[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EHV2WNPXAC788TYMGEF1BX":3,"skill-same:01M7EHV2WNPXAC788TYMGEF1BX":64},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":15,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M7EHV2WNPXAC788TYMGEF1BX","fit-page-limit",null,"篇幅达标规划——论文超页限或篇幅不足时，逐节量化\"长度去哪了\"，给出优先级方案：压缩\u002F移附录哪些低价值节、补实哪些薄弱节，同时保护贡献、结果与引用；不删证据、不为凑页注水。触发：超页限、页数超了、压缩论文、该删哪里、trim、over the page limit、too long、too short、fit the limit。","deyi2026\u002Fllm-first-loop","deyi2026","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F267286635?v=4","01M7EHT3KGDPR2R5HCCRQA3HYM","01M7EHT3M140G7BHY5CBAJVRH4",1,"MIT","https:\u002F\u002Fgithub.com\u002Fdeyi2026\u002Fllm-first-loop\u002Fblob\u002Fmain\u002Fskills\u002Ffit-page-limit\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fdeyi2026\u002Fllm-first-loop\u002Fblob\u002Fmain\u002Fskills\u002Ffit-page-limit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: fit-page-limit\ndescription: 篇幅达标规划——论文超页限或篇幅不足时，逐节量化\"长度去哪了\"，给出优先级方案：压缩\u002F移附录哪些低价值节、补实哪些薄弱节，同时保护贡献、结果与引用；不删证据、不为凑页注水。触发：超页限、页数超了、压缩论文、该删哪里、trim、over the page limit、too long、too short、fit the limit。\nlicense: MIT\nmetadata:\n  vendored-from: ShaishavMaisuria\u002Fresearch-paper-lifecycle-skills@f9a0ed8\n  adapted-for: llm-first-loop（2026-10-10）\n---\n\n# Fit Page Limit\n\n> **LFL 本地化说明（2026-10-10）**：源自 ShaishavMaisuria\u002Fresearch-paper-lifecycle-skills@f9a0ed8f0f1770fb0321c5b022d55ed34c939927（MIT，LICENSE 随附）。scripts\u002Fsection_budget.py 纯 stdlib，本机已实测（真实 tex 输入，逐节词数\u002F页数估算，输出自带 \"Estimate only\" 提示）。\n\nTwo sides of the same problem: a paper that is **over** the limit and needs\ncareful cuts, or a paper that is **under** and needs useful substance rather\nthan filler. This skill maps the draft section by section, then gives the author\na prioritized plan for whichever direction they need.\n\nIt coordinates with [`polish-prose`](..\u002Fpolish-prose\u002FSKILL.md) for sentence-level\ntightening, [`refactor-structure`](..\u002Frefactor-structure\u002FSKILL.md) for larger\nreorganization, [`polish-tables-figures`](..\u002Fpolish-tables-figures\u002FSKILL.md) for\nvisual layout, and [`preflight-check`](..\u002Fpreflight-check\u002FSKILL.md) when the\npage limit comes from a venue rule. Run it after the draft is roughly complete.\n\n## When to use\n\n- The draft is over the limit and the author needs to know where the bulk is.\n- The draft is under the target length and the author wants to use space well.\n- The author asks for a length map: \"where is all my length going?\"\n\n## Inputs\n\n- The `.tex` source.\n- The real compiled page count, if available, to calibrate the estimate.\n- The target: a venue page limit or a length the author names.\n- The venue CFP or profile, if the target comes from a venue.\n\n## Process\n\n1. **Map the length.** Run the analyzer from this skill directory; do not\n   eyeball where the pages went.\n\n   ```bash\n   python3 scripts\u002Fsection_budget.py paper.tex --target-pages 10 --current-pages 11\n   ```\n\n   It reports per-section words, percentage of the paper, estimated pages, and\n   the over\u002Funder gap. `--current-pages` calibrates words per page to the\n   author's actual compile. Use `--json` for machine-readable output.\n\n2. **Confirm what counts.** Re-verify the venue's limit and exclusions against\n   the live CFP before relying on appendix moves or excluded sections. A stale\n   page limit can desk-reject the paper.\n\n3. **Pick the right branch.** Use\n   [references\u002Fresize-tactics.md](references\u002Fresize-tactics.md) to turn the\n   map into a value-aware resize plan.\n\n### If over: compress value-aware, never blind\n\nRank sections by **compressibility x low impact**, and cut there first:\n\n- **Redundancy**: the same point repeated in the intro, method, and conclusion.\n- **Over-long related work**: condense paragraph-per-paper prose into clusters\n  that state only the delta that matters.\n- **Verbose method\u002Fsetup**: tighten with `polish-prose`; cut walkthroughs a\n  figure already shows.\n- **Move, do not delete**: push proofs, extra results, or implementation detail\n  to an appendix only when the venue excludes it.\n- **Figures\u002Ftables**: resize, merge subfigures, or drop a redundant baseline\n  column with `polish-tables-figures`.\n\nProtect contributions, headline results, and every citation. Present estimated\nsavings per cut and let the author approve before editing. Never delete a\nresult, claim, or reference to hit a number.\n\n### If under: expand with substance\n\nA short, complete paper can be fine; say so. If there is real room to strengthen\nit, suggest substance: a missing ablation, deeper error analysis, limitations\nor threats to validity, clearer motivation, a worked example, or a related-work\ngap. Flag suggestions that would merely pad. Hand drafting to the writing\nskills.