Researchwrite Proposal Pipeline

What it does

When your agent uses it

• Drafting a Chinese research proposal or opening report from a topic
• Revising an existing proposal against an evidence table
• Auditing a proposal for unsupported claims and scope creep
• Exporting a finished proposal project to Markdown or Word

Example prompts

• “Compose a research proposal on solid-state electrolytes starting from my topic and notes.”
• “Revise chapter 2 of my opening report and flag any claim the evidence table does not support.”
• “Audit my proposal draft and tell me whether to keep iterating or stop.”
• “Export the finished proposal project as a .docx file.”

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

1. 1证据先于文字 — 起草前必须建立或读取 research_canon 和 evidence_table
2. 2论证先于章节 — 写正文前必须完成 argument_map
3. 3契约先于段落 — 每节需要 purpose / allowed claims / forbidden claims / inputs / validation
4. 4范围先于完备 — 如果是分阶段写作，先锁定阶段边界
5. 5动态专家，不设固定池 — 用 professor 按失败模式召唤对应专家
6. 6内容先于语言 — 诊断科学逻辑后再做 anti-slop / 语言打磨
7. 7不自动升级事实 — 永远不把 "may indicate" 改成 "proves"，除非有证据支撑
8. 8删除胜于解释 — 当某主张不可行，直接删除。正文干净，解释留给答辩
9. 9该停就停 — 平台期、专家冲突、证据缺失是停止理由，不是润色理由

What it can do on your machine

Read from SKILL.md and the folder at commit 2a20e4a. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/, which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Researchwrite Proposal Pipeline loads about 1.1k tokens when it runs, and up to ~20k if it reads all its reference files. Until then it costs about 61 tokens; SKILL.md has 213 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~61

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~20k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from Yuan1z0825/nature-skills at commit 2a20e4a, republished under its MIT licence (© Yuan1z0825). 213 words, ~1,122 tokens.

name

researchwrite

description

Compose, revise, or audit research proposals, opening reports, and research plans from supporting evidence. Use for 研究计划、开题报告、科研项目申请书. Invoked as researchwrite for compatibility; use nature-writing for general manuscript sections.

license

MIT

00_scope.md              写作任务边界
01_research_canon.md     硬事实和约束
02_evidence_table.md      claim → evidence 映射表
03_argument_map.md        论证架构
04_section_contracts.md   每节的 purpose / inputs / allowed & forbidden claims
05_style_guide.md         风格、术语、禁用表达
state.json                项目状态（mode、round、scores、technical_debts）
sources/                  用户材料、文献、数据
drafts/                   草稿和分节文件
revision_briefs/          修订简报
qa_logs/                  诊断、专家审查、anti-slop、打分记录
exports/                  最终输出（.md + .docx）

Gate 2: professor Convener（内容层）
  ├── 论文 → 方法论专家 + 领域专家
  ├── proposal → 可行性专家 + 创新性专家
  └── 文献综述 → 覆盖面专家 + 批判深度专家
  │
  ▼
Gate 1: avoid-ai-writing 模式 detect-only
  └── 只对英文有效，中文跳过或降级为手工扫读
  │
  ▼
Gate 3: auto-validation（格式/完整性层）
  └── 每个 claim 有 citation？方法可复现？编号连续？
  │
  ▼
Gate 4: 评分阈值（分维度打分）
  ├── 总分≥阈值 → 通过 ✅
  └── 总分<阈值 → 按低分维度定向回退（不超过 3 轮）

用户: "用 researchwrite 审查这段 discussion，paper 挡位"
  → 自动走 Gate 2 → Gate 1 → Gate 3 → Gate 4
  → 返回审查报告 + 定向修改建议

用户: "快速扫一下这个邮件"
  → 走 quick 挡位，只标记 P0 问题

© Yuan1z0825, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 35 other files (scripts, references) in skills/nature-proposal-writer of Yuan1z0825/nature-skills.

• SKILL.md
• README.md
• README_EN.md
• agents/openai.yaml
• manifest.yaml
• references/chinese-review-writing-style.md
• references/compose-mode.md
• references/evaluation-rubric.md
• references/export-archive.md
• references/foundation-files.md
• references/gpt-handoff-revision-brief.md
• references/hybrid-mode.md
• references/partial-proposal-scope.md
• references/professor-dispatch.md
• references/project-structure.md
• references/ref-renumbering-cascade.md
• references/research-anti-slop.md
• references/review-critique-methodology.md
• references/review-paper-framework.md
• … and 17 more

Open the folder on GitHubat commit 2a20e4a

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in Yuan1z0825/nature-skills, which our catalogue first saw on October 7, 2026.

• Tai609/NebulaMatruntime/skills-bundle/researchwrite