AI Research Writing
Citrus-bit/Anaxa
A skill your agent uses when the user wants academic writing prompts, paper polishing workflows, translation/rewrite guidance, reviewer-style paper critique, experiment write-up help, title/caption…
CVPR / ICCV / ECCV paper formatting — activate when the user wants to submit to CVPR, ICCV, or ECCV, follow their template, or fix format issues for these computer vision conferences.
$ npx skills add nanoAgentTeam/research-claw --skill cvpr-iccv-eccv -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nanoAgentTeam/research-claw cvpr-iccv-eccv --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/nanoAgentTeam/research-claw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/config/.skills/cvpr-iccv-eccv .claude/skills/cvpr-iccv-eccv && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cvpr-iccv-eccv" agent skill from https://github.com/nanoAgentTeam/research-claw/tree/main/config/.skills/cvpr-iccv-eccv into .claude/skills/cvpr-iccv-eccv/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cvpr-iccv-eccv", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/nanoAgentTeam/research-claw/tree/main/config/.skills/cvpr-iccv-eccvType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add nanoAgentTeam/research-claw --skill cvpr-iccv-eccv -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nanoAgentTeam/research-claw cvpr-iccv-eccv --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nanoAgentTeam/research-claw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/config/.skills/cvpr-iccv-eccv .agents/skills/cvpr-iccv-eccv && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cvpr-iccv-eccv" agent skill from https://github.com/nanoAgentTeam/research-claw/tree/main/config/.skills/cvpr-iccv-eccv into .agents/skills/cvpr-iccv-eccv/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cvpr-iccv-eccv", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nanoAgentTeam/research-claw --skill cvpr-iccv-eccv -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nanoAgentTeam/research-claw cvpr-iccv-eccv --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nanoAgentTeam/research-claw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/config/.skills/cvpr-iccv-eccv .cursor/skills/cvpr-iccv-eccv && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cvpr-iccv-eccv" agent skill from https://github.com/nanoAgentTeam/research-claw/tree/main/config/.skills/cvpr-iccv-eccv into .cursor/skills/cvpr-iccv-eccv/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cvpr-iccv-eccv", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/nanoAgentTeam/research-claw.git --path config/.skills/cvpr-iccv-eccv--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add nanoAgentTeam/research-claw --skill cvpr-iccv-eccv -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nanoAgentTeam/research-claw cvpr-iccv-eccv --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nanoAgentTeam/research-claw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/config/.skills/cvpr-iccv-eccv .gemini/skills/cvpr-iccv-eccv && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cvpr-iccv-eccv" agent skill from https://github.com/nanoAgentTeam/research-claw/tree/main/config/.skills/cvpr-iccv-eccv into .gemini/skills/cvpr-iccv-eccv/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cvpr-iccv-eccv", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install nanoAgentTeam/research-claw cvpr-iccv-eccvInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add nanoAgentTeam/research-claw --skill cvpr-iccv-eccv -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nanoAgentTeam/research-claw.git skills-src && mkdir -p .github/skills && cp -r skills-src/config/.skills/cvpr-iccv-eccv .github/skills/cvpr-iccv-eccv && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cvpr-iccv-eccv" agent skill from https://github.com/nanoAgentTeam/research-claw/tree/main/config/.skills/cvpr-iccv-eccv into .github/skills/cvpr-iccv-eccv/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cvpr-iccv-eccv", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nanoAgentTeam/research-claw --skill cvpr-iccv-eccv -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nanoAgentTeam/research-claw cvpr-iccv-eccv --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nanoAgentTeam/research-claw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/config/.skills/cvpr-iccv-eccv .opencode/skills/cvpr-iccv-eccv && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cvpr-iccv-eccv" agent skill from https://github.com/nanoAgentTeam/research-claw/tree/main/config/.skills/cvpr-iccv-eccv into .opencode/skills/cvpr-iccv-eccv/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cvpr-iccv-eccv", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
cvpr-iccv-eccvCVPR / ICCV / ECCV paper formatting — activate when the user wants to submit to CVPR, ICCV, or ECCV, follow their template, or fix format issues for these computer vision conferences.
Cvpr Iccv Eccv is an agent skill from nanoAgentTeam/research-claw. CVPR / ICCV / ECCV paper formatting — activate when the user wants to submit to CVPR, ICCV, or ECCV, follow their template, or fix format issues for these computer vision conferences.
Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Computer vision and Scientific writing. The repository describes itself as: A self-hosted AI assistant for academic research — manages your papers, searches literature, tracks deadlines, and answers you on the channels you already use. The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit ce3a4ac. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
read_filewrite_filestr_replacebashlatex_compileFrom allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are latex).
From the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
overleaf.comcvpr.thecvf.comiccv.thecvf.comeccv.ecva.netspringer.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Cvpr Iccv Eccv loads about 3.2k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 1,258 words of instructions outside code blocks.
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.
The automated check found no risky patterns in SKILL.md.
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); files beside SKILL.md are not scanned.
The full file from nanoAgentTeam/research-claw at commit ce3a4ac, republished under its MIT licence (© nanoAgentTeam). 1,258 words, ~3,161 tokens.
