[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DH22SVM2DTTKC8K3Z2RG12":3,"skill-same:01M6DH22SVM2DTTKC8K3Z2RG12":92},{"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":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":38,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M6DH22SVM2DTTKC8K3Z2RG12","peer-review",null,"Peer review of research funding applications and academic submissions. Scheme-agnostic; fetches round criteria dynamically. Covers Detailed Assessor, General Assessor \u002F College of Experts, and collegial draft review.","nicsuzor\u002FacademicOps","nicsuzor","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4496978?v=4","01M6DGWCFNDYP03M4DQAHA6DN1","Nicolas Suzor","01M6DGWCPXG37BMXRZZKXR0A1Z",5,"MIT","https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fcowork\u002Ftools\u002Fskills\u002Fpeer-review\u002FSKILL.md",[],[19,20,21,22,23,24,25,26],"review","peer review","peer","research","applications","general","draft","Academic","2026-11-10 10:12:30",false,"---\nname: peer-review\ndescription: Peer review of research funding applications and academic submissions. Scheme-agnostic; fetches round criteria dynamically. Covers Detailed Assessor, General Assessor \u002F College of Experts, and collegial draft review.\n---\n\n# Peer Review\n\nPrepare evidence-based, signable peer reviews matching current round criteria. The agent drafts and verifies; the academic owns scores, net call, and submitted text.\n\n## Core Rules\n\n- **Framing precedes defects**: Establish what the document aims to achieve before criterion-level critique.\n- **Evidence-based**: Cite application locations (page, section, line, or quote) for every claim.\n- **Documented absence search**: Treat missing elements as critique only after documented synonym search.\n- **Fetch round criteria**: Retrieve current scheme guidelines, bands, and weights fresh each round.\n- **Human owns judgment**: Leave scores blank in drafts to comply with funding-body GenAI policies.\n- **No speculative outcomes**: Evaluate research feasibility without pre-committing what unrun studies will show.\n- **Route integrity breaches**: Report suspected research-integrity issues through official scheme channels, never in assessment text (see `references\u002Fplatform-instructions.md`).\n- **Single living draft**: Maintain one draft per review versioned in git history; avoid duplicate version files.\n- **Verbatim accuracy**: Use real, verified quotes or generic placeholders; never invent illustrative quotes.\n\n## Five-Stage Workflow\n\nSerial execution by a single agent is the default. Lead sessions with multi-review rounds may parallelise Stage 2 (isolated per-application verifiers) and Stage 3 (whole-set de-templating).\n\n### Stage 0: Intake & Setup\n\n1. Capture metadata: scheme, round, application ID, candidate, title, role (`references\u002Freviewer-roles.md`), deadline.\n2. Check conflicts of interest (CoI) once across participants and references; flag to academic for confirmation.\n3. Fetch scheme criteria, score bands, and character limits from the current handbook.\n4. Extract text to `${ACA_DATA}\u002Freviews\u002F{scheme}\u002F{appid}\u002F` via `pdftotext -layout`. Inspect tables and budgets directly from the PDF.\n\n### Stage 1: PREP (Probe-Driven Draft)\n\n1. Read against analytical probes (`references\u002Fprobes.md`).\n2. Produce reading notes (`references\u002Freading-notes-format.md`) with two separated layers: line-mapped facts and a private raw judgment block.\n3. Draft criterion comments aligned with scheme bands (`references\u002Freview-guidance.md`), leaving scores blank.\n4. Self-check: verify arithmetic, confirm paraphrase is marked, and exclude integrity allegations.\n\n### Stage 2: VERIFY (Adversarial Verification)\n\nExecute an independent cold check per `references\u002Fverification.md`:\n\n- Run quote-existence greps, recompute arithmetic with tools, and verify absence claims.\n- Classify findings: CONFIRMED, UNSUPPORTED, or WRONG; assign severity (BLOCKER, FIX, NIT).\n- Triage and apply fixes using narrow edits; verify diffs directly.\n\n### Stage 3: Voice & De-template\n\n1. Match the academic's voice and convert prep notes into signable prose per `references\u002Fvoice-and-detemplating.md`.