fit-page-limit
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/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…
Skill by deyi2026
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/deyi2026-fit-page-limit
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/fit-page-limit
What's inside
- Skill name
fit-page-limit- Description
- 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/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。
- License
- MIT
- Metadata
- adapted-for: llm-first-loop(2026-10-10) · vendored-from: ShaishavMaisuria/research-paper-lifecycle-skills@f9a0ed8
- Instructions
- 109 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (4)
- LICENSE
- SKILL.md
- resize-tactics.md · references/
- section_budget.py · scripts/
SKILL.md (first lines)
# Fit Page Limit > **LFL 本地化说明(2026-10-10)**:源自 ShaishavMaisuria/research-paper-lifecycle-skills@f9a0ed8f0f1770fb0321c5b022d55ed34c939927(MIT,LICENSE 随附)。scripts/section_budget.py 纯 stdlib,本机已实测(真实 tex 输入,逐节词数/页数估算,输出自带 "Estimate only" 提示)。 Two sides of the same problem: a paper that is **over** the limit and needs careful cuts, or a paper that is **under** and needs useful substance rather than filler. This skill maps the draft section by section, then gives the author a prioritized plan for whichever direction they need. It coordinates with [`polish-prose`](../polish-prose/SKILL.md) for sentence-level tightening, [`refactor-structure`](../refactor-structure/SKILL.md) for larger reorganization, [`polish-tables-figures`](../polish-tables-figures/SKILL.md) for visual layout, and [`preflight-check`](../preflight-check/SKILL.md) when the page limit comes from a venue rule. Run it after the draft is roughly complete. ## When to use - The draft is over the limit and the author needs to know where the bulk is. - The draft is under the target length and the author wants to use space well. - The author asks for a length map: "where is all my length going?" ## Inputs - The `.tex` source. - The real compiled page count, if available, to calibrate the estimate. - The target: a venue page limit or a length the author names. - The venue CFP or profile, if the target comes from a venue. ## Process 1. **Map the length.** Run the analyzer from this skill directory; do not eyeball where the pages went. ```bash python3 scripts/section_budget.py paper.tex --target-pages 10 --current-pages 11 ``` It reports per-section words, percentage of the paper, estimated pages, and the over/under gap. `--current-pages` calibrates words per page to the author's actual compile. Use `--json` for machine-readable output. 2. **Confirm what counts.** Re-verify the venue's limit and exclusions against the live CFP before relying on appendix moves or excluded sections. A stale page limit can desk-reject the paper. 3. **Pick the right branch.** Use [references/resize-tactics.md](references/resize-tactics.md) to turn the map into a value-aware resize plan. ### If over: compress value-aware, never blind Rank sections by **compressibility x low impact**, and cut there first: - **Redundancy**: the same point repeated in the intro, method, and conclusion. - **Over-long related work**: condense paragraph-per-paper prose into clusters that state only the delta that matters. - **Verbose method/setup**: tighten with `polish-prose`; cut walkthroughs a figure already shows. - **Move, do not delete**: push proofs, extra results, or implementation detail to an appendix only when the venue excludes it. - **Figures/tables**: resize, merge subfigures, or drop a redundant baseline column with `polish-tables-figures`. Protect contributions, headline results, and every citation. Present estimated savings per cut and let the author approve before editing. Never delete a result, claim, or reference to hit a number. ### If under: expand with substance A short, complete paper can be fine; say so. If there is real room to strengthen it, suggest substance: a missing ablation, deeper error analysis, limitations or threats to validity, clearer motivation, a worked example, or a related-work gap. Flag suggestions that would merely pad. Hand drafting to the writing skills. ## Output A length map and prioritized resize plan: - **Over**: ranked cut list, estimated savings, and protected material. - **Under**: substantive additions ranked by value. Write durable outputs to the user's local `paper-workspace/writing/` directory when a workspace exists. The skill recommends and explains; the author decides and edits. ## Guardrails - Never delete results, claims, or citations to fit. - Never pad to fill. - Page numbers are estimates; tell the author to compile and check the real count. - Re-verify venue limits and exclusions against the live CFP before advising appendix moves. - Copilot, not pilot: propose the plan; the author approves and edits. ## Memory Uses the shared `.paper-memory/` convention documented by [`paper-profile`](../paper-profile/references/paper-memory-convention.md). - **At start:** read `lessons.md` for recurring overspend patterns, such as "related work always runs long". - **At end:** append `date - fit-page-limit - over/under - where the length went - what was cut/added` after deduping. - Create `.paper-memory/` on demand in the user's paper directory. It is local only and should usually be ignored by git.
From deyi2026/llm-first-loop, MIT.
