[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E8G31B0DDF2QPKEVM9V6HB":3,"skill-same:01M7E8G31B0DDF2QPKEVM9V6HB":58},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":14,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":37,"updatedAt":38,"install":39,"resources":51},"01M7E8G31B0DDF2QPKEVM9V6HB","ask",null,"Answer a question from a finished study, citing back into its evidence, and say plainly when the study does not cover it","tony\u002Fskills","tony","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F26336?v=4","01M72E5RNJ7SQV8F9KBM5RKRMN","Tony Narlock","01M7E7MBN5C6YZ4JJJ5Y82KBJG",0,"MIT","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fscholar\u002Fskills\u002Fask\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ask\ndescription: \"Answer a question from a finished study, citing back into its evidence, and say plainly when the study does not cover it\"\nallowed-tools: [\"Read\", \"Grep\", \"Glob\", \"AskUserQuestion\"]\nargument-hint: \"\u003Cquestion> [--study=\u003Cdir>]\"\ndisable-model-invocation: true\n---\n\n\n# \u002Fscholar:ask\n\nConsult a study instead of re-reading the corpus. Answers come from\n`terms.jsonl` and the evidence documents, and they carry the citation the\nstudy already earned.\n\nUser arguments: $ARGUMENTS\n\nWithout `--study`, the study is found as stage-gates.md describes under \"The\nstudy directory\" (`..\u002F..\u002Freferences\u002Fstage-gates.md`).\n\nRead `..\u002F..\u002Freferences\u002Foutput-contract.md` before answering.\n\n## Answer from the evidence, or name the gap\n\nAn agent asked a question about a corpus it has partly read will reason from\nthe parts it has to the parts it has not, and the result is indistinguishable\nin tone from an answer it actually knows. This skill does not do that.\n\nWhere the study does not cover the question, say so, and say what would have\nto be read to cover it. That answer is more useful than a plausible one,\nbecause it can be acted on: `sources.jsonl` already records what was skipped\nand why.\n\n## Procedure\n\n### 1. Locate the question in the ontology\n\nWhich terms does it touch, and which types do they sit under. A question that\ntouches no term in the table is a coverage question, not a lookup.\n\n### 2. Answer from the rows\n\nEvery claim in the answer names the evidence file and the term row it came\nfrom. An answer with no citations is either trivial or invented.\n\n### 3. Trace on request\n\n\"Show me the evidence for X\" is a question this skill answers: the term's\ndefinition, every citation with its locator, any measurement that mentions it,\nand any verdict `contest` recorded about it. That chain is what lets a reader\ncheck the study rather than trust it.\n\n### 4. Say what is missing\n\nDistinguish three cases, because they mean different things:\n\n- The study covers the question and the answer is here.\n- The study read the relevant source and the corpus does not settle the\n  question. That is a fact about the corpus.\n- The study never read the relevant source. That is a fact about the study,\n  and `sources.jsonl` says why it was skipped.\n\n## Rules\n\n- Never cite the corpus directly. If the answer needs a source the study did\n  not read, that is case three; report it and stop.\n- Quote the study's own words for a definition rather than paraphrasing; a\n  paraphrase silently drops the distinction the term exists to carry.\n\n## Output\n\nPer `..\u002F..\u002Freferences\u002Foutput-contract.md`. Hero: `✓ answered from \u003Cn> terms`,\n`⚠ Not covered: \u003Cwhat would have to be read>` when the study exists but does\nnot settle the question, or `⚠ Blocked: \u003Creason>` when no study is at the path.\nA question the study answers in part takes the `✓` hero, with the rest under\n`## Gaps`.\nA blocked run is the halted-run shape; the unblock is the real study path, or\n`\u002Fscholar:ontology` to build one:\n\n```text\n⚠ Blocked: no study at notes\u002Fontology\u002Fsample-lib\u002F, so there is no terms.jsonl to answer from.\n\nPass --study with the path of an existing study, or run \u002Fscholar:ontology on the corpus.\n```\n\nSections, for the first two heroes:\n\n1. `## Answer`: the answer, each claim citing its evidence file and row.\n2. `## Evidence`: the chain: definitions, citations with locators, and any\n   verdict recorded about the terms involved.\n3. `## Gaps`: what the question needs and the study does not settle, and\n   which of the three cases applies. Add no gap the question did not ask\n   about.\n\nThe hero is exactly the line above, with nothing after the count.\n\nNext-step options: widen the study to cover the gap, ask another question, stop\nhere.\n\nWrite it per `..\u002F..\u002Freferences\u002Fprose-rules.md`.\n","# \u002Fscholar:ask\n\nConsult a study instead of re-reading the corpus. Answers come from\n`terms.jsonl` and the evidence documents, and they carry the citation the\nstudy already earned.\n\nUser arguments: $ARGUMENTS\n\nWithout `--study`, the study is found as stage-gates.md describes under \"The\nstudy directory\" (`..\u002F..\u002Freferences\u002Fstage-gates.md`).\n\nRead `..\u002F..\u002Freferences\u002Foutput-contract.md` before answering.\n\n## Answer from the evidence, or name the gap\n\nAn agent asked a question about a corpus it has partly read will reason from\nthe parts it has to the parts it has not, and the result is indistinguishable\nin tone from an answer it actually knows. This skill does not do that.