bestpaper-writing

gulucaptain/Best-Paper-Writing-Skill Science & research AI & ML engineering Writing & content

bestpaper-writing is a skill in gulucaptain/Best-Paper-Writing-Skill, last changed 28 Oct 2026. It can run shell commands, name web addresses and bundle scripts.

From the author

Draft or rewrite the title, Abstract, Introduction, Method and Experiments of an ML/CV paper in the style of CVPR/ICCV/NeurIPS best papers, distilled from 60 award papers, and plan and draw its figures (Figure 1, method overview, result figures) with award-paper layout and style. Use when the user either (A) fills in the intake form (assets/intake_form.html JSON) or describes problem, idea, method and results, or (B) pastes an existing abstract (or abstract plus introduction) to make it more convincing. Can write directly into a LaTeX template such as the CVPR author kit. Not for related-work surveys, rebuttals or plain proofreading.

How much a skill can do, not whether it is risky.

Pattern check

Nothing flagged

That isn't proof the skill is harmless.

Commit b9eff99 · 3 Nov 2026

How the check works

Pattern check: nothing flagged

That isn't proof the skill is harmless.

Install

Each tab says whether it installs commit b9eff99, the one we checked, or the latest version.

OpenCode also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Goose also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Windsurf (Devin Desktop) also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Zed also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Roo Code also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Factory Droid also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Junie also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Amp also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

No install command here reaches Kiro. Copy the skill's folder into .kiro/skills/ in your project, or ~/.kiro/skills/ for all your projects. gulucaptain/Best-Paper-Writing-Skill/skills/bestpaper-writing (opens in a new tab)

Antigravity also looks in .agents/skills/, so the Any agent steps reach it with This project. For All projects, see where Antigravity looks.

Cline also looks in .claude/skills/, so the Claude Code steps reach it with This project. For All projects, see where Cline looks.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie and Amp. With This project, Any agent also reaches Antigravity and Claude Code reaches Cline. Kiro needs the folder copied by hand.

Pinned to commit b9eff99, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/gulucaptain/Best-Paper-Writing-Skill.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin b9eff99a2130bea960ef1050eacf9f40cb792dd4 &&git -C "$tmp" sparse-checkout set -- skills/bestpaper-writing &&git -C "$tmp" checkout -q b9eff99a2130bea960ef1050eacf9f40cb792dd4 &&mkdir -p .claude/skills &&mkdir .claude/skills/bestpaper-writing &&cp -R "$tmp"/skills/bestpaper-writing/. .claude/skills/bestpaper-writing/ &&rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs

Pinned to commit b9eff99, the one we checked.

Skills in the Claude apps belong to your account rather than to a project.

Make bestpaper-writing.zip, with the skill folder at the top level:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/gulucaptain/Best-Paper-Writing-Skill.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin b9eff99a2130bea960ef1050eacf9f40cb792dd4 &&git -C "$tmp" sparse-checkout set -- skills/bestpaper-writing &&git -C "$tmp" checkout -q b9eff99a2130bea960ef1050eacf9f40cb792dd4 &&out="$(mktemp -d)" &&cp -R "$tmp"/skills/bestpaper-writing "$out"/bestpaper-writing &&(cd "$out" && zip -qr - bestpaper-writing) > bestpaper-writing.zip &&rm -rf "$tmp" "$out"

In Claude, open Customize > Skills, select +, then + Create skill > Upload a skill, and choose bestpaper-writing.zip.

On Free, Pro and Max plans, turn on Code execution and file creation (Create and edit files in newer settings) under Settings > Capabilities.

Claude apps docs

Pinned to commit b9eff99, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/gulucaptain/Best-Paper-Writing-Skill.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin b9eff99a2130bea960ef1050eacf9f40cb792dd4 &&git -C "$tmp" sparse-checkout set -- skills/bestpaper-writing &&git -C "$tmp" checkout -q b9eff99a2130bea960ef1050eacf9f40cb792dd4 &&mkdir -p .agents/skills &&mkdir .agents/skills/bestpaper-writing &&cp -R "$tmp"/skills/bestpaper-writing/. .agents/skills/bestpaper-writing/ &&rm -rf "$tmp"

Codex picks up new skills on its own; restart it if this one does not appear.

