Not in the top 1,000 by GitHub stars
SyntaxSmith/nature-writing-skill
Claude Code / Codex skill — Nature-family paper writing (NMI / NC / NCS / Nature) for Chinese AI/ML researchers, distilled from 44 OA papers
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
c1a8716047b6 → c1a8716047b6
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → c1a8716047b6
No earlier version was observed for comparison.
188GitHub stars
7stars in 7 days
1skill in this repository
0commits in 30 days
Heat
5.6- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
nature-writing
When your agent uses it
面向中国 AI / ML 研究者，主投 Nature Machine Intelligence、次投 Nature Communications / Nature Computational Science、必要时冲刺 Nature 的论文写作技能（craft + taste + story-craft）。v5 在 v4 拆分版上吸收了 8 篇 2024–2026 NMI/NC/Nature 纯 AI 方法论文（DeepSeek-R1、Densing law、AligNet、ADeLe、Webb-MAP、DiscoRL、Farquhar semantic-entropy、Whitelam Simmering），新增 measurement / new-ruler hook、correctness-gap limitation、pure-AI 数字密度 carve-out、SI black hole 反模式、AI evaluation/measurement 子门类剧本等。本 SKILL.md 为瘦索引：骨架公式、写作顺序、按任务加载的 routing table、提交前 checklist、屏幕边 quick card、附录。详细章节按需 Read `references/01-story.md` … `references/15-taste-development.md`。视觉/figure 设计见姊妹 skill `FIGURE-SKILL.md`。所有 verbatim 引文可回查 `extracts/01-singlecell.md` … `extracts/07-ai-methods.md` 7 个文件 / 共 44 篇论文。
What it loads into context
Frontmatter
287 tokensAlways available to the agent
SKILL.md
6,070 tokensWhen the skill is activated
Reference documents
134,455 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Craft, Taste, and Story-Craft for NMI / NC / NCS / Nature
- 0. 先记住这句话：论文不是实验清单，是阅读体验
- 1. Routing — 按任务加载
- 2. 提交前 checklist
- 3. Quick field manual（屏幕边贴条）
Files
.gitignoreasset51 bytesFIGURE-SKILL.mddoc13,846 bytesREADME.mddoc8,043 bytesSKILL.mdcore21,448 bytes_framework.mddoc5,097 bytesarchive/README.mddoc225 bytesarchive/SKILL.v3.mddoc53,675 bytesextracts/01-singlecell.mddoc50,981 bytesextracts/02-protein.mddoc34,800 bytesextracts/03-physics.mddoc32,503 bytesextracts/04-drug.mddoc48,737 bytesextracts/05-medical.mddoc46,643 bytesextracts/06-ml.mddoc42,974 bytesextracts/07-ai-methods.mddoc66,013 bytesfigure-references/01-fig1-schematic.mddoc8,875 bytesfigure-references/02-color.mddoc4,372 bytesfigure-references/03-typography-layout.mddoc5,099 bytesfigure-references/04-chart-selection.mddoc3,106 bytesfigure-references/05-stats-in-figure.mddoc2,091 bytesfigure-references/06-workflow-and-files.mddoc3,553 bytesfigure-references/07-voice-by-subgenre.mddoc2,498 bytesfigure-references/08-antipatterns.mddoc2,198 bytesfigure-references/09-caption.mddoc2,288 bytesfigure-references/10-templates.mddoc4,908 bytesfigure-references/11-taste-development.mddoc2,387 bytesfigure-references/12-bridge-to-writing.mddoc2,829 bytesfigure-references/README.mddoc2,539 bytesreferences/01-story.mddoc8,926 bytesreferences/02-title.mddoc4,633 bytesreferences/03-abstract.mddoc9,951 bytesreferences/04-intro.mddoc7,491 bytesreferences/05-results.mddoc11,175 bytesreferences/06-methods.mddoc5,333 bytesreferences/07-discussion.mddoc8,935 bytesreferences/08-sentence-taste.mddoc10,676 bytesreferences/09-reviewer-protocol.mddoc4,292 bytesreferences/10-voice.mddoc5,733 bytesreferences/11-language-bank.mddoc3,426 bytesreferences/12-subgenres.mddoc12,031 bytesreferences/13-antipatterns.mddoc3,073 bytesreferences/14-journals.mddoc4,086 bytesreferences/15-taste-development.mddoc2,003 bytesreferences/README.mddoc2,714 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- nature-writing
Repository facts
- License
- No license detected
- Created
- Apr 27, 2026
- Last pushed
- Apr 27, 2026
- Forks
- 19
- Open issues
- 0
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
- No broad tool permissions
- No dangerous shell commands
- 183 network referencesin 22 files: archive/SKILL.v3.md:1 README.md:42 SKILL.md:6 and 19 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 183 signals by file
FIGURE-SKILL.md
- Network accessline 116
| `figure-references/05-stats-in-figure.md` | error bar / 显著性 / N / boxplot 约定 | 60 | | `figure-references/06-workflow-and-files.md` | matplotlib→Illustrator pipeline、PNG 反模式、字体 embed、DPI 300/450、RGB vs CMYK、主图格式白名单、50MB 上限 | 90 | | `figure - Network accessline 117
| `figure-references/06-workflow-and-files.md` | matplotlib→Illustrator pipeline、PNG 反模式、字体 embed、DPI 300/450、RGB vs CMYK、主图格式白名单、50MB 上限 | 90 | | `figure-references/07-voice-by-subgenre.md` | Nature 旗舰 / NMI / NC / NCS / 临床 5 种视觉口音 | 70 | - Network accessline 118
| `figure-references/07-voice-by-subgenre.md` | Nature 旗舰 / NMI / NC / NCS / 临床 5 种视觉口音 | 70 | - Network accessline 220
- https://research-figure-guide.nature.com/figures/preparing-figures-our-specifications/ - Network accessline 221
- https://research-figure-guide.nature.com/figures/building-and-exporting-figure-panels/ - Network accessline 222
- https://www.nature.com/documents/NRJs-guide-to-preparing-final-artwork.pdf - Network accessline 223
- https://www.nature.com/articles/nmeth.1618 （Wong 2011 著录页） - Network accessline 224
- https://clauswilke.com/dataviz/color-pitfalls.html （Wong / Okabe-Ito 8 色板 hex 交叉验证）
