[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E80VMNYACSHW5B495WYWHY":3,"skill-same:01M7E80VMNYACSHW5B495WYWHY":80},{"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":35,"commitSha":36,"skillDirectory":37,"forksCount":14,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":55},"01M7E80VMNYACSHW5B495WYWHY","scholar-revise",null,"Record a correction to a standing claim: what was believed, what it rested on, and why it failed, rather than editing it away","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\u002F.agents\u002Fskills\u002Fscholar-revise\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: scholar-revise\ndescription: >-\n  Record a correction to a standing claim: what was believed, what it rested\n  on, and why it failed, rather than editing it away\ndisable-model-invocation: true\nallowed-tools: [\"Bash\", \"Read\", \"Glob\", \"Edit\", \"Write\", \"AskUserQuestion\"]\nmetadata:\n  argument-hint: \"\u003Cterm-or-claim> [--study=\u003Cdir>]\"\n  source: \"plugins\u002Fscholar\u002Fskills\u002Frevise\u002FSKILL.md\"\n---\n\n# this skill\n\nSomething the study asserted turned out to be wrong. This records that, rather\nthan quietly making it true.\n\nUser arguments: $ARGUMENTS\n\n`\u003Canalyzer>` is `references\u002Fterm_metrics.py`, resolved against this skill's\ndirectory to an absolute path.\n\nWithout `--study`, the study is found as \"The study directory\" describes in\n`references\u002Fstage-gates.md`.\n\nRead `references\u002Foutput-contract.md` before writing study files.\n\n## Why a correction is kept\n\nA retracted claim is worth more written down than deleted. Deleting it does\nnot delete it from anyone's memory. A figure that circulated and turned out to\nmeasure something else keeps being repeated by everyone who read it before the\nfix, and they have no way to learn otherwise unless the study says so.\n\nThe correction also carries information the replacement does not: knowing that\na plausible reading of the evidence was wrong tells the next reader which\nplausible readings to distrust.\n\n## Procedure\n\n### 1. Establish what is being overturned\n\nUsually from the `scholar-verify` skill (a citation that no longer says what it was\nquoted as saying) or from the `scholar-contest` skill (a later round that killed an\nearlier verdict). Take the claim as it currently stands, verbatim.\n\nRead the source the claim rested on at its recorded pin, and the evidence that\noverturns it. A correction written from the study's stored quotations alone\nrepeats whatever they got wrong. When the source cannot be read, stop with\n`⚠ Blocked` naming it.\n\n### 2. Record the correction first\n\nAppend the entry to `evidence\u002Fcorrections.md` before any edit to\n`terms.jsonl`, an evidence document, or the brief. An interrupted run then\nleaves the retraction on disk rather than a claim changed with no record.\n\n```markdown\n## \u003Cthe term or claim>\n\nWas: the claim as it stood, quoted exactly.\n\nRested on: the citation or measurement that supported it.\n\nFailed because: what overturned it, cited or measured.\n\nNow: the replacement claim, or a statement that the question is open.\n```\n\nAppend with `Edit` at the end of the file; never `Write` it back whole. Never\nrewrite an existing correction: a correction that was itself wrong gets its\nown entry beneath. Then read it back; this exits zero only when every entry\ncarries all four fields and the last one is the claim just recorded, so a\ncorrection that did not land stops the run before step 3:\n\n```console\n$ python3 \u003Canalyzer> notes\u002Fontology\u002F\u003Csubject>\u002F \\\n    --check-corrections \"\u003Cthe term or claim>\"\n```\n\n### 3. Update the study\n\nOnly after step 2 is on disk, change the affected row in `terms.jsonl` and the affected evidence document,\nthen link the correction from the brief's section so a reader of the brief\nmeets it. A brief edit can break the brief gate, so run it and report the\nresult in `## Touched`:\n\n```console\n$ python3 \u003Canalyzer> notes\u002Fontology\u002F\u003Csubject>\u002F --check-brief\n```\n\nFix the brief until it exits zero.\n\n## Rules\n\n- A correction states what overturned the claim, with the same evidence tier\n  the claim itself required. \"This turned out to be wrong\" is not a\n  correction.\n- Where the replacement is \"we do not know\", say that. A confident replacement\n  invented to fill the hole is worse.\n\n## Output\n\nPer `references\u002Foutput-contract.md`. Hero: `✓ corrected \u003Cclaim>` or `⚠\nBlocked: \u003Creason>`. Sections:\n\n1. `## Correction`: the four fields as plain `Was: ...` lines, never bold.\n2. `## Touched`: the rows and evidence documents updated, with no sentence\n   about an entry or file left as it was.\n3. `## Downstream`: anything else in the study that rested on the same\n   evidence and may now be unsupported.\n\nA halted run (no study, no standing claim to correct, or an unreadable source)\nis the halted-run shape:\n\n```text\n⚠ Blocked: no study at notes\u002Fontology\u002Fsample-lib\u002F to correct.\n\nPass the study path, or run scholar-ontology to build one.\n```\n\nNext-step options: verify the downstream claims, re-run contest, stop here.\n\nWrite it per `references\u002Fprose-rules.md`.\n\n\n## Portability notes\n\n- `$ARGUMENTS` — the text the user passed when invoking this skill. If your host does not substitute it, read it as the user's request in the current turn, and ask when there is none.\n- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.\n","# this skill\n\nSomething the study asserted turned out to be wrong. This records that, rather\nthan quietly making it true.\n\nUser arguments: $ARGUMENTS\n\n`\u003Canalyzer>` is `references\u002Fterm_metrics.py`, resolved against this skill's\ndirectory to an absolute path.\n\nWithout `--study`, the study is found as \"The study directory\" describes in\n`references\u002Fstage-gates.md`.\n\nRead `references\u002Foutput-contract.md` before writing study files.