\n\n## Output\n\nA length map and prioritized resize plan:\n\n- **Over**: ranked cut list, estimated savings, and protected material.\n- **Under**: substantive additions ranked by value.\n\nWrite durable outputs to the user's local `paper-workspace\u002Fwriting\u002F` directory\nwhen a workspace exists. The skill recommends and explains; the author decides\nand edits.\n\n## Guardrails\n\n- Never delete results, claims, or citations to fit.\n- Never pad to fill.\n- Page numbers are estimates; tell the author to compile and check the real\n  count.\n- Re-verify venue limits and exclusions against the live CFP before advising\n  appendix moves.\n- Copilot, not pilot: propose the plan; the author approves and edits.\n\n## Memory\n\nUses the shared `.paper-memory\u002F` convention documented by\n[`paper-profile`](..\u002Fpaper-profile\u002Freferences\u002Fpaper-memory-convention.md).\n\n- **At start:** read `lessons.md` for recurring overspend patterns, such as\n  \"related work always runs long\".\n- **At end:** append `date - fit-page-limit - over\u002Funder - where the length went\n  - what was cut\u002Fadded` after deduping.\n- Create `.paper-memory\u002F` on demand in the user's paper directory. It is local\n  only and should usually be ignored by git.\n","# Fit Page Limit\n\n> **LFL 本地化说明（2026-10-10）**：源自 ShaishavMaisuria\u002Fresearch-paper-lifecycle-skills@f9a0ed8f0f1770fb0321c5b022d55ed34c939927（MIT，LICENSE 随附）。scripts\u002Fsection_budget.py 纯 stdlib，本机已实测（真实 tex 输入，逐节词数\u002F页数估算，输出自带 \"Estimate only\" 提示）。\n\nTwo sides of the same problem: a paper that is **over** the limit and needs\ncareful cuts, or a paper that is **under** and needs useful substance rather\nthan filler. This skill maps the draft section by section, then gives the author\na prioritized plan for whichever direction they need.\n\nIt coordinates with [`polish-prose`](..\u002Fpolish-prose\u002FSKILL.md) for sentence-level\ntightening, [`refactor-structure`](..\u002Frefactor-structure\u002FSKILL.md) for larger\nreorganization, [`polish-tables-figures`](..\u002Fpolish-tables-figures\u002FSKILL.md) for\nvisual layout, and [`preflight-check`](..\u002Fpreflight-check\u002FSKILL.md) when the\npage limit comes from a venue rule. Run it after the draft is roughly complete.\n\n## When to use\n\n- The draft is over the limit and the author needs to know where the bulk is.\n- The draft is under the target length and the author wants to use space well.\n- The author asks for a length map: \"where is all my length going?\"\n\n## Inputs\n\n- The `.tex` source.\n- The real compiled page count, if available, to calibrate the estimate.\n- The target: a venue page limit or a length the author names.\n- The venue CFP or profile, if the target comes from a venue.\n\n## Process\n\n1. **Map the length.** Run the analyzer from this skill directory; do not\n   eyeball where the pages went.\n\n   ```bash\n   python3 scripts\u002Fsection_budget.py paper.tex --target-pages 10 --current-pages 11\n   ```\n\n   It reports per-section words, percentage of the paper, estimated pages, and\n   the over\u002Funder gap. `--current-pages` calibrates words per page to the\n   author's actual compile. Use `--json` for machine-readable output.\n\n2. **Confirm what counts.** Re-verify the venue's limit and exclusions against\n   the live CFP before relying on appendix moves or excluded sections. A stale\n   page limit can desk-reject the paper.\n\n3. **Pick the right branch.** Use\n   [references\u002Fresize-tactics.md](references\u002Fresize-tactics.md) to turn the\n   map into a value-aware resize plan.\n\n### If over: compress value-aware, never blind\n\nRank sections by **compressibility x low impact**, and cut there first:\n\n- **Redundancy**: the same point repeated in the intro, method, and conclusion.\n- **Over-long related work**: condense paragraph-per-paper prose into clusters\n  that state only the delta that matters.\n- **Verbose method\u002Fsetup**: tighten with `polish-prose`; cut walkthroughs a\n  figure already shows.\n- **Move, do not delete**: push proofs, extra results, or implementation detail\n  to an appendix only when the venue excludes it.\n- **Figures\u002Ftables**: resize, merge subfigures, or drop a redundant baseline\n  column with `polish-tables-figures`.\n\nProtect contributions, headline results, and every citation. Present estimated\nsavings per cut and let the author approve before editing. Never delete a\nresult, claim, or reference to hit a number.