README.md
- Network accessline 42
# 用户级（所有项目都能用） git clone https://github.com/SyntaxSmith/nature-writing-skill.git ~/.claude/skills/nature-writing - Network accessline 43
git clone https://github.com/SyntaxSmith/nature-writing-skill.git ~/.claude/skills/nature-writing - Network accessline 45
# 或项目级（仅当前项目） git clone https://github.com/SyntaxSmith/nature-writing-skill.git .claude/skills/nature-writing - Network accessline 46
git clone https://github.com/SyntaxSmith/nature-writing-skill.git .claude/skills/nature-writing - Network accessline 56
git clone https://github.com/SyntaxSmith/nature-writing-skill.git ~/skills/nature-writing - Network accessline 60
<!-- AGENTS.md --> ## Writing for Nature-family journals When drafting or revising papers for NMI / NC / NCS / Nature, first read - Network accessline 61
## Writing for Nature-family journals When drafting or revising papers for NMI / NC / NCS / Nature, first read `~/skills/nature-writing/SKILL.md`, then load only the relevant - Network accessline 62
When drafting or revising papers for NMI / NC / NCS / Nature, first read - Network accessline 128
│ ├── 08-sentence-taste.md # rhythm、经济、restraint、negative space │ ├── 09-reviewer-protocol.md │ ├── 10-voice.md # DeepMind / NMI / NC / NCS / 临床 5 种 voice - Network accessline 129
│ ├── 09-reviewer-protocol.md │ ├── 10-voice.md # DeepMind / NMI / NC / NCS / 临床 5 种 voice │ ├── 11-language-bank.md # 强动词 / hedge / 段间连接 - Network accessline 130
│ ├── 10-voice.md # DeepMind / NMI / NC / NCS / 临床 5 种 voice - Network accessline 145
| # | 领域 | 论文 | 刊物 | |---|---|---|---| | 1–6 | 单细胞基因组 | Geneformer · SCimilarity · Tangram · scIB · CellOracle · CellFM | Nature × 3 / Nat Methods × 2 / NC | - Network accessline 146
|---|---|---|---| | 1–6 | 单细胞基因组 | Geneformer · SCimilarity · Tangram · scIB · CellOracle · CellFM | Nature × 3 / Nat Methods × 2 / NC | | 7–12 | 蛋白 / 结构 AI | AlphaFold2 · ESM-2 · ProteinMPNN · RFdiffusion · AlphaMissense · Foldseek | Natur - Network accessline 147
| 1–6 | 单细胞基因组 | Geneformer · SCimilarity · Tangram · scIB · CellOracle · CellFM | Nature × 3 / Nat Methods × 2 / NC | - Network accessline 148
| 7–12 | 蛋白 / 结构 AI | AlphaFold2 · ESM-2 · ProteinMPNN · RFdiffusion · AlphaMissense · Foldseek | Nature × 2 / Science × 3 / Nat Biotechnol | | 13–18 | 物理 / 气候 / 材料 | GraphCast · GenCast · DIMON · M3GNet · HINTS · GNoME | Science / Nature × - Network accessline 149
| 13–18 | 物理 / 气候 / 材料 | GraphCast · GenCast · DIMON · M3GNet · HINTS · GNoME | Science / Nature × 2 / NCS × 2 / NMI | | 19–24 | 药物发现 | DynamicBind · Wong-MRSA · Halicin · SyntheMol · RetroExplainer · DRAGONFLY | NC × 4 / Nature / Cell | | - Network accessline 150
| 19–24 | 药物发现 | DynamicBind · Wong-MRSA · Halicin · SyntheMol · RetroExplainer · DRAGONFLY | NC × 4 / Nature / Cell | - Network accessline 151
| 25–30 | 临床 AI | MedSAM · UNI · CONCH · Virchow · MedPerf · Ferber-GPT4V | Nat Med × 3 / NC × 2 / NMI | - Network accessline 152
| 31–36 | ML 通用 / 基础模型 | ChemCrow · AlphaGeometry · MolE · SemanticLens · Cancer-Imaging-FM · FunSearch | NMI × 4 / Nature × 2 / NC | - Network accessline 153
| 37–44 | 纯 AI 方法 (v5 新增) | DeepSeek-R1 · Densing-law · AligNet · ADeLe · Webb-MAP · DiscoRL · Farquhar-semantic-entropy · Whitelam-Simmering | Nature × 5 / NMI / NC × 2 |
SKILL.md
- Network accessline 6
# Nature 系 AI / ML 论文写作技巧 v4（拆分版） ## Craft, Taste, and Story-Craft for NMI / NC / NCS / Nature - Network accessline 7
## Craft, Taste, and Story-Craft for NMI / NC / NCS / Nature - Network accessline 135
| `references/08-sentence-taste.md` | 10 句 memorable sentences 解剖、rhythm、经济、name-your-noun、negative space | 370 | | `references/09-reviewer-protocol.md` | 5-pass harsh referee protocol、SNEER/NOD/ASK/CUT、每段末尾 invisible answer | 150 | | `refe - Network accessline 136
| `references/09-reviewer-protocol.md` | 5-pass harsh referee protocol、SNEER/NOD/ASK/CUT、每段末尾 invisible answer | 150 | | `references/10-voice.md` | DeepMind / NMI / NC / NCS / 临床 5 种 voice、confident vs arrogant、modest vs timid | 160 | | `re - Network accessline 137
| `references/10-voice.md` | DeepMind / NMI / NC / NCS / 临床 5 种 voice、confident vs arrogant、modest vs timid | 160 | - Network accessline 139
| `references/12-subgenres.md` | 7 个子门类剧本：ML 方法 / Foundation / LLM-agent / Interpretability / Benchmark / AI-for-X / 临床 | 335 | | `references/13-antipatterns.md` | craft + AI-specific + taste 三类反模式 | 90 | | `references/14-journals.md` | Nat - Network accessline 140
| `references/13-antipatterns.md` | craft + AI-specific + taste 三类反模式 | 90 | | `references/14-journals.md` | Nature / NMI / NC / NCS / NM / Nat Med 各自 voice 与策略 | 160 | | `references/15-taste-development.md` | 读法 / rewrite-by-hand / taste n - Network accessline 141
| `references/14-journals.md` | Nature / NMI / NC / NCS / NM / Nat Med 各自 voice 与策略 | 160 | - Network accessline 356
| # | 领域 | 论文 | 刊物 | 取样文件 | |---|---|---|---|---| | 1–6 | 单细胞 | Geneformer, SCimilarity, Tangram, scIB, CellOracle, CellFM | Nature × 3, Nat Methods × 2, NC × 1 | `extracts/01-singlecell.md` | - Network accessline 357