Codex docs

Pinned to commit b9eff99, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/gulucaptain/Best-Paper-Writing-Skill.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin b9eff99a2130bea960ef1050eacf9f40cb792dd4 &&git -C "$tmp" sparse-checkout set -- skills/bestpaper-writing &&git -C "$tmp" checkout -q b9eff99a2130bea960ef1050eacf9f40cb792dd4 &&mkdir -p .cursor/skills &&mkdir .cursor/skills/bestpaper-writing &&cp -R "$tmp"/skills/bestpaper-writing/. .cursor/skills/bestpaper-writing/ &&rm -rf "$tmp"

Cursor docs

Pinned to commit b9eff99, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/gulucaptain/Best-Paper-Writing-Skill.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin b9eff99a2130bea960ef1050eacf9f40cb792dd4 &&git -C "$tmp" sparse-checkout set -- skills/bestpaper-writing &&git -C "$tmp" checkout -q b9eff99a2130bea960ef1050eacf9f40cb792dd4 &&mkdir -p .github/skills &&mkdir .github/skills/bestpaper-writing &&cp -R "$tmp"/skills/bestpaper-writing/. .github/skills/bestpaper-writing/ &&rm -rf "$tmp"

In a running Copilot CLI session, run /skills reload.

Or install it with gh skill, which also installs the commit we checked. Needs GitHub CLI 2.90 or later.

gh skill install gulucaptain/Best-Paper-Writing-Skill skills/bestpaper-writing/SKILL.md@b9eff99a2130bea960ef1050eacf9f40cb792dd4 --agent github-copilot --scope project

Copilot & VS Code docs

Pinned to commit b9eff99, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/gulucaptain/Best-Paper-Writing-Skill.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin b9eff99a2130bea960ef1050eacf9f40cb792dd4 &&git -C "$tmp" sparse-checkout set -- skills/bestpaper-writing &&git -C "$tmp" checkout -q b9eff99a2130bea960ef1050eacf9f40cb792dd4 &&mkdir -p .gemini/skills &&mkdir .gemini/skills/bestpaper-writing &&cp -R "$tmp"/skills/bestpaper-writing/. .gemini/skills/bestpaper-writing/ &&rm -rf "$tmp"

In a running session, run /skills reload.

Or use Gemini CLI’s own installer. Installs the latest version, not the one we checked.

gemini skills install https://github.com/gulucaptain/Best-Paper-Writing-Skill.git --path skills/bestpaper-writing --scope workspace

Gemini CLI docs

Pinned to commit b9eff99, the one we checked.

OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity read .agents/skills in a project.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/gulucaptain/Best-Paper-Writing-Skill.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin b9eff99a2130bea960ef1050eacf9f40cb792dd4 &&git -C "$tmp" sparse-checkout set -- skills/bestpaper-writing &&git -C "$tmp" checkout -q b9eff99a2130bea960ef1050eacf9f40cb792dd4 &&mkdir -p .agents/skills &&mkdir .agents/skills/bestpaper-writing &&cp -R "$tmp"/skills/bestpaper-writing/. .agents/skills/bestpaper-writing/ &&rm -rf "$tmp"

Or use the skills CLI from skills.sh. Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.

npx skills@1.7.4 add gulucaptain/Best-Paper-Writing-Skill --skill bestpaper-writing

Agent Skills docs

Read SKILL.md first

MIT

Licence

213

Repo stars

Folder last changed

Publisher

Files

Checked

3 Nov 2026

What it can touch

From the files and frontmatter at commit b9eff99. This is how much a skill can do, not whether it is risky.

