill to make the bad invocation pass.\n",{"name":5,"description":7},"main","14cf84bcc80d7abf0008335efac4d92aacfa682e","skills\u002Fdiagnose-skill-run",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 diagnose-skill-run",{"tool":55,"command":56},"bunx","bunx skills add runxhq\u002Frunx --skill diagnose-skill-run",{"tool":58,"command":59},"pnpm","pnpm dlx skills add runxhq\u002Frunx --skill diagnose-skill-run","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002FSKILL.md",true,[63,69,73,79,83,87,93,97,101,105,109,113,117,121,125],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"diagnose-skill-run.mjs","SCRIPT","脚本",3707,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Fdiagnose-skill-run.mjs",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"diagnose-skill-run.test.mjs",2444,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Fdiagnose-skill-run.test.mjs",{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"eval_queries.json","REFERENCE","参考文档",2292,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Feval_queries.json",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"evals\u002Fevals.json",1478,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Fevals\u002Fevals.json",{"path":84,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":85,"sourceHtmlUrl":86},"evals\u002Ffiles\u002Fcontext-flattening-failure.json",2639,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Fevals\u002Ffiles\u002Fcontext-flattening-failure.json",{"path":88,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":91,"sourceHtmlUrl":92},"mark.svg","ASSET","资产文件",465,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Fmark.svg",{"path":94,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":95,"sourceHtmlUrl":96},"packets\u002Fdiagnosis.v1.schema.json",501,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Fpackets\u002Fdiagnosis.v1.schema.json",{"path":98,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fcatalog.md",159,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Freferences\u002Fcatalog.md",{"path":102,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fmark-license.md",3208,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Freferences\u002Fmark-license.md",{"path":106,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":107,"sourceHtmlUrl":108},"run.yaml",6954,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Frun.yaml",{"path":110,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":111,"sourceHtmlUrl":112},"tests\u002Fcomposes-in-workflow.yaml",914,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Ftests\u002Fcomposes-in-workflow.yaml",{"path":114,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":115,"sourceHtmlUrl":116},"tests\u002Fdiagnose-skill-run-finds-context-flattening.yaml",2584,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Ftests\u002Fdiagnose-skill-run-finds-context-flattening.yaml",{"path":118,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":119,"sourceHtmlUrl":120},"tests\u002Fdiagnose-skill-run-passes-on-paused-workflow.yaml",1115,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Ftests\u002Fdiagnose-skill-run-passes-on-paused-workflow.yaml",{"path":122,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":123,"sourceHtmlUrl":124},"tests\u002Fno-evidence.yaml",311,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Ftests\u002Fno-evidence.yaml",{"path":126,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":127,"sourceHtmlUrl":128},"tests\u002Fsupplemental-only.yaml",1319,"https:\u002F\u002Fgithub.com\u002Frunxhq\u002Frunx\u002Fblob\u002Fmain\u002Fskills\u002Fdiagnose-skill-run\u002Ftests\u002Fsupplemental-only.yaml",[130,155,177,193,212,229],{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":137,"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",[136],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[138,139,140,141,142,143,12,144,145,146,147,148,149,150,151,30,152,153,154],"webhook","handoff","webhook handoff","approval","zapier","context","hook","cloud","payload","n8n","validate","catch","with","workflow","acknowledgement","deliver","receiver",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"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",[],[162,163,164,165,166,167,168,169,170,171,28,172,173,34,174,175,176],"web","search","web search","fresh","preserve","query","selection","provider","for","discover","SET","cost","prepare","source","research",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"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",[],[184,185,162,186,187,188,189,190,191,150,192,175],"fetch","web fetch","full","content","extract","public","digest","hosts","provenance",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":200,"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",[199],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[201,202,166,203,204,205,206,207,208,209,210,211],"triage","vuln triage","prioritize","remediation","draft","advisory","vulnerability","unknown","coordinate","practical","coverage",{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":216,"categories":217,"keywords":219,"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",[218],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[214,28,220,221,150,222,30,169,170,223,224,225,141,226,227,228],"gated","work","plans","three","posting","hygiene","timeline","live","act",{"skillNo":230,"name":231,"nameZh":6,"description":232,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":233,"categories":234,"keywords":236,"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",[235],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[237,238,239,34,143,175,240,221,150,241,242,243],"team","team delegate","delegate","operator","across","acceptance","scope"]