|---|---|---|---|---| | 1–6 | 单细胞 | Geneformer, SCimilarity, Tangram, scIB, CellOracle, CellFM | Nature × 3, Nat Methods × 2, NC × 1 | `extracts/01-singlecell.md` | | 7–12 | 蛋白 / 结构 AI | AlphaFold2, ESM-2/ESMFold, ProteinMPNN, RFdiffusion, - Network accessline 358
| 1–6 | 单细胞 | Geneformer, SCimilarity, Tangram, scIB, CellOracle, CellFM | Nature × 3, Nat Methods × 2, NC × 1 | `extracts/01-singlecell.md` | - Network accessline 359
| 7–12 | 蛋白 / 结构 AI | AlphaFold2, ESM-2/ESMFold, ProteinMPNN, RFdiffusion, AlphaMissense, Foldseek | Nature × 2, Science × 3, Nat Biotechnol × 1 | `extracts/02-protein.md` | | 13–18 | 物理 / 气候 / 材料 | GraphCast, GenCast, DIMON, M3GNet, HINTS, - Network accessline 360
| 13–18 | 物理 / 气候 / 材料 | GraphCast, GenCast, DIMON, M3GNet, HINTS, GNoME | Science, Nature × 2, NCS × 2, NMI | `extracts/03-physics.md` | | 19–24 | 药物发现 | DynamicBind, Wong-MRSA, Halicin, SyntheMol, RetroExplainer, DRAGONFLY | NC × 4, Natur - Network accessline 361
| 19–24 | 药物发现 | DynamicBind, Wong-MRSA, Halicin, SyntheMol, RetroExplainer, DRAGONFLY | NC × 4, Nature, Cell | `extracts/04-drug.md` | - Network accessline 362
| 25–30 | 临床 AI | MedSAM, UNI, CONCH, Virchow, MedPerf, Ferber-GPT4V | Nat Med × 3, NC × 2, NMI | `extracts/05-medical.md` | - Network accessline 363
| 31–36 | ML 通用 / 基础模型 | ChemCrow, AlphaGeometry, MolE, SemanticLens, Cancer-Imaging-FM, FunSearch | NMI × 4, Nature × 2, NC | `extracts/06-ml.md` | - Network accessline 364
| 37–44 | **纯 AI 方法（v5 新加）** | Webb-MAP, Xiao-Densing-law, Whitelam-Simmering, DeepSeek-R1, Oh-DiscoRL, Farquhar-semantic-entropy, Muttenthaler-AligNet, Zhou-ADeLe | Nature × 5, NMI × 1, NC × 2 | `extracts/07-ai-methods.md` |
archive/SKILL.v3.md
- Network accessline 1
--- name: nature-writing description: 以 AI / ML 研究者为主要读者，写作 Nature 系（NMI 主，NC / NCS / Nature 次，必要时 Nature Methods / Medicine 跨域参考）顶刊论文的修辞与结构骨架。基于 36 篇开放获取论文的逐句抽取与跨刊归纳，提供可复用的章节模板、动词与连接词词库、子门类剧本、AI-specific 反模式与提交前自检表。所有"verbatim"短语都可在 `extra - Network accessline 2
name: nature-writing description: 以 AI / ML 研究者为主要读者，写作 Nature 系（NMI 主，NC / NCS / Nature 次，必要时 Nature Methods / Medicine 跨域参考）顶刊论文的修辞与结构骨架。基于 36 篇开放获取论文的逐句抽取与跨刊归纳，提供可复用的章节模板、动词与连接词词库、子门类剧本、AI-specific 反模式与提交前自检表。所有"verbatim"短语都可在 `extracts/ - Network accessline 3
description: 以 AI / ML 研究者为主要读者，写作 Nature 系（NMI 主，NC / NCS / Nature 次，必要时 Nature Methods / Medicine 跨域参考）顶刊论文的修辞与结构骨架。基于 36 篇开放获取论文的逐句抽取与跨刊归纳，提供可复用的章节模板、动词与连接词词库、子门类剧本、AI-specific 反模式与提交前自检表。所有"verbatim"短语都可在 `extracts/0X-*.md` 回查。 - Network accessline 41
**AI 视角下的关键差异**： - 物理 / 化学 / 临床论文偏好 Nature 排版的 Results-then-Methods；NMI 与 NC 的方法论文允许 Methods 在前，或把"Architecture"小节合并进 Results 第 1 节。 - Network accessline 42
- 物理 / 化学 / 临床论文偏好 Nature 排版的 Results-then-Methods；NMI 与 NC 的方法论文允许 Methods 在前，或把"Architecture"小节合并进 Results 第 1 节。 - Network accessline 85
1. **多数论文有一句明确的 pivot 句**——把方法名、定位、一句机制装进去。词法上有几种活法： - "Here we [introduce/present/develop/show/report]"——Nature/DeepMind 旗舰偏好； - "We introduce / We present / We propose / We report"——NMI / NC 的 ML 方法论文也常用； - Network accessline 86
- "Here we [introduce/present/develop/show/report]"——Nature/DeepMind 旗舰偏好； - "We introduce / We present / We propose / We report"——NMI / NC 的 ML 方法论文也常用； - "This paper introduces …"——少数； - Network accessline 87
- "We introduce / We present / We propose / We report"——NMI / NC 的 ML 方法论文也常用； - Network accessline 196
|---|---|---| | **A. 陈述性发现（claim header）** | "X improves Y" / "Tangram maps cells with MERFISH measurements" / "Scaling shifts integration performance toward batch removal" / "Virchow enables pan-cancer detection" / "In-context learning ena - Network accessline 197
| **A. 陈述性发现（claim header）** | "X improves Y" / "Tangram maps cells with MERFISH measurements" / "Scaling shifts integration performance toward batch removal" / "Virchow enables pan-cancer detection" / "In-context learning enables multimoda - Network accessline 198
| **B. 方法名为主语（method-as-subject）** | "DRAGONFLY enables …" / "DynamicBind achieves …" / "CellFM improves …" / "MedSAM can improve the annotation efficiency" | 工具/品牌驱动；想让方法名成为"故事的主角"；NC 方法论文偏爱 | - Network accessline 659
**Nature Communications**（NC——跨学科 AI 应用 + 方法） - 接受范围最广。AI 在生物 / 化学 / 物理 / 临床的应用论文最常发。 - 方法严谨即可，不必一定是 ML 范式革命。许多 NC 论文是"在某个具体科学问题上把 AI 跑通了"。 - Network accessline 660
- 接受范围最广。AI 在生物 / 化学 / 物理 / 临床的应用论文最常发。 - 方法严谨即可，不必一定是 ML 范式革命。许多 NC 论文是"在某个具体科学问题上把 AI 跑通了"。 - 写作风格：method-as-subject Results header（B 风格）很流行；abstract 务实；closing 偏 community / 工具发布。 - Network accessline 661
- 方法严谨即可，不必一定是 ML 范式革命。许多 NC 论文是"在某个具体科学问题上把 AI 跑通了"。 - Network accessline 718
| # | 领域 | 论文 | 刊物 | 取样文件 | |---|---|---|---|---| | 1–6 | 单细胞 | Geneformer, SCimilarity, Tangram, scIB, CellOracle, CellFM | Nature × 3, Nat Methods × 2, NC × 1 | `extracts/01-singlecell.md` | - Network accessline 719
|---|---|---|---|---| | 1–6 | 单细胞 | Geneformer, SCimilarity, Tangram, scIB, CellOracle, CellFM | Nature × 3, Nat Methods × 2, NC × 1 | `extracts/01-singlecell.md` | | 7–12 | 蛋白 / 结构 AI | AlphaFold2, ESM-2/ESMFold, ProteinMPNN, RFdiffusion, - Network accessline 720