\n2. Run whole-set de-templating across all reviews in the round to eliminate repeated phrases and AI artifacts.\n3. Ensure quote accuracy and evidence anchors remain unaltered.\n\n### Stage 4: Final Check & Submit\n\n1. Execute pre-ready gate: verbatim-quote grep, spelling check, and budget verification.\n2. Boundary gate: verification applies to committed artifacts; post-verification edits require re-verification.\n3. Academic reviews, assigns scores, and submits. Record confirmation in the task file.\n\n## Scribe Mode (Collegial Review)\n\nFor pre-submission drafts by colleagues:\n\n1. Store materials under `${ACA_DATA}\u002Freviews\u002F{author}\u002F`.\n2. Map author questions to line numbers in reading notes (`references\u002Freading-notes-format.md`).\n3. Budget feedback length to available time (lead with working elements, then one structural priority).\n4. Quote the colleague's text directly rather than paraphrasing into labels.\n\n## References\n\n- `references\u002Fprobes.md` -- Analytical probes for proposal evaluation\n- `references\u002Fverification.md` -- Adversarial verification techniques and severity ladder\n- `references\u002Fvoice-and-detemplating.md` -- Voice registers and whole-set phrase deduplication\n- `references\u002Fexternal-feedback.md` -- Distrust-default integration of external and model critiques\n- `references\u002Freviewer-roles.md` -- Detailed Assessor, General Assessor, and collegial reviewer scopes\n- `references\u002Freview-guidance.md` -- Feedback taxonomy, scoring bands, and anti-bias drafting\n- `references\u002Freview-template.md` -- Assessment markdown template\n- `references\u002Freading-notes-format.md` -- Factual map and raw judgment structure\n- `references\u002Fplatform-instructions.md` -- RMS, ERC, SNSF, and NHMRC submission guidelines\n","# Peer Review\n\nPrepare evidence-based, signable peer reviews matching current round criteria. The agent drafts and verifies; the academic owns scores, net call, and submitted text.\n\n## Core Rules\n\n- **Framing precedes defects**: Establish what the document aims to achieve before criterion-level critique.\n- **Evidence-based**: Cite application locations (page, section, line, or quote) for every claim.\n- **Documented absence search**: Treat missing elements as critique only after documented synonym search.\n- **Fetch round criteria**: Retrieve current scheme guidelines, bands, and weights fresh each round.\n- **Human owns judgment**: Leave scores blank in drafts to comply with funding-body GenAI policies.\n- **No speculative outcomes**: Evaluate research feasibility without pre-committing what unrun studies will show.\n- **Route integrity breaches**: Report suspected research-integrity issues through official scheme channels, never in assessment text (see `references\u002Fplatform-instructions.md`).\n- **Single living draft**: Maintain one draft per review versioned in git history; avoid duplicate version files.\n- **Verbatim accuracy**: Use real, verified quotes or generic placeholders; never invent illustrative quotes.\n\n## Five-Stage Workflow\n\nSerial execution by a single agent is the default. Lead sessions with multi-review rounds may parallelise Stage 2 (isolated per-application verifiers) and Stage 3 (whole-set de-templating).\n\n### Stage 0: Intake & Setup\n\n1. Capture metadata: scheme, round, application ID, candidate, title, role (`references\u002Freviewer-roles.md`), deadline.\n2. Check conflicts of interest (CoI) once across participants and references; flag to academic for confirmation.\n3. Fetch scheme criteria, score bands, and character limits from the current handbook.\n4. Extract text to `${ACA_DATA}\u002Freviews\u002F{scheme}\u002F{appid}\u002F` via `pdftotext -layout`. Inspect tables and budgets directly from the PDF.\n\n### Stage 1: PREP (Probe-Driven Draft)\n\n1. Read against analytical probes (`references\u002Fprobes.md`).\n2. Produce reading notes (`references\u002Freading-notes-format.md`) with two separated layers: line-mapped facts and a private raw judgment block.\n3. Draft criterion comments aligned with scheme bands (`references\u002Freview-guidance.md`), leaving scores blank.