.claude/skills/cvpr-iccv-eccv/SKILL.md (or your agent's skills folder).[SKILL: CVPR / ICCV / ECCV PAPER FORMAT]
Activate when: user mentions CVPR, ICCV, ECCV, Computer Vision and Pattern Recognition, International Conference on Computer Vision, or European Conference on Computer Vision.
⚠️ Reference only — always verify: The rules below reflect common patterns from recent years. Conference requirements (page limits, required sections, package restrictions, submission options, etc.) can change each year. Before making any formatting changes, verify all requirements against the current year's official CFP and the author kit files (sample
.tex, README, formatting guide PDF) bundled in the template download.
Note: CVPR and ICCV share nearly identical templates (both use IEEE CVPR-style). ECCV uses a different Springer LNCS-based template. Instructions are split below — read the section matching the target venue.
After this skill is activated, select the matching scenario based on user intent.
Before venue-specific template steps, also load and follow:
config/.skills/ml-paper-writing/SKILL.mdAt minimum, apply these shared references:
writing-guide.md (narrative and clarity)citation-workflow.md (verified citations; no hallucinations)reviewer-guidelines.md (reviewer-facing quality checks)checklists.md (pre-submission gates)Built-in template: None — this skill does not bundle templates. Templates must always be downloaded from official sources (see Template Download below).
This step MUST be completed before any scenario below.
submission (blind review) or camera-ready (final)..zip.zip.tex file from the downloaded kit to confirm preamble structure, package requirements, and author block format.Step 1 — Download and copy template files to project core directory (see Pre-step).
Step 2 — Read the sample .tex from the downloaded kit with read_file:
egpaper_for_review.tex (submission) or egpaper_final.tex (camera-ready)samplepaper.texStep 3 — Create main.tex using write_file:
For CVPR/ICCV:
\documentclass[10pt,twocolumn,letterpaper]{article}\usepackage{cvpr} (or \usepackage{iccv} for ICCV)\cvprfinalcopy commented out for submission\def\cvprPaperID{****} with submission system paper ID\usepackage{hyperref} (style loads it internally)For ECCV:
\documentclass[runningheads]{llncs}\author{} + \institute{} (LNCS syntax)Step 4 — Set up bibliography and run latex_compile.
Step 1 — Read current main.tex with read_file.
Step 2 — Read the downloaded sample .tex with read_file as migration reference.
Step 3 — Copy style files using bash (style files only — do NOT overwrite paper content).
Step 4 — Update preamble using str_replace:
For CVPR/ICCV:
\documentclass[10pt,twocolumn,letterpaper]{article}\usepackage{cvpr} (or iccv)geometry, hyperref, multicol)\cvprfinalcopy for submissionFor ECCV:
\documentclass[runningheads]{llncs}article-class-specific commands\author{} + \institute{})Step 5 — Anonymize for submission (remove author names/affiliations).
Step 6 — Fix bibliography setup (see Bibliography section below).
Step 7 — Run latex_compile and resolve remaining issues.
Step 1 — Run latex_compile to capture errors/warnings.
Step 2 — Read preamble in main.tex and compare with downloaded sample .tex.
Step 3 — Check common failures (see Common Pitfalls below):
.sty/.cls/.bst in project roothyperref loaded manually (CVPR/ICCV load it internally)\cvprfinalcopy left uncommented at submissiongeometry package conflicting with stylearticle instead of llncs)Step 4 — Apply fixes with str_replace.
Step 5 — Re-run latex_compile until clean.
Step 1 — Read full main.tex with read_file.
Step 2 — Verify checklist items:
For CVPR/ICCV:
\documentclass[10pt,twocolumn,letterpaper]{article} is used\cvprfinalcopy is commented out for submission\cvprPaperID is set correctly\usepackage{hyperref} (style loads it)geometry package{\small ...}For ECCV:
\documentclass[runningheads]{llncs} is used\bibliographystyle{splncs04} is usedStep 3 — Report and fix issues one by one with str_replace.
Step 4 — Run final latex_compile verification.
⚠️ Reference only — always verify: The rules below reflect common patterns from recent years. Always prioritize the target year's CFP and author kit over defaults in this skill.
CVPR:
.zip from the official site (URL changes each year)ICCV:
iccv.sty and iccv.bstECCV:
Unzip into the project root (same directory as main.tex):
CVPR/ICCV:
project/
├── main.tex ← your paper
├── cvpr.sty ← style file (or iccv.sty for ICCV)
├── cvpr.bst ← bibliography style (or iccv.bst)
├── egpaper_for_review.tex ← submission template — READ THIS
└── egpaper_final.tex ← camera-ready template — read for final versionECCV (Springer LNCS):
project/
├── main.tex
├── llncs.cls ← Springer LNCS class — REQUIRED at root
├── splncs04.bst ← bibliography style
└── samplepaper.tex ← sample paper — READ THISCVPR/ICCV:
egpaper_for_review.tex — submission template with all preamble settings, author anonymization, figure/table examples, and bibliography setupegpaper_final.tex — camera-ready template showing how to add author info and paper IDECCV:
samplepaper.tex — Springer sample paper with all Springer-specific macros and format rulesllncs.cls comments — for edge cases not covered in the sample\documentclass[10pt,twocolumn,letterpaper]{article}
\usepackage{cvpr} % or \usepackage{iccv} for ICCV
\usepackage{times}
\usepackage{epsfig}
\usepackage{graphicx}
\usepackage{amsmath}
\usepackage{amssymb}
% Include OTHER packages BEFORE hyperref:
% \usepackage{...}
% For camera-ready ONLY — uncomment AFTER acceptance:
% \cvprfinalcopy
\def\cvprPaperID{****} % ← Replace **** with your paper ID from submission system
\def\httilde{\mbox{\tt\raisebox{-.5ex}{\symbol{126}}}}Rule: Keep % \cvprfinalcopy commented out for blind review. Uncomment and set \cvprPaperID to your actual paper ID for camera-ready.