| 1–6 | 单细胞 | Geneformer, SCimilarity, Tangram, scIB, CellOracle, CellFM | Nature × 3, Nat Methods × 2, NC × 1 | `extracts/01-singlecell.md` | - Network accessline 721
| 7–12 | 蛋白 / 结构 AI | AlphaFold2, ESM-2/ESMFold, ProteinMPNN, RFdiffusion, AlphaMissense, Foldseek | Nature × 2, Science × 3, Nat Biotechnol × 1 | `extracts/02-protein.md` | | 13–18 | 物理 / 气候 / 材料 | GraphCast, GenCast, DIMON, M3GNet, HINTS, - Network accessline 722
| 13–18 | 物理 / 气候 / 材料 | GraphCast, GenCast, DIMON, M3GNet, HINTS, GNoME | Science, Nature × 2, NCS × 2, NMI | `extracts/03-physics.md` | | 19–24 | 药物发现 | DynamicBind, Wong-MRSA, Halicin, SyntheMol, RetroExplainer, DRAGONFLY | NC × 4, Natur - Network accessline 723
| 19–24 | 药物发现 | DynamicBind, Wong-MRSA, Halicin, SyntheMol, RetroExplainer, DRAGONFLY | NC × 4, Nature, Cell | `extracts/04-drug.md` | - Network accessline 724
| 25–30 | 临床 AI | MedSAM, UNI, CONCH, Virchow, MedPerf, Ferber-GPT4V | Nat Med × 3, NC × 2, NMI | `extracts/05-medical.md` | - Network accessline 725
| 31–36 | ML 通用 / 基础模型 | ChemCrow, AlphaGeometry, MolE, SemanticLens, Cancer-Imaging-FM, FunSearch | NMI × 4, Nature × 2, NC | `extracts/06-ml.md` |
extracts/01-singlecell.md
- Network accessline 10
## Paper 1: Theodoris et al., "Transfer learning enables predictions in network biology" (Geneformer) - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC10949956/ (publisher: https://www.nature.com/articles/s41586-023-06139-9) - Network accessline 11
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC10949956/ (publisher: https://www.nature.com/articles/s41586-023-06139-9) - Network accessline 68
## Paper 2: Heimberg et al., "A cell atlas foundation model for scalable search of similar human cells" (SCimilarity) - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC11864978/ (publisher: https://www.nature.com/articles/s41586-024-08411 - Network accessline 69
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC11864978/ (publisher: https://www.nature.com/articles/s41586-024-08411-y) - Network accessline 127
## Paper 3: Biancalani et al., "Deep learning and alignment of spatially resolved single-cell transcriptomes with Tangram" - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC8566243/ (publisher: https://www.nature.com/articles/s41592-021-0 - Network accessline 128
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC8566243/ (publisher: https://www.nature.com/articles/s41592-021-01264-7) - Network accessline 185
## Paper 4: Luecken et al., "Benchmarking atlas-level data integration in single-cell genomics" (scIB) - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC8748196/ (publisher: https://www.nature.com/articles/s41592-021-01336-8) - Network accessline 186
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC8748196/ (publisher: https://www.nature.com/articles/s41592-021-01336-8) - Network accessline 242
## Paper 5: Kamimoto et al., "Dissecting cell identity via network inference and in silico gene perturbation" (CellOracle) - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC9946838/ (publisher: https://www.nature.com/articles/s41586-022-0 - Network accessline 243
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC9946838/ (publisher: https://www.nature.com/articles/s41586-022-05688-9) - Network accessline 297
## Paper 6: Zeng et al., "CellFM: a large-scale foundation model pre-trained on transcriptomics of 100 million human cells" - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC12092794/ (publisher: https://www.nature.com/articles/s41467-025 - Network accessline 298
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC12092794/ (publisher: https://www.nature.com/articles/s41467-025-59926-5)
extracts/02-protein.md
- Network accessline 11
## Paper 1: Jumper et al., AlphaFold2, Nature 2021 - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC8371605/ ; https://www.nature.com/articles/s41586-021-03819-2 - Network accessline 12
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC8371605/ ; https://www.nature.com/articles/s41586-021-03819-2 - Network accessline 69
## Paper 2: Lin et al., ESM-2 / ESMFold, Science 2023 (bioRxiv OA preprint) - url_oa: https://www.biorxiv.org/content/10.1101/2022.07.20.500902v3 (bioRxiv) ; PDF mirror: https://www.marcottelab.org/users/BCH394P_364C_2024/ESMFold_2023.pdf - Network accessline 70
- url_oa: https://www.biorxiv.org/content/10.1101/2022.07.20.500902v3 (bioRxiv) ; PDF mirror: https://www.marcottelab.org/users/BCH394P_364C_2024/ESMFold_2023.pdf - Network accessline 90
B4_pivot_first2sent: "We posit that the task of filling in missing amino acids in protein sequences across evolution will require a language model to understand the underlying structure that creates the patterns in the sequences." B5_contri - Network accessline 92
B6_last_intro_sentence: "These predicted structures can be accessed in the ESM Metagenomic Atlas (https://esmatlas.com) open science resource." - Network accessline 119
## Paper 3: Dauparas et al., ProteinMPNN, Science 2022 (bioRxiv OA + PMC) - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC9997061/ - Network accessline 120
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC9997061/ - Network accessline 170