Runs shell commands
Its instructions or files give the agent commands to run on your computer.
Names web addresses
It mentions outside web addresses the agent may visit. We list them but don't follow them.
Outside links we did not follow
Bundles scripts
The folder holds code files the agent may run.
evals/guidance-with-weaker-model/place-files.sh (opens in a new tab) · evals/image-space-motion-prior/place-files.sh (opens in a new tab) · evals/next-scale-autoregressive-images/place-files.sh (opens in a new tab) and 3 more

Pattern check

Pattern check: nothing flagged · commit b9eff99 · 3 Nov 2026

We checked every text file in this skill, at commit b9eff99 on 3 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check works Report an incorrect finding

Outside links we did not follow

https://github.com/Master-cai/Research-Paper-Writing-Skills
https://pengsida.notion.site/c1a22465a0fa4b15a12985223916048e
https://github.com/pengsida/learning_research
https://segment-anything.com
https://imaging.cs.cmu.edu/svaf
https://github.com/NVlabs/edm,EDM,NeurIPS,2022
https://avalovelace1.github.io/BrickGPT/
https://decodingtrust.github.io/.,DecodingTrust,NeurIPS,2023
https://minedojo.org
https://dreambooth.github.io/,DreamBooth,CVPR,2023

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

Agent Skills specPasses
The open format from agentskills.io, held to the strictest version of each rule among the agents we check.
- Note
  Anthropic's packaging script leaves these out: evals/. F8
  Fix: Delete them, or list them in .gitignore.
- Note
  The first sentence of the description is 280 characters. Agents shorten long descriptions, so lead with the main job. D8
  Fix: Start with one short sentence that names the job.
- Note
  There is no license field, so readers can't tell whether they may reuse the skill. O2
  Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.
- Note
  Reference files that SKILL.md doesn't link: evals/guidance-with-weaker-model/graders/01-paper-sec-0-abstract-tex.md, evals/guidance-with-weaker-model/graders/02-the-latex-project-compiles-to.md, evals/guidance-with-weaker-model/graders/03-every-citation-uses-a-key.md, evals/guidance-with-weaker-model/graders/04-every-number-in-the-abstract.md, evals/guidance-with-weaker-model/graders/05-the-abstract-and-introduction-contain.md and 71 more. Anthropic suggests linking every reference file directly from SKILL.md. B4
  Fix: Link each one from SKILL.md and say when to read it.
- Note
  Reference files over 100 lines with no table of contents at the top: references/figures.md (155 lines), references/introduction.md (214 lines) and references/style-rules.md (131 lines). B5
  Fix: Add a short list of the sections at the top of each.
Claude CodePasses
Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.
- Note
  Anthropic's packaging script leaves these out: evals/. F8
  Fix: Delete them, or list them in .gitignore.
- Note
  The first sentence of the description is 280 characters. Agents shorten long descriptions, so lead with the main job. D8
  Fix: Start with one short sentence that names the job.
- Note
  Reference files that SKILL.md doesn't link: evals/guidance-with-weaker-model/graders/01-paper-sec-0-abstract-tex.md, evals/guidance-with-weaker-model/graders/02-the-latex-project-compiles-to.md, evals/guidance-with-weaker-model/graders/03-every-citation-uses-a-key.md, evals/guidance-with-weaker-model/graders/04-every-number-in-the-abstract.md, evals/guidance-with-weaker-model/graders/05-the-abstract-and-introduction-contain.md and 71 more. Anthropic suggests linking every reference file directly from SKILL.md. B4
  Fix: Link each one from SKILL.md and say when to read it.
- Note
  Reference files over 100 lines with no table of contents at the top: references/figures.md (155 lines), references/introduction.md (214 lines) and references/style-rules.md (131 lines). B5
  Fix: Add a short list of the sections at the top of each.
Claude apps & API uploadPasses
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Note
  Anthropic's packaging script leaves these out: evals/. F8
  Fix: Delete them, or list them in .gitignore.
- Note
  The description is 641 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4
  Fix: If the claude.ai upload refuses it, trim the description to 200 characters.
- Note
  Reference files that SKILL.md doesn't link: evals/guidance-with-weaker-model/graders/01-paper-sec-0-abstract-tex.md, evals/guidance-with-weaker-model/graders/02-the-latex-project-compiles-to.md, evals/guidance-with-weaker-model/graders/03-every-citation-uses-a-key.md, evals/guidance-with-weaker-model/graders/04-every-number-in-the-abstract.md, evals/guidance-with-weaker-model/graders/05-the-abstract-and-introduction-contain.md and 71 more. Anthropic suggests linking every reference file directly from SKILL.md. B4
  Fix: Link each one from SKILL.md and say when to read it.
- Note
  Reference files over 100 lines with no table of contents at the top: references/figures.md (155 lines), references/introduction.md (214 lines) and references/style-rules.md (131 lines). B5
  Fix: Add a short list of the sections at the top of each.
OpenAI (Codex & API)Passes
Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.
- Note
  Anthropic's packaging script leaves these out: evals/. F8
  Fix: Delete them, or list them in .gitignore.
- Note
  The first sentence of the description is 280 characters. Agents shorten long descriptions, so lead with the main job. D8
  Fix: Start with one short sentence that names the job.
VS Code & CopilotPasses
VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.
- Note
  Anthropic's packaging script leaves these out: evals/. F8
  Fix: Delete them, or list them in .gitignore.