\n\nWhere the study does not cover the question, say so, and say what would have\nto be read to cover it. That answer is more useful than a plausible one,\nbecause it can be acted on: `sources.jsonl` already records what was skipped\nand why.\n\n## Procedure\n\n### 1. Locate the question in the ontology\n\nWhich terms does it touch, and which types do they sit under. A question that\ntouches no term in the table is a coverage question, not a lookup.\n\n### 2. Answer from the rows\n\nEvery claim in the answer names the evidence file and the term row it came\nfrom. An answer with no citations is either trivial or invented.\n\n### 3. Trace on request\n\n\"Show me the evidence for X\" is a question this skill answers: the term's\ndefinition, every citation with its locator, any measurement that mentions it,\nand any verdict `contest` recorded about it. That chain is what lets a reader\ncheck the study rather than trust it.\n\n### 4. Say what is missing\n\nDistinguish three cases, because they mean different things:\n\n- The study covers the question and the answer is here.\n- The study read the relevant source and the corpus does not settle the\n  question. That is a fact about the corpus.\n- The study never read the relevant source. That is a fact about the study,\n  and `sources.jsonl` says why it was skipped.\n\n## Rules\n\n- Never cite the corpus directly. If the answer needs a source the study did\n  not read, that is case three; report it and stop.\n- Quote the study's own words for a definition rather than paraphrasing; a\n  paraphrase silently drops the distinction the term exists to carry.\n\n## Output\n\nPer `..\u002F..\u002Freferences\u002Foutput-contract.md`. Hero: `✓ answered from \u003Cn> terms`,\n`⚠ Not covered: \u003Cwhat would have to be read>` when the study exists but does\nnot settle the question, or `⚠ Blocked: \u003Creason>` when no study is at the path.\nA question the study answers in part takes the `✓` hero, with the rest under\n`## Gaps`.\nA blocked run is the halted-run shape; the unblock is the real study path, or\n`\u002Fscholar:ontology` to build one:\n\n```text\n⚠ Blocked: no study at notes\u002Fontology\u002Fsample-lib\u002F, so there is no terms.jsonl to answer from.\n\nPass --study with the path of an existing study, or run \u002Fscholar:ontology on the corpus.\n```\n\nSections, for the first two heroes:\n\n1. `## Answer`: the answer, each claim citing its evidence file and row.\n2. `## Evidence`: the chain: definitions, citations with locators, and any\n   verdict recorded about the terms involved.\n3. `## Gaps`: what the question needs and the study does not settle, and\n   which of the three cases applies. Add no gap the question did not ask\n   about.\n\nThe hero is exactly the line above, with nothing after the count.\n\nNext-step options: widen the study to cover the gap, ask another question, stop\nhere.\n\nWrite it per `..\u002F..\u002Freferences\u002Fprose-rules.md`.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":29,"disable-model-invocation":30},[25,26,27,28],"Read","Grep","Glob","AskUserQuestion","\u003Cquestion> [--study=\u003Cdir>]",true,"main","5fbeb3b47beedea13813be7b7023f736a8d97a65","plugins\u002Fscholar\u002Fskills\u002Fask","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills","https:\u002F\u002Fgithub.com\u002Ftony","https:\u002F\u002Ftony.sh","lighthouse keeper","2026-11-08 17:57:34",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":30},[41,44,47],{"tool":42,"command":43},"npx","npx skills add tony\u002Fskills --skill ask",{"tool":45,"command":46},"bunx","bunx skills add tony\u002Fskills --skill ask",{"tool":48,"command":49},"pnpm","pnpm dlx skills add tony\u002Fskills --skill ask","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fscholar\u002Fskills\u002Fask\u002FSKILL.md",[52],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"agents\u002Fopenai.yaml","REFERENCE","参考文档",297,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fscholar\u002Fskills\u002Fask\u002Fagents\u002Fopenai.yaml",[59,66,73,80,87,94],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7E8NCSHXV2JPW4J61R0TQS7","serene-bliss","Use when asked to make a CLI --help, docs page, error message, or tooling UX more serene or calmer for developer experience; returns text, no edits.","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fserene-bliss\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7E8N87MAVJD8RRQKQB1ZPS6","review","Weave code review: run independent adversarial reviews in parallel, then synthesize findings","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7E8N402XG4ZBFNACQ413163","refine","Use when asked to refine a draft, iterate on code until cleaner, or polish a README through repeated critique and improvement.","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Frefine\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7E8N01KB86A7136P00GVKJW","prompt","Weave prompt: compare independent adversarial implementations, then adopt the single best one","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fprompt\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7E8MW7YJW2PCMDW3G9RTGNK","plan","Weave planning: compare independent adversarial plans, then synthesize the best one","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fplan\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7E8MSBYXNCV4ZYWDS4PFJXK","fix-review","Fix weave review findings: validate, add test coverage, fix, and commit each as atomic changes","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Ffix-review\u002FSKILL.md",[],[]]