\documentclass[runningheads]{llncs}
\usepackage{graphicx}
\usepackage{amsmath}
\usepackage[T1]{fontenc}
% For ECCV 2024+ (check the specific year's guidelines):
\usepackage[misc]{ifsym} % or other venue-specific packages per CFPECCV's LNCS format is fundamentally different from CVPR/ICCV — single column, numbered sections, different author macro syntax.
| Item | Requirement |
|---|---|
| Page limit | Typically 8 pages content + unlimited references — verify at https://cvpr.thecvf.com / https://iccv.thecvf.com current year CFP |
| Layout | Two-column, 10pt, letter paper |
| Anonymous | Blind review — no author names/affiliations in submission; paper ID shown instead |
| Camera-ready | Add \cvprfinalcopy, set \cvprPaperID, add author info |
| Supplementary | Separate PDF — verify page/size limit at current year CFP |
| Item | Requirement |
|---|---|
| Page limit | Typically 14 pages total (content + references combined) — verify at https://eccv.ecva.net current year CFP |
| Layout | Single column, A4 paper |
| Font | Computer Modern (default LaTeX) or Times if specified |
| Anonymous | Double-blind; remove author names |
.sty or .bst: Both must be in the project root. cvpr.sty and cvpr.bst (or iccv.sty/iccv.bst) must be placed there.\cvprfinalcopy left uncommented at submission: If this is active, the paper is not anonymized — the header shows the paper ID but the submission is not blind. Use egpaper_for_review.tex as your base, which has it commented out.hyperref loading order: The CVPR style loads hyperref at the end of the preamble. Do NOT add \usepackage{hyperref} yourself — it causes "option clash" errors. Any packages that interact with hyperref (e.g., cleveref) must be loaded after \usepackage{cvpr}.figure* and table* environments for full-width floats spanning both columns.geometry package conflict: Do not use geometry — CVPR sets margins via the document class options.article class: Do not use \documentclass{article} for ECCV. Use \documentclass[runningheads]{llncs}.\author{} + \institute{} (LNCS syntax), not standard LaTeX \author{} + \affil{}.CVPR / ICCV:
{\small
\bibliographystyle{ieee_fullname} % or cvpr.bst / iccv.bst
\bibliography{references}
}Wrap the bibliography in {\small ...} to match the template. Some years use ieee_fullname.bst; check egpaper_for_review.tex for the exact .bst name used.
ECCV (LNCS):
\bibliographystyle{splncs04} % Springer's official .bst
\bibliography{references}© nanoAgentTeam, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in config/.skills/cvpr-iccv-eccv of nanoAgentTeam/research-claw.
Open the folder on GitHubat commit ce3a4ac
Cvpr Iccv Eccv next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cvpr Iccv Eccv this skillnanoAgentTeam/research-claw | 293 | — | ~3.2k | Automated safety check: Pass | MIT | |
| AI Research WritingCitrus-bit/Anaxa | 120 | — | ~886 | Automated safety check: Pass | MIT | |
| Matlab Process Imagesmatlab/matlab-agentic-toolkit | 1.1k | — | ~3.7k | Automated safety check: Pass | Custom licence | |
| Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs | 13k | 9 repos | ~3.3k | Automated safety check: Pass | MIT | |
| CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Yolo Master AgentTencent/YOLO-Master | 742 | — | ~755 | Automated safety check: Pass | AGPL-3.0 |
Citrus-bit/Anaxa
A skill your agent uses when the user wants academic writing prompts, paper polishing workflows, translation/rewrite guidance, reviewer-style paper critique, experiment write-up help, title/caption…
matlab/matlab-agentic-toolkit
Load this first for any task involving images, pictures, photos, scans, frames, volumes, or visual data — including reading, writing, filtering, enhancing, denoising, sharpening, deblurring…
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
Orchestra-Research/AI-Research-SKILLs
Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.
Tencent/YOLO-Master
A skill your agent uses when the user wants to run a YOLO-Master task (train/val/predict/track/export/benchmark) or use the Agent Skill dispatcher.
jjyaoao/HelloAgents
Implement specialized video understanding capabilities using the z-ai-web-dev-sdk.
nanoAgentTeam/research-claw
AAAI paper formatting — activate