SKILL.md

Read SKILL.md on GitHub

Files

125 files

Path	Size
LICENSE-base-skill (opens in a new tab)	1 KB
NOTICE.md (opens in a new tab)	1.3 KB
SKILL.md (opens in a new tab)	17 KB
agents/openai.yaml (opens in a new tab)	363 B
assets/figures/bestpaper.mplstyle (opens in a new tab)	765 B
assets/figures/figures_preamble.tex (opens in a new tab)	2.9 KB
assets/figures/overview_tikz.tex (opens in a new tab)	1.5 KB
assets/figures/plot_style.py (opens in a new tab)	2.5 KB
assets/figures/qualitative_grid.tex (opens in a new tab)	1.5 KB
assets/figures/teaser_strip.tex (opens in a new tab)	1.5 KB
assets/intake_form.html (opens in a new tab)	26.3 KB
evals/README.md (opens in a new tab)	2.4 KB
evals/guidance-with-weaker-model/case.yaml (opens in a new tab)	518 B
evals/guidance-with-weaker-model/files/refs.bib (opens in a new tab)	1.1 KB
evals/guidance-with-weaker-model/graders/01-paper-sec-0-abstract-tex.md (opens in a new tab)	232 B
evals/guidance-with-weaker-model/graders/02-the-latex-project-compiles-to.md (opens in a new tab)	150 B
evals/guidance-with-weaker-model/graders/03-every-citation-uses-a-key.md (opens in a new tab)	182 B
evals/guidance-with-weaker-model/graders/04-every-number-in-the-abstract.md (opens in a new tab)	162 B
evals/guidance-with-weaker-model/graders/05-the-abstract-and-introduction-contain.md (opens in a new tab)	198 B
evals/guidance-with-weaker-model/graders/06-the-abstract-and-introduction-contain.md (opens in a new tab)	245 B