\n\n### If under: expand with substance\n\nA short, complete paper can be fine; say so. If there is real room to strengthen\nit, suggest substance: a missing ablation, deeper error analysis, limitations\nor threats to validity, clearer motivation, a worked example, or a related-work\ngap. Flag suggestions that would merely pad. Hand drafting to the writing\nskills.\n\n## Output\n\nA length map and prioritized resize plan:\n\n- **Over**: ranked cut list, estimated savings, and protected material.\n- **Under**: substantive additions ranked by value.\n\nWrite durable outputs to the user's local `paper-workspace\u002Fwriting\u002F` directory\nwhen a workspace exists. The skill recommends and explains; the author decides\nand edits.\n\n## Guardrails\n\n- Never delete results, claims, or citations to fit.\n- Never pad to fill.\n- Page numbers are estimates; tell the author to compile and check the real\n  count.\n- Re-verify venue limits and exclusions against the live CFP before advising\n  appendix moves.\n- Copilot, not pilot: propose the plan; the author approves and edits.\n\n## Memory\n\nUses the shared `.paper-memory\u002F` convention documented by\n[`paper-profile`](..\u002Fpaper-profile\u002Freferences\u002Fpaper-memory-convention.md).\n\n- **At start:** read `lessons.md` for recurring overspend patterns, such as\n  \"related work always runs long\".\n- **At end:** append `date - fit-page-limit - over\u002Funder - where the length went\n  - what was cut\u002Fadded` after deduping.\n- Create `.paper-memory\u002F` on demand in the user's paper directory. It is local\n  only and should usually be ignored by git.\n",{"name":5,"license":14,"metadata":24,"description":7},{"adapted-for":25,"vendored-from":26},"llm-first-loop（2026-10-10）","ShaishavMaisuria\u002Fresearch-paper-lifecycle-skills@f9a0ed8","main","57f220f344f02e6abf6eb55434077d104c209804","skills\u002Ffit-page-limit",0,"https:\u002F\u002Fgithub.com\u002Fdeyi2026\u002Fllm-first-loop","https:\u002F\u002Fgithub.com\u002Fdeyi2026","2026-11-15 10:23:32",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add deyi2026\u002Fllm-first-loop --skill fit-page-limit",{"tool":40,"command":41},"bunx","bunx skills add deyi2026\u002Fllm-first-loop --skill fit-page-limit",{"tool":43,"command":44},"pnpm","pnpm dlx skills add deyi2026\u002Fllm-first-loop --skill fit-page-limit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdeyi2026\u002Fllm-first-loop\u002Fblob\u002Fmain\u002Fskills\u002Ffit-page-limit\u002FSKILL.md",true,[48,52,58],{"path":49,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":15},"LICENSE","许可证",10278,{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fresize-tactics.md","REFERENCE","参考文档",2633,"https:\u002F\u002Fgithub.com\u002Fdeyi2026\u002Fllm-first-loop\u002Fblob\u002Fmain\u002Fskills\u002Ffit-page-limit\u002Freferences\u002Fresize-tactics.md",{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"scripts\u002Fsection_budget.py","SCRIPT","脚本",5770,"https:\u002F\u002Fgithub.com\u002Fdeyi2026\u002Fllm-first-loop\u002Fblob\u002Fmain\u002Fskills\u002Ffit-page-limit\u002Fscripts\u002Fsection_budget.py",[65,73,80,87,94,101],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7EJ01AM5PZXYNM9GBF6CW12","security-audit","Audit project for security issues.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdeyi2026\u002Fllm-first-loop\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fvendor_gemini_demo\u002Fskills\u002Fsecurity-audit\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7EJ00CD2JXGVB0JETXGEX43","metrics","Collect project metrics.","https:\u002F\u002Fgithub.com\u002Fdeyi2026\u002Fllm-first-loop\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fvendor_codex_demo\u002Fskills\u002Fmetrics\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7EHZZD7DVVTSECGF5HHHQZ5","lint","Lint the repo using project config.","https:\u002F\u002Fgithub.com\u002Fdeyi2026\u002Fllm-first-loop\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fvendor_claude_demo\u002Fskills\u002Flint\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7EHZYGGYKDZDEHVF4YSD22X","report","值班报告生成","https:\u002F\u002Fgithub.com\u002Fdeyi2026\u002Fllm-first-loop\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fstd_plugin_demo\u002Fskills\u002Freport\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7EHZVX0V6ER3X3017K47RK4","deploy","标准部署流程（多行 YAML frontmatter 演示）","https:\u002F\u002Fgithub.com\u002Fdeyi2026\u002Fllm-first-loop\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fstd_plugin_demo\u002Fskills\u002Fdeploy\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7EHZRENGPKXXFBA3YJ1QF1S","web-self-restart-triage","https:\u002F\u002Fgithub.com\u002Fdeyi2026\u002Fllm-first-loop\u002Fblob\u002Fmain\u002Fskills\u002Fweb-self-restart-triage\u002FSKILL.md",[],[]]