## Paper 4: Watson et al., RFdiffusion, Nature 2023 - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC10468394/ ; https://www.nature.com/articles/s41586-023-06415-8 - Network accessline 171
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC10468394/ ; https://www.nature.com/articles/s41586-023-06415-8 - Network accessline 226
## Paper 5: Cheng et al., AlphaMissense, Science 2023 - url_oa: https://www.science.org/doi/10.1126/science.adg7492 (abstract via PubMed: https://pubmed.ncbi.nlm.nih.gov/37733863/) - Network accessline 227
- url_oa: https://www.science.org/doi/10.1126/science.adg7492 (abstract via PubMed: https://pubmed.ncbi.nlm.nih.gov/37733863/) - Network accessline 275
## Paper 6: van Kempen et al., Foldseek, Nature Biotechnology 2024 - url_oa: https://www.nature.com/articles/s41587-023-01773-0 (abstract via PubMed: https://pubmed.ncbi.nlm.nih.gov/37156916/) - Network accessline 276
- url_oa: https://www.nature.com/articles/s41587-023-01773-0 (abstract via PubMed: https://pubmed.ncbi.nlm.nih.gov/37156916/)
extracts/03-physics.md
- Network accessline 9
## Paper 1: Lam et al., GraphCast, Science 2023 (arXiv 2212.12794) - url_oa: https://arxiv.org/abs/2212.12794 ; https://ar5iv.labs.arxiv.org/html/2212.12794 - Network accessline 10
- url_oa: https://arxiv.org/abs/2212.12794 ; https://ar5iv.labs.arxiv.org/html/2212.12794 - Network accessline 63
## Paper 2: Price et al., GenCast, Nature 2024 (arXiv 2312.15796) - url_oa: https://arxiv.org/abs/2312.15796 ; https://arxiv.org/html/2312.15796v1 - Network accessline 64
- url_oa: https://arxiv.org/abs/2312.15796 ; https://arxiv.org/html/2312.15796v1 - Network accessline 112
## Paper 3: Yin et al., DIMON, Nature Computational Science 2024 (arXiv 2402.07250) - url_oa: https://arxiv.org/abs/2402.07250 ; https://arxiv.org/html/2402.07250v1 - Network accessline 113
- url_oa: https://arxiv.org/abs/2402.07250 ; https://arxiv.org/html/2402.07250v1 - Network accessline 162
## Paper 4: Chen & Ong, M3GNet, Nature Computational Science 2022 (arXiv 2202.02450) - url_oa: https://arxiv.org/abs/2202.02450 - Network accessline 163
- url_oa: https://arxiv.org/abs/2202.02450 - Network accessline 212
## Paper 5: Zhang et al., HINTS, Nature Machine Intelligence 2024 (arXiv 2208.13273) - url_oa: https://arxiv.org/abs/2208.13273 ; https://ar5iv.labs.arxiv.org/html/2208.13273 - Network accessline 213
- url_oa: https://arxiv.org/abs/2208.13273 ; https://ar5iv.labs.arxiv.org/html/2208.13273 - Network accessline 261
## Paper 6: Merchant et al., GNoME / Scaling Deep Learning for Materials Discovery, Nature 2023 - url_oa: https://www.nature.com/articles/s41586-023-06735-9 (Nature OA); abstract reproduced from openly indexed source - Network accessline 262
- url_oa: https://www.nature.com/articles/s41586-023-06735-9 (Nature OA); abstract reproduced from openly indexed source
extracts/04-drug.md
- Network accessline 7
## Paper 1: Lu et al., DynamicBind (Nature Communications, 2024) - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC10844226/ - Network accessline 8
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC10844226/ - Network accessline 78
## Paper 2: Wong et al., Discovery of a structural class of antibiotics with explainable deep learning (Nature, 2024) - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC10866013/ - Network accessline 79
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC10866013/ - Network accessline 156
## Paper 3: Stokes et al., A deep learning approach to antibiotic discovery — Halicin (Cell, 2020) - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC8349178/ - Network accessline 157
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC8349178/ - Network accessline 227
## Paper 4: Swanson et al., SyntheMol (Nature Machine Intelligence, 2024; workshop preprint NeurIPS 2023 GenAI & Biology) - url_oa: https://www.nature.com/articles/s42256-024-00809-7 (NeurIPS workshop PDF used for verbatim text) - Network accessline 228
- url_oa: https://www.nature.com/articles/s42256-024-00809-7 (NeurIPS workshop PDF used for verbatim text) - Network accessline 297
## Paper 5: Wang et al., RetroExplainer (Nature Communications, 2023) - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC10547708/ - Network accessline 298
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC10547708/ - Network accessline 367
## Paper 6: Cretu et al. / Atz et al., DRAGONFLY — Prospective de novo drug design with deep interactome learning (Nature Communications, 2024) - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC11035696/ - Network accessline 368
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC11035696/
extracts/05-medical.md
- Network accessline 10
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC10803759/ - Network accessline 89
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC11403354/ - Network accessline 175
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC11384335/ - Network accessline 257
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC11485232/ - Network accessline 337