Show 105 more

Path	Size
evals/guidance-with-weaker-model/graders/07-the-main-idea-or-finding.md (opens in a new tab)	196 B
evals/guidance-with-weaker-model/graders/08-the-abstract-contains-at-most.md (opens in a new tab)	209 B
evals/guidance-with-weaker-model/graders/09-the-introduction-contains-a-stance.md (opens in a new tab)	224 B
evals/guidance-with-weaker-model/graders/10-the-introduction-explains-the-specific.md (opens in a new tab)	210 B
evals/guidance-with-weaker-model/graders/11-the-text-states-the-surprising.md (opens in a new tab)	201 B
evals/guidance-with-weaker-model/graders/12-the-headline-results-record-fids.md (opens in a new tab)	167 B
evals/guidance-with-weaker-model/graders/13-the-text-mentions-that-the.md (opens in a new tab)	113 B
evals/guidance-with-weaker-model/place-files.sh (opens in a new tab)	62 B
evals/guidance-with-weaker-model/prompt.md (opens in a new tab)	3 KB
evals/image-space-motion-prior/case.yaml (opens in a new tab)	474 B
evals/image-space-motion-prior/files/refs.bib (opens in a new tab)	1.4 KB
evals/image-space-motion-prior/graders/01-paper-sec-0-abstract-tex.md (opens in a new tab)	232 B
evals/image-space-motion-prior/graders/02-the-latex-project-compiles-to.md (opens in a new tab)	150 B
evals/image-space-motion-prior/graders/03-every-citation-uses-a-key.md (opens in a new tab)	182 B
evals/image-space-motion-prior/graders/04-every-number-in-the-abstract.md (opens in a new tab)	162 B
evals/image-space-motion-prior/graders/05-the-abstract-and-introduction-contain.md (opens in a new tab)	198 B
evals/image-space-motion-prior/graders/06-the-abstract-and-introduction-contain.md (opens in a new tab)	245 B
evals/image-space-motion-prior/graders/07-the-main-idea-or-finding.md (opens in a new tab)	196 B
evals/image-space-motion-prior/graders/08-the-abstract-contains-at-most.md (opens in a new tab)	209 B
evals/image-space-motion-prior/graders/09-the-introduction-contains-a-stance.md (opens in a new tab)	224 B
evals/image-space-motion-prior/graders/10-the-abstract-and-introduction-present.md (opens in a new tab)	204 B
evals/image-space-motion-prior/graders/11-the-text-conveys-why-motion.md (opens in a new tab)	174 B
evals/image-space-motion-prior/graders/12-the-results-are-stated-with.md (opens in a new tab)	151 B
evals/image-space-motion-prior/graders/13-the-introduction-mentions-interactive-dynamics.md (opens in a new tab)	163 B
evals/image-space-motion-prior/place-files.sh (opens in a new tab)	62 B
evals/image-space-motion-prior/prompt.md (opens in a new tab)	3.9 KB
evals/next-scale-autoregressive-images/case.yaml (opens in a new tab)	545 B
evals/next-scale-autoregressive-images/files/refs.bib (opens in a new tab)	1.1 KB
evals/next-scale-autoregressive-images/graders/01-paper-sec-0-abstract-tex.md (opens in a new tab)	232 B
evals/next-scale-autoregressive-images/graders/02-the-latex-project-compiles-to.md (opens in a new tab)	150 B
evals/next-scale-autoregressive-images/graders/03-every-citation-uses-a-key.md (opens in a new tab)	182 B
evals/next-scale-autoregressive-images/graders/04-every-number-in-the-abstract.md (opens in a new tab)	162 B
evals/next-scale-autoregressive-images/graders/05-the-abstract-and-introduction-contain.md (opens in a new tab)	198 B
evals/next-scale-autoregressive-images/graders/06-the-abstract-and-introduction-contain.md (opens in a new tab)	245 B
evals/next-scale-autoregressive-images/graders/07-the-main-idea-or-finding.md (opens in a new tab)	196 B
evals/next-scale-autoregressive-images/graders/08-the-abstract-contains-at-most.md (opens in a new tab)	209 B
evals/next-scale-autoregressive-images/graders/09-the-introduction-contains-a-stance.md (opens in a new tab)	224 B
evals/next-scale-autoregressive-images/graders/10-the-introduction-attributes-the-weakness.md (opens in a new tab)	232 B
evals/next-scale-autoregressive-images/graders/11-the-text-states-the-headline.md (opens in a new tab)	191 B
evals/next-scale-autoregressive-images/graders/12-the-text-mentions-llm-like.md (opens in a new tab)	111 B
evals/next-scale-autoregressive-images/graders/13-the-introduction-motivates-the-idea.md (opens in a new tab)	166 B
evals/next-scale-autoregressive-images/place-files.sh (opens in a new tab)	62 B
evals/next-scale-autoregressive-images/prompt.md (opens in a new tab)	3 KB
evals/participatory-alignment-dataset/case.yaml (opens in a new tab)	508 B
evals/participatory-alignment-dataset/files/refs.bib (opens in a new tab)	1 KB
evals/participatory-alignment-dataset/graders/01-paper-sec-0-abstract-tex.md (opens in a new tab)	232 B
evals/participatory-alignment-dataset/graders/02-the-latex-project-compiles-to.md (opens in a new tab)	150 B