\n4. Self-check: verify arithmetic, confirm paraphrase is marked, and exclude integrity allegations.\n\n### Stage 2: VERIFY (Adversarial Verification)\n\nExecute an independent cold check per `references\u002Fverification.md`:\n\n- Run quote-existence greps, recompute arithmetic with tools, and verify absence claims.\n- Classify findings: CONFIRMED, UNSUPPORTED, or WRONG; assign severity (BLOCKER, FIX, NIT).\n- Triage and apply fixes using narrow edits; verify diffs directly.\n\n### Stage 3: Voice & De-template\n\n1. Match the academic's voice and convert prep notes into signable prose per `references\u002Fvoice-and-detemplating.md`.\n2. Run whole-set de-templating across all reviews in the round to eliminate repeated phrases and AI artifacts.\n3. Ensure quote accuracy and evidence anchors remain unaltered.\n\n### Stage 4: Final Check & Submit\n\n1. Execute pre-ready gate: verbatim-quote grep, spelling check, and budget verification.\n2. Boundary gate: verification applies to committed artifacts; post-verification edits require re-verification.\n3. Academic reviews, assigns scores, and submits. Record confirmation in the task file.\n\n## Scribe Mode (Collegial Review)\n\nFor pre-submission drafts by colleagues:\n\n1. Store materials under `${ACA_DATA}\u002Freviews\u002F{author}\u002F`.\n2. Map author questions to line numbers in reading notes (`references\u002Freading-notes-format.md`).\n3. Budget feedback length to available time (lead with working elements, then one structural priority).\n4. Quote the colleague's text directly rather than paraphrasing into labels.\n\n## References\n\n- `references\u002Fprobes.md` -- Analytical probes for proposal evaluation\n- `references\u002Fverification.md` -- Adversarial verification techniques and severity ladder\n- `references\u002Fvoice-and-detemplating.md` -- Voice registers and whole-set phrase deduplication\n- `references\u002Fexternal-feedback.md` -- Distrust-default integration of external and model critiques\n- `references\u002Freviewer-roles.md` -- Detailed Assessor, General Assessor, and collegial reviewer scopes\n- `references\u002Freview-guidance.md` -- Feedback taxonomy, scoring bands, and anti-bias drafting\n- `references\u002Freview-template.md` -- Assessment markdown template\n- `references\u002Freading-notes-format.md` -- Factual map and raw judgment structure\n- `references\u002Fplatform-instructions.md` -- RMS, ERC, SNSF, and NHMRC submission guidelines\n",{"name":5,"description":7},"main","22a4e466ac352d09f636273685845a312ee07a15","cowork\u002Ftools\u002Fskills\u002Fpeer-review",3,"https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps","https:\u002F\u002Fgithub.com\u002Fnicsuzor","https:\u002F\u002Fnic.suzor.net\u002F","2026-11-11 20:31:05",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add nicsuzor\u002FacademicOps --skill peer-review",{"tool":46,"command":47},"bunx","bunx skills add nicsuzor\u002FacademicOps --skill peer-review",{"tool":49,"command":50},"pnpm","pnpm dlx skills add nicsuzor\u002FacademicOps --skill peer-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fcowork\u002Ftools\u002Fskills\u002Fpeer-review\u002FSKILL.md",true,[54,60,64,68,72,76,80,84,88],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fexternal-feedback.md","REFERENCE","参考文档",1788,"https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fcowork\u002Ftools\u002Fskills\u002Fpeer-review\u002Freferences\u002Fexternal-feedback.md",{"path":61,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fplatform-instructions.md",1233,"https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fcowork\u002Ftools\u002Fskills\u002Fpeer-review\u002Freferences\u002Fplatform-instructions.md",{"path":65,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fprobes.md",2303,"https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fcowork\u002Ftools\u002Fskills\u002Fpeer-review\u002Freferences\u002Fprobes.md",{"path":69,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Freading-notes-format.md",2188,"https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fcowork\u002Ftools\u002Fskills\u002Fpeer-review\u002Freferences\u002Freading