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC11068064/ - Network accessline 414
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC11582649/
extracts/06-ml.md
- Network accessline 7
## Paper 1: Bran, A. M., Cox, S., Schilter, O., Baldassari, C., White, A. D. & Schwaller, P. "Augmenting large language models with chemistry tools." Nature Machine Intelligence 6, 525–535 (2024). - url_oa: https://pmc.ncbi.nlm.nih.gov/arti - Network accessline 8
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC11116106/ - Network accessline 59
## Paper 2: Trinh, T. H., Wu, Y., Le, Q. V., He, H. & Luong, T. "Solving olympiad geometry without human demonstrations." Nature 625, 476–482 (2024). - url_oa: https://research.google/pubs/solving-olympiad-geometry-without-human-demonstrati - Network accessline 60
- url_oa: https://research.google/pubs/solving-olympiad-geometry-without-human-demonstrations/ (open author copy); Nature record https://www.nature.com/articles/s41586-023-06747-5 - Network accessline 110
## Paper 3: Méndez-Lucio, O. et al. "MolE: a foundation model for molecular graphs using disentangled attention." Nature Communications 15, 9431 (2024). - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC11557931/ - Network accessline 111
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC11557931/ - Network accessline 164
## Paper 4: Dreyer, M., Berend, J., Labarta, T., Vielhaben, J., Lapuschkin, S., Höhne, M. M.-C. & Samek, W. "Mechanistic understanding and validation of large AI models with SemanticLens." Nature Machine Intelligence 7, 1572–1585 (2025). - - Network accessline 165
- url_oa: https://arxiv.org/abs/2501.05398 ; Nature record https://www.nature.com/articles/s42256-025-01084-w - Network accessline 214
## Paper 5: Pai, S., Bontempi, D., Hadzic, I., Prudente, V., Sokač, M., Chaunzwa, T. L., Bernatz, S., Hosny, A., Mak, R. H., Birkbak, N. J. & Aerts, H. J. W. L. "Foundation model for cancer imaging biomarkers." Nature Machine Intelligence 6 - Network accessline 215
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC10957482/ - Network accessline 261
## Paper 6: Romera-Paredes, B., Barekatain, M., Novikov, A., Balog, M., Kumar, M. P., Dupont, E., Ruiz, F. J. R., Ellenberg, J. S., Wang, P., Fawzi, O., Kohli, P. & Fawzi, A. "Mathematical discoveries from program search with large language - Network accessline 262
- url_oa: https://storage.googleapis.com/deepmind-media/DeepMind.com/Blog/funsearch-making-new-discoveries-in-mathematical-sciences-using-large-language-models/Mathematical-discoveries-from-program-search-with-large-language-models.pdf (aut
extracts/07-ai-methods.md
- Network accessline 9
## Paper 1: Webb, T. W., Mondal, S. S., Jang, C., Chang, K., Frankland, S. M., Lake, B. M., Cohen, J. D. & Russin, J. "A brain-inspired agentic architecture to improve planning with LLMs." Nature Communications 16, 8804 (2025). - url_oa: ht - Network accessline 10
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC12485071/ ; https://www.nature.com/articles/s41467-025-63804-5 - Network accessline 69
## Paper 2: Xiao, C., Cai, J., Zhao, W., Zeng, G., Lin, B. Y., Han, X., Shi, Z., Zhao, Y., Liu, Z. & Sun, M. "Densing law of LLMs." Nature Machine Intelligence (2025). - url_oa: https://arxiv.org/abs/2412.04315 ; https://arxiv.org/html/2412 - Network accessline 70
- url_oa: https://arxiv.org/abs/2412.04315 ; https://arxiv.org/html/2412.04315v2 ; Nature record https://www.nature.com/articles/s42256-025-01137-0 - Network accessline 128
## Paper 3: Whitelam, S. "Sufficient is better than optimal for training neural networks." Nature Communications 16, 18044 (2025). - url_oa: https://arxiv.org/abs/2410.19912 ; https://arxiv.org/html/2410.19912 ; https://www.nature.com/artic - Network accessline 129
- url_oa: https://arxiv.org/abs/2410.19912 ; https://arxiv.org/html/2410.19912 ; https://www.nature.com/articles/s41467-025-66983-3 - Network accessline 184
## Paper 4: DeepSeek-AI; Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R. et al. "DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning." Nature 645, 633–638 (2025). - url_oa: https://arxiv.org/abs/2501.12948 ; - Network accessline 185
- url_oa: https://arxiv.org/abs/2501.12948 ; https://arxiv.org/html/2501.12948v1 ; Nature record https://www.nature.com/articles/s41586-025-09422-z - Network accessline 240
## Paper 5: Oh, J., Farquhar, G., Schroecker, Y., Chen, R., Whiteson, S., Singh, S. & Silver, D. "Discovering state-of-the-art reinforcement learning algorithms." Nature 648, 312–319 (2025). - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/P - Network accessline 241
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC12695655/ ; https://www.nature.com/articles/s41586-025-09761-x - Network accessline 291
notable: **Biology-vs-engineering analogy** as opener — same cross-engineering-domain hook pattern noted in SemanticLens (06-ml.md Paper 4). **Title is a verb-noun-phrase** ("Discovering …") — present-participle voice signals the paper *is* - Network accessline 295