evals/participatory-alignment-dataset/graders/03-every-citation-uses-a-key.md (opens in a new tab)	182 B
evals/participatory-alignment-dataset/graders/04-every-number-in-the-abstract.md (opens in a new tab)	162 B
evals/participatory-alignment-dataset/graders/05-the-abstract-and-introduction-contain.md (opens in a new tab)	198 B
evals/participatory-alignment-dataset/graders/06-the-abstract-and-introduction-contain.md (opens in a new tab)	245 B
evals/participatory-alignment-dataset/graders/07-the-main-idea-or-finding.md (opens in a new tab)	196 B
evals/participatory-alignment-dataset/graders/08-the-abstract-contains-at-most.md (opens in a new tab)	209 B
evals/participatory-alignment-dataset/graders/09-the-introduction-contains-a-stance.md (opens in a new tab)	224 B
evals/participatory-alignment-dataset/graders/10-the-introduction-frames-the-gap.md (opens in a new tab)	218 B
evals/participatory-alignment-dataset/graders/11-the-text-presents-the-dataset.md (opens in a new tab)	168 B
evals/participatory-alignment-dataset/graders/12-the-headline-scale-1-500.md (opens in a new tab)	158 B
evals/participatory-alignment-dataset/graders/13-the-text-explains-that-the.md (opens in a new tab)	196 B
evals/participatory-alignment-dataset/place-files.sh (opens in a new tab)	62 B
evals/participatory-alignment-dataset/prompt.md (opens in a new tab)	3.4 KB
evals/rubric.md (opens in a new tab)	1.8 KB
evals/score_outputs.py (opens in a new tab)	4.5 KB
evals/taylor-mode-operator-estimator/case.yaml (opens in a new tab)	496 B
evals/taylor-mode-operator-estimator/files/refs.bib (opens in a new tab)	1.5 KB
evals/taylor-mode-operator-estimator/graders/01-paper-sec-0-abstract-tex.md (opens in a new tab)	232 B
evals/taylor-mode-operator-estimator/graders/02-the-latex-project-compiles-to.md (opens in a new tab)	150 B
evals/taylor-mode-operator-estimator/graders/03-every-citation-uses-a-key.md (opens in a new tab)	182 B
evals/taylor-mode-operator-estimator/graders/04-every-number-in-the-abstract.md (opens in a new tab)	162 B
evals/taylor-mode-operator-estimator/graders/05-the-abstract-and-introduction-contain.md (opens in a new tab)	198 B
evals/taylor-mode-operator-estimator/graders/06-the-abstract-and-introduction-contain.md (opens in a new tab)	245 B
evals/taylor-mode-operator-estimator/graders/07-the-main-idea-or-finding.md (opens in a new tab)	196 B
evals/taylor-mode-operator-estimator/graders/08-the-abstract-contains-at-most.md (opens in a new tab)	209 B
evals/taylor-mode-operator-estimator/graders/09-the-introduction-contains-a-stance.md (opens in a new tab)	224 B
evals/taylor-mode-operator-estimator/graders/10-the-introduction-explains-the-cost.md (opens in a new tab)	237 B
evals/taylor-mode-operator-estimator/graders/11-the-text-states-the-key.md (opens in a new tab)	227 B
evals/taylor-mode-operator-estimator/graders/12-the-headline-results-more-than.md (opens in a new tab)	236 B
evals/taylor-mode-operator-estimator/graders/13-the-text-mentions-that-existing.md (opens in a new tab)	174 B
evals/taylor-mode-operator-estimator/place-files.sh (opens in a new tab)	62 B
evals/taylor-mode-operator-estimator/prompt.md (opens in a new tab)	2.9 KB
references/abstract.md (opens in a new tab)	5.4 KB
references/claim-calibration.md (opens in a new tab)	5.3 KB
references/corpus-profile.md (opens in a new tab)	3.6 KB
references/corpus/corpus_stats.json (opens in a new tab)	18.8 KB
references/exemplars/README.md (opens in a new tab)	2.2 KB
references/exemplars/cards/dpo.md (opens in a new tab)	4 KB
references/exemplars/cards/dreambooth.md (opens in a new tab)	4 KB
references/exemplars/cards/mip-nerf.md (opens in a new tab)	3.8 KB
references/exemplars/cards/mip-splatting.md (opens in a new tab)	4 KB
references/exemplars/cards/vggt.md (opens in a new tab)	4.3 KB
references/exemplars/moves.jsonl (opens in a new tab)	64.3 KB
references/exemplars/paragraphs.jsonl (opens in a new tab)	72.3 KB
references/exemplars/phrasebank.csv (opens in a new tab)	45.6 KB
references/experiments.md (opens in a new tab)	7.1 KB
references/figures.md (opens in a new tab)	13.1 KB
references/intake-form.md (opens in a new tab)	5.2 KB
references/introduction.md (opens in a new tab)	17.2 KB
references/latex-output.md (opens in a new tab)	3.4 KB
references/method.md (opens in a new tab)	6.7 KB
references/routing.md (opens in a new tab)	5 KB
references/style-rules.md (opens in a new tab)	10.6 KB
scripts/check_draft.py (opens in a new tab)	15.8 KB
scripts/check_figures.py (opens in a new tab)	9.1 KB
scripts/find_exemplars.py (opens in a new tab)	3.2 KB
scripts/intake_to_brief.py (opens in a new tab)	8.1 KB
scripts/style_metrics.py (opens in a new tab)	9 KB