-notes-format.md",{"path":73,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Freview-guidance.md",2515,"https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fcowork\u002Ftools\u002Fskills\u002Fpeer-review\u002Freferences\u002Freview-guidance.md",{"path":77,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Freview-template.md",977,"https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fcowork\u002Ftools\u002Fskills\u002Fpeer-review\u002Freferences\u002Freview-template.md",{"path":81,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Freviewer-roles.md",1714,"https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fcowork\u002Ftools\u002Fskills\u002Fpeer-review\u002Freferences\u002Freviewer-roles.md",{"path":85,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fverification.md",2489,"https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fcowork\u002Ftools\u002Fskills\u002Fpeer-review\u002Freferences\u002Fverification.md",{"path":89,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fvoice-and-detemplating.md",2125,"https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fcowork\u002Ftools\u002Fskills\u002Fpeer-review\u002Freferences\u002Fvoice-and-detemplating.md",[93,120,125,130,135,159],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":27},"01M6M6JR6VXPDA3MDPVS36DSSP","refresh-questions","Sweep and refresh open questions in the Telegram Mini App by closing questions that are answered elsewhere, superseded, or asking for completed actions, and ensuring active open questions carry recommendations and context. Use when asked to refresh questions, sweep stale questions, or keep the Mini App decision queue current. Exclude for asking new questions or routine chat replies.","https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fopenclaw\u002Fida-telegram\u002Fskills\u002Frefresh-questions\u002FSKILL.md",[],[100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119],"refresh","refresh questions","questions","actions","telegram mini app","open","decision","context","use","queue","telegram","stale","chat","active","recommendations","app","keep","replies","closing","for",{"skillNo":121,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":27},"01M6M6JGW7Q0SC5B28TQ7PKE8E","https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fida-telegram-openclaw\u002Fskills\u002Frefresh-questions\u002FSKILL.md",[],[100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119],{"skillNo":126,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":27},"01M6M6J7D0ZTQ4VSS5ADRSA12E","https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fida-telegram-claude\u002Fskills\u002Frefresh-questions\u002FSKILL.md",[],[100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119],{"skillNo":131,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":27},"01M6M6EP6BK1DDN2212S7Y95G0","https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fcowork\u002Fida-telegram\u002Fskills\u002Frefresh-questions\u002FSKILL.md",[],[100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":27},"01M6G9Q8538NENA2TE2V4HPRSF","dispatch-queue","Show the user the tasks ready to dispatch, ranked with a recommendation on each, and start workers on the ones the user approves -- redirects to universal workflow template wf-dispatch-queue. Use for \"what's ready\", \"what should we dispatch\", or \"dispatch the queue\". Exclude for starting workers on named tasks without the user's choice (use dispatch) or graph truth maintenance (use reconcile).","https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fopenclaw\u002Fida\u002Fskills\u002Fdispatch-queue\u002FSKILL.md",[],[142,109,143,144,145,146,147,148,149,150,108,151,152,153,154,155,156,157,158],"dispatch","dispatch queue","workflow","tasks","graph","start","template","choice","user","reconcile","ready","maintenance","workers","show","wf","recommendation","with",{"skillNo":160,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":27},"01M6G9P9M3PQXPX3647RA5E4D0","https:\u002F\u002Fgithub.com\u002Fnicsuzor\u002FacademicOps\u002Fblob\u002Fmain\u002Fida-openclaw\u002Fskills\u002Fdispatch-queue\u002FSKILL.md",[],[142,109,143,144,145,146,147,148,149,150,108,151,152,153,154,155,156,157,158]]