More from deyi2026/llm-first-loop
- 0.589score
integrity-auditor
deyi2026
论文诚信审计——对一篇论文(外部 PDF/DOI/arXiv 或本地写作产出)做图像误用、数值异常、逻辑缺口三轨证据审计,产出 Level 1–4 分级、可复核的 audit_report.md。用于投稿前自查、审稿前评估、对 AI 生成内容做"数字有没有来源、图表有没有被动过"级核验。触发:integrity…
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
anonymize-paper
deyi2026
双盲匿名深扫 + camera-ready 干净还原——投稿前扫尽泄漏面(作者块/grant 致谢/PDF 元数据/第一人称自引/仓库与主页链接/LaTeX 注释/.bib 注释/主目录路径/补充材料),自带 stdlib…
SkillAFreshness: A★ 1Claude Code +9 - 0.588score
gzh-design
deyi2026
微信公众号文章排版引擎,将 Markdown 转换为可直接粘贴到公众号编辑器的 HTML。主题风格从 references/theme-index.md 注册的自定义主题库中选取,自动章节编号、关键词下划线标记、引言卡片、目录导航、代码块、图片/GIF、作者签名。支持 Markdown / Word(.docx)…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
assess-paper
deyi2026
论文整体健康度评估——"我这论文现在什么水平/能不能投/先改哪里/优缺点"时使用。编排本仓库已装的 preflight-check、verify-citations、anonymize-paper、fit-page-limit 做桌拒合规/引用/匿名/篇幅检查,汇总成一份先优点、再风险、带优先级修改清单的…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
method-ab-experiment
deyi2026
设计或审查模型、Agent、缓存、上下文、工具策略、runtime 优化的 A/B/qualification 实验时使用。用于锁唯一自变量、隔离 cache/session/evidence/model residency 等跨 run…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
method-candidate-ab-validity-trigger-confound
deyi2026
A/B qualification candidate distilled verbatim by Qwen3.8-27B from the working-set receipts teacher episode; experimental candidate only, not promoted.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
method-candidate-current-callsite-refresh
deyi2026
Repo/API candidate distilled verbatim by Qwen3.8-27B from the parallel-line stale-callsite teacher episode; experimental candidate only, not promoted.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
method-candidate-hydrate-trace
deyi2026
Qwen3.8-27B 从离线网页绕路 episode 经 teacher exemplar 蒸馏出的实验 candidate;仅用于独立 transfer qualification,不代表已 promotion。适用于当前页面是 loading shell 且显式引用可能负责加载目标内容的脚本时,测试是否应先沿…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
method-candidate-relative-clock-never-state
deyi2026
Root Cause candidate distilled verbatim by Qwen3.8-27B from the fresh-process relative-clock sentinel teacher episode; experimental candidate only, not…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
code-nav
deyi2026
使用仓库已有的 Pyright language server 做 Python 跨文件语义导航。用于改函数前确认调用者/被调用者、收敛 grep 结果到真实语义引用、检查符号爆炸半径,或在陌生模块里追踪引用链。必须通过 readiness gate 才接受语义结果;把 LSP semantic scope 与…
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
merge-review-gate
deyi2026
合并 main 审查闸(RULE-AI-34)——分支 Goal/任务收口前的专门合并审查子代理任务书:核完成证据、核分支卫生、核 main 基线、批准并入 main、落盘回执
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
humanizer-zh-next
deyi2026
编辑或审阅已有中文文本中的空话、重复和模板化表达,保留原意、事实、确定程度和作者声音。 主文件包含通用表达模式、中文句式、体裁判断、作者样本使用和文件保护,适用于去 AI 腔与自然化润色。 商务营销、论文与审稿回复、基金申请分别按需加载专用 reference。用于写作质量编辑,不判定作者身份。
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 10, 2026 (20 days ago)
- Last release
- Oct 22, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/deyi2026/llm-first-loop
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from deyi2026
- 0.589score
integrity-auditor
deyi2026
论文诚信审计——对一篇论文(外部 PDF/DOI/arXiv 或本地写作产出)做图像误用、数值异常、逻辑缺口三轨证据审计,产出 Level 1–4 分级、可复核的 audit_report.md。用于投稿前自查、审稿前评估、对 AI 生成内容做"数字有没有来源、图表有没有被动过"级核验。触发:integrity…
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
anonymize-paper
deyi2026
双盲匿名深扫 + camera-ready 干净还原——投稿前扫尽泄漏面(作者块/grant 致谢/PDF 元数据/第一人称自引/仓库与主页链接/LaTeX 注释/.bib 注释/主目录路径/补充材料),自带 stdlib…
SkillAFreshness: A★ 1Claude Code +9 - 0.588score
gzh-design
deyi2026
微信公众号文章排版引擎,将 Markdown 转换为可直接粘贴到公众号编辑器的 HTML。主题风格从 references/theme-index.md 注册的自定义主题库中选取,自动章节编号、关键词下划线标记、引言卡片、目录导航、代码块、图片/GIF、作者签名。支持 Markdown / Word(.docx)…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
assess-paper
deyi2026
论文整体健康度评估——"我这论文现在什么水平/能不能投/先改哪里/优缺点"时使用。编排本仓库已装的 preflight-check、verify-citations、anonymize-paper、fit-page-limit 做桌拒合规/引用/匿名/篇幅检查,汇总成一份先优点、再风险、带优先级修改清单的…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
method-ab-experiment
deyi2026
设计或审查模型、Agent、缓存、上下文、工具策略、runtime 优化的 A/B/qualification 实验时使用。用于锁唯一自变量、隔离 cache/session/evidence/model residency 等跨 run…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
method-candidate-ab-validity-trigger-confound
deyi2026
A/B qualification candidate distilled verbatim by Qwen3.8-27B from the working-set receipts teacher episode; experimental candidate only, not promoted.
SkillAFreshness: A★ 1Claude Code +9
Cite this page
fit-page-limit skill. Agent Mart. https://agentmart.dev/skills/deyi2026-fit-page-limit (last updated 2026-10-24)