Other Science & research skills

Same category, most repo stars first.

Skill	What it can touch	Pattern check	Licence	Updated
deep-researchProduce cited research reports from multiple web sources using firecrawl and exa MCP tools — plan sub-questions, search and deep-read sources, then synthesize findings with inline citations and confidence levels. Use when the user asks to research a topic in depth, run a deep dive or investigation, or do competitive analysis, technology evaluation, market sizing, or due diligence on a company. affaan-m/ECC Instructions only Pattern check: Nothing flaggedMITUpdated 27 Sept 2026	Instructions only	Pattern check: Nothing flagged	MIT	27 Sept 2026
healthcare-cdss-patternsClinical Decision Support System (CDSS) development patterns. Drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), alert severity classification, and integration into EMR workflows. Use when building clinical decision support — drug interaction checks, dose validation, clinical scoring, or alert severity. affaan-m/ECC Instructions only Pattern check: Nothing flaggedMITUpdated 11 Aug 2026	Instructions only	Pattern check: Nothing flagged	MIT	11 Aug 2026
clinical-case-reportStructured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds", "case summary", or "patient presentation". nexu-io/open-design Instructions only Pattern check: Nothing flaggedApache 2.0Updated 18 Aug 2026	Instructions only	Pattern check: Nothing flagged	Apache 2.0	18 Aug 2026
clinical-case-reportStructured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds", "case summary", or "patient presentation". nexu-io/open-design Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 18 Aug 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	18 Aug 2026
style-samplingMake a new episode in a proven video style - Collage Explainer, Finance Explainer, Animated Science Explainer, 3D Brand Explainer, 3D True Crime - on the person's topic. Use for "an episode of", "in the style of", "sample this style", 「用这个风格做一集」. One video to copy is reverse-any-video. heygen-com/hyperframes Runs shell commands Pattern check: Nothing flaggedApache 2.0Updated 3 Nov 2026	Runs shell commands	Pattern check: Nothing flagged	Apache 2.0	3 Nov 2026
security-research code-yeongyu/oh-my-openagent Names web addresses Pattern check: Nothing flaggedNo licenceUpdated 31 Aug 2026	Names web addresses	Pattern check: Nothing flagged	No licence	31 Aug 2026

At a glance

What it can touch

Pattern check

Install

Claude Code

Claude apps

Codex

Cursor

Copilot & VS Code

Gemini CLI

Any agent

What it can touch

Pattern check

Outside links we did not follow

Format check

SKILL.md

Files

Other Science & research skills