## Paper 6: Farquhar, S., Kossen, J., Kuhn, L. & Gal, Y. "Detecting hallucinations in large language models using semantic entropy." Nature 630, 625–630 (2024). - url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC11186750/ ; Nature record ht - Network accessline 296
- url_oa: https://pmc.ncbi.nlm.nih.gov/articles/PMC11186750/ ; Nature record https://www.nature.com/articles/s41586-024-07421-0 - Network accessline 353
## Paper 7: Muttenthaler, L. et al. (Google DeepMind / Helmholtz Munich). "Aligning machine and human visual representations across abstraction levels." Nature 648, 165–173 (2025). - url_oa: https://arxiv.org/abs/2409.06509 ; https://arxiv. - Network accessline 354
- url_oa: https://arxiv.org/abs/2409.06509 ; https://arxiv.org/html/2409.06509v4 ; Nature record https://www.nature.com/articles/s41586-025-09631-6 - Network accessline 412
## Paper 8: Zhou, L., Pacchiardi, L., Martínez-Plumed, F., Collins, K. M., Moros-Daval, Y., Zhang, S., Zhao, Q., Huang, Y., Sun, L., Prunty, J. E., Li, Z., Sánchez-Monzón, P., Schellaert, W., Ó hÉigeartaigh, S., Tešić, J., Hernández-Orallo, - Network accessline 413
- url_oa: https://arxiv.org/abs/2503.06378 ; https://arxiv.org/html/2503.06378 ; Nature record https://www.nature.com/articles/s41586-026-10303-2
figure-references/07-voice-by-subgenre.md
- Network accessline 3
（FIGURE-SKILL Part VII §8：Nature 旗舰 / NMI / NC / NCS / 临床 5 种 voice；总索引见 `../FIGURE-SKILL.md`）
figure-references/12-bridge-to-writing.md
- Network accessline 41
corpus 内 NMI / NC / NCS 的常见配置：
figure-references/README.md
- Network accessline 27
| `05-stats-in-figure.md` | error bar / 显著性 / N / boxplot 约定 | | `06-workflow-and-files.md` | matplotlib→Illustrator pipeline、PNG 反模式、字体 embed Type 42、DPI 300/450、RGB vs CMYK 政策、主图格式白名单（不接受 PNG/JPG/TIFF 作主图本体）、文件大小 ≤50MB | | `07-voice-by-su - Network accessline 28
| `06-workflow-and-files.md` | matplotlib→Illustrator pipeline、PNG 反模式、字体 embed Type 42、DPI 300/450、RGB vs CMYK 政策、主图格式白名单（不接受 PNG/JPG/TIFF 作主图本体）、文件大小 ≤50MB | | `07-voice-by-subgenre.md` | Nature 旗舰 / NMI / NC / NCS / 临床 5 种视觉口音 | | `08-an - Network accessline 29
| `07-voice-by-subgenre.md` | Nature 旗舰 / NMI / NC / NCS / 临床 5 种视觉口音 |
references/02-title.md
- Network accessline 15
|---|---|---|---| | **A. 工具名 / 极简短语** | "Foldseek"；"Segment anything in medical images" | 工具本身能成为品牌；Brief / tool paper | 短标题必须有识别度，否则显得空 | | **B. 工具名 + 冒号 + 描述** | "DynamicBind: predicting ligand-specific protein-ligand complex structure wi - Network accessline 16
| **A. 工具名 / 极简短语** | "Foldseek"；"Segment anything in medical images" | 工具本身能成为品牌；Brief / tool paper | 短标题必须有识别度，否则显得空 | | **B. 工具名 + 冒号 + 描述** | "DynamicBind: predicting ligand-specific protein-ligand complex structure with a deep equivari - Network accessline 17
| **B. 工具名 + 冒号 + 描述** | "DynamicBind: predicting ligand-specific protein-ligand complex structure with a deep equivariant generative model"；"MolE: a foundation model for molecular graphs using disentangled attention"；"GenCast: Diffusion-ba
references/03-abstract.md
- Network accessline 75
- Webb (NC 2025) S6：*"three challenging planning tasks"* — 不是数据规模，是 task 多样性。
references/05-results.md
- Network accessline 17
| **B. Method-as-subject** | `<NAME> <verb> <capability>` | DynamicBind: "DynamicBind achieves higher accuracy…"；DRAGONFLY: "DRAGONFLY outperforms…"；CellFM: "CellFM enables…" | 工具要成为 protagonist | | **C. Task-neutral / capability noun phras - Network accessline 19
| **D. RQ / analysis-scaffold header**（v5 新加） | `RQ1: does <X> explain <Y>?` / `<Capability>: <task>` | Webb (NC 2025): "Problem solving: Tower of Hanoi"；Zhou (Nature 2026): "RQ1 examines…"；Muttenthaler: "Alignment improves generalization…" - Network accessline 24
- 一篇论文最好主用一种 header 风格。 - Benchmark 论文偏 A。 - NC 方法论文常用 B。 - Network accessline 25
- Benchmark 论文偏 A。 - NC 方法论文常用 B。 - Foundation model / pathology 常用 C。 - Network accessline 26
- NC 方法论文常用 B。
references/06-methods.md
- Network accessline 58
**主文 / SI 分工**（来自 `extracts/07-ai-methods.md` 8 篇 2024–2026 NMI/Nature/NC AI 方法论文的共同惯例）：
references/09-reviewer-protocol.md
- Network accessline 22
2. Abstract s4 是否一句说清 contribution？ 3. s6 是否有 named benchmark / baseline / human anchor？ 4. 这篇是否适合 NMI / NC / NCS / Nature？ - Network accessline 23
3. s6 是否有 named benchmark / baseline / human anchor？ 4. 这篇是否适合 NMI / NC / NCS / Nature？ 5. 有没有一句让我愿意送审？ - Network accessline 24
4. 这篇是否适合 NMI / NC / NCS / Nature？
references/10-voice.md
- Network accessline 3
（v4 SKILL Part IX：DeepMind / NMI / NC / NCS / 临床 voice 对比；总索引见 `../SKILL.md`） - Network accessline 15
两句话都好，但不能互换。AlphaFold 有 CASP14 + 50-year problem + field adoption；MolE 是 NC methods paper，`initial step` 是正确 register。 - Network accessline 92
NC voice 适合：“我解决了一个具体科学 / 工程问题，并验证充分。” - Network accessline 161
- AI-for-X voice（§12.3 NC 跨学科）："*we apply <method> to <domain> and find…*"
references/14-journals.md
- Network accessline 3
（v4 SKILL Part XIV：Nature / NMI / NC / NCS / NM / Nat Med；总索引见 `../SKILL.md`） - Network accessline 99
NC 的好稿件常像： - Network accessline 102