\n\n## Why a correction is kept\n\nA retracted claim is worth more written down than deleted. Deleting it does\nnot delete it from anyone's memory. A figure that circulated and turned out to\nmeasure something else keeps being repeated by everyone who read it before the\nfix, and they have no way to learn otherwise unless the study says so.\n\nThe correction also carries information the replacement does not: knowing that\na plausible reading of the evidence was wrong tells the next reader which\nplausible readings to distrust.\n\n## Procedure\n\n### 1. Establish what is being overturned\n\nUsually from the `scholar-verify` skill (a citation that no longer says what it was\nquoted as saying) or from the `scholar-contest` skill (a later round that killed an\nearlier verdict). Take the claim as it currently stands, verbatim.\n\nRead the source the claim rested on at its recorded pin, and the evidence that\noverturns it. A correction written from the study's stored quotations alone\nrepeats whatever they got wrong. When the source cannot be read, stop with\n`⚠ Blocked` naming it.\n\n### 2. Record the correction first\n\nAppend the entry to `evidence\u002Fcorrections.md` before any edit to\n`terms.jsonl`, an evidence document, or the brief. An interrupted run then\nleaves the retraction on disk rather than a claim changed with no record.\n\n```markdown\n## \u003Cthe term or claim>\n\nWas: the claim as it stood, quoted exactly.\n\nRested on: the citation or measurement that supported it.\n\nFailed because: what overturned it, cited or measured.\n\nNow: the replacement claim, or a statement that the question is open.\n```\n\nAppend with `Edit` at the end of the file; never `Write` it back whole. Never\nrewrite an existing correction: a correction that was itself wrong gets its\nown entry beneath. Then read it back; this exits zero only when every entry\ncarries all four fields and the last one is the claim just recorded, so a\ncorrection that did not land stops the run before step 3:\n\n```console\n$ python3 \u003Canalyzer> notes\u002Fontology\u002F\u003Csubject>\u002F \\\n    --check-corrections \"\u003Cthe term or claim>\"\n```\n\n### 3. Update the study\n\nOnly after step 2 is on disk, change the affected row in `terms.jsonl` and the affected evidence document,\nthen link the correction from the brief's section so a reader of the brief\nmeets it. A brief edit can break the brief gate, so run it and report the\nresult in `## Touched`:\n\n```console\n$ python3 \u003Canalyzer> notes\u002Fontology\u002F\u003Csubject>\u002F --check-brief\n```\n\nFix the brief until it exits zero.\n\n## Rules\n\n- A correction states what overturned the claim, with the same evidence tier\n  the claim itself required. \"This turned out to be wrong\" is not a\n  correction.\n- Where the replacement is \"we do not know\", say that. A confident replacement\n  invented to fill the hole is worse.\n\n## Output\n\nPer `references\u002Foutput-contract.md`. Hero: `✓ corrected \u003Cclaim>` or `⚠\nBlocked: \u003Creason>`. Sections:\n\n1. `## Correction`: the four fields as plain `Was: ...` lines, never bold.\n2. `## Touched`: the rows and evidence documents updated, with no sentence\n   about an entry or file left as it was.\n3. `## Downstream`: anything else in the study that rested on the same\n   evidence and may now be unsupported.\n\nA halted run (no study, no standing claim to correct, or an unreadable source)\nis the halted-run shape:\n\n```text\n⚠ Blocked: no study at notes\u002Fontology\u002Fsample-lib\u002F to correct.\n\nPass the study path, or run scholar-ontology to build one.\n```\n\nNext-step options: verify the downstream claims, re-run contest, stop here.\n\nWrite it per `references\u002Fprose-rules.md`.\n\n\n## Portability notes\n\n- `$ARGUMENTS` — the text the user passed when invoking this skill. If your host does not substitute it, read it as the user's request in the current turn, and ask when there is none.\n- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.\n",{"name":5,"metadata":24,"description":7,"allowed-tools":27,"disable-model-invocation":34},{"source":25,"argument-hint":26},"plugins\u002Fscholar\u002Fskills\u002Frevise\u002FSKILL.md","\u003Cterm-or-claim> [--study=\u003Cdir>]",[28,29,30,31,32,33],"Bash","Read","Glob","Edit","Write","AskUserQuestion",true,"main","5fbeb3b47beedea13813be7b7023f736a8d97a65",".agents\u002Fskills\u002Fscholar-revise","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":44,"prompt":54,"zipAvailable":34},[45,48,51],{"tool":46,"command":47},"npx","npx skills add tony\u002Fskills --skill scholar-revise",{"tool":49,"command":50},"bunx","bunx skills add tony\u002Fskills --skill scholar-revise",{"tool":52,"command":53},"pnpm","pnpm dlx skills add tony\u002Fskills --skill scholar-revise","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fscholar-revise\u002FSKILL.md",[56,62,66,70,74],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"agents\u002Fopenai.yaml","REFERENCE","参考文档",293,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fscholar-revise\u002Fagents\u002Fopenai.yaml",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Foutput-contract.md",4098,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fscholar-revise\u002Freferences\u002Foutput-contract.md",{"path":67,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fprose-rules.md",4644,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fscholar-revise\u002Freferences\u002Fprose-rules.md",{"path":71,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fstage-gates.md",4310,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fscholar-revise\u002Freferences\u002Fstage-gates.md",{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fterm_metrics.py","SCRIPT","脚本",48954,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fscholar-revise\u002Freferences\u002Fterm_metrics.py",[81,88,95,102,109,116],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"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":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"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":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"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",[],[]]