**v5 update**：NC 也容纳 narrow but sharp methodological rebuttal（Whitelam Simmering：反驳 optimization-based training），或 brain-inspired agent architecture（Webb MAP）。这一支共同点：**狭窄但锋利**，明确反驳/补充某个 dominant practice，而不是 broadly application-driven。White
references/README.md
- Network accessline 30
| `08-sentence-taste.md` | 10 句 memorable sentences 解剖、rhythm、经济、name-your-noun、negative space | | `09-reviewer-protocol.md` | 5-pass harsh referee protocol、SNEER/NOD/ASK/CUT、invisible answer 练习 | | `10-voice.md` | DeepMind / NMI / NC / NCS - Network accessline 31
| `09-reviewer-protocol.md` | 5-pass harsh referee protocol、SNEER/NOD/ASK/CUT、invisible answer 练习 | | `10-voice.md` | DeepMind / NMI / NC / NCS / 临床 5 种 voice | | `11-language-bank.md` | 强动词 / hedge / 段间连接词 / 高复用句型 | - Network accessline 32
| `10-voice.md` | DeepMind / NMI / NC / NCS / 临床 5 种 voice | - Network accessline 34
| `12-subgenres.md` | 7 个子门类剧本：ML 方法 / Foundation / LLM-agent / Interpretability / Benchmark / AI-for-X / 临床 | | `13-antipatterns.md` | craft + AI-specific + taste 反模式 | | `14-journals.md` | Nature / NMI / NC / NCS / NM / Nat Med 各自 voice 与 - Network accessline 35
| `13-antipatterns.md` | craft + AI-specific + taste 反模式 | | `14-journals.md` | Nature / NMI / NC / NCS / NM / Nat Med 各自 voice 与策略 | | `15-taste-development.md` | 读法 / 临摹 / taste notebook / mentor / OpenReview / 返回旧草稿 | - Network accessline 36
| `14-journals.md` | Nature / NMI / NC / NCS / NM / Nat Med 各自 voice 与策略 |
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Signal confidence: 183 facts
- Network access in prose of documentationFIGURE-SKILL.md:116Low confidence
- Network access in prose of documentationFIGURE-SKILL.md:117Low confidence
- Network access in prose of documentationFIGURE-SKILL.md:118Low confidence
- Network access in prose of documentationFIGURE-SKILL.md:220Low confidence
- Network access in prose of documentationFIGURE-SKILL.md:221Low confidence
- Network access in prose of documentationFIGURE-SKILL.md:222Low confidence
- Network access in prose of documentationFIGURE-SKILL.md:223Low confidence
- Network access in prose of documentationFIGURE-SKILL.md:224Low confidence
- Network access in code of documentationREADME.md:42Low confidence
- Network access in code of documentationREADME.md:43Low confidence
- Network access in code of documentationREADME.md:45Low confidence
- Network access in code of documentationREADME.md:46Low confidence
- Network access in code of documentationREADME.md:56Low confidence
- Network access in code of documentationREADME.md:60Low confidence
- Network access in code of documentationREADME.md:61Low confidence
- Network access in code of documentationREADME.md:62Low confidence
- Network access in code of documentationREADME.md:128Low confidence
- Network access in code of documentationREADME.md:129Low confidence
- Network access in code of documentationREADME.md:130Low confidence
- Network access in prose of documentationREADME.md:145Low confidence
- Network access in prose of documentationREADME.md:146Low confidence
- Network access in prose of documentationREADME.md:147Low confidence
- Network access in prose of documentationREADME.md:148Low confidence
- Network access in prose of documentationREADME.md:149Low confidence
- Network access in prose of documentationREADME.md:150Low confidence
- Network access in prose of documentationREADME.md:151Low confidence
- Network access in prose of documentationREADME.md:152Low confidence
- Network access in prose of documentationREADME.md:153Low confidence
- Network access in prose of the SKILL.mdSKILL.md:6Low confidence
- Network access in prose of the SKILL.mdSKILL.md:7Low confidence
- Network access in prose of the SKILL.mdSKILL.md:135Low confidence
- Network access in prose of the SKILL.mdSKILL.md:136Low confidence
- Network access in prose of the SKILL.mdSKILL.md:137Low confidence
- Network access in prose of the SKILL.mdSKILL.md:139Low confidence
- Network access in prose of the SKILL.mdSKILL.md:140Low confidence
- Network access in prose of the SKILL.mdSKILL.md:141Low confidence
- Network access in prose of the SKILL.mdSKILL.md:356Low confidence
- Network access in prose of the SKILL.mdSKILL.md:357Low confidence
- Network access in prose of the SKILL.mdSKILL.md:358Low confidence
- Network access in prose of the SKILL.mdSKILL.md:359Low confidence
- Network access in prose of the SKILL.mdSKILL.md:360Low confidence
- Network access in prose of the SKILL.mdSKILL.md:361Low confidence
- Network access in prose of the SKILL.mdSKILL.md:362Low confidence
- Network access in prose of the SKILL.mdSKILL.md:363Low confidence
- Network access in prose of the SKILL.mdSKILL.md:364Low confidence
- Network access in prose of documentationarchive/SKILL.v3.md:1Low confidence
- Network access in prose of documentationarchive/SKILL.v3.md:2Low confidence
- Network access in prose of documentationarchive/SKILL.v3.md:3Low confidence
- Network access in prose of documentationarchive/SKILL.v3.md:41Low confidence
- Network access in prose of documentationarchive/SKILL.v3.md:42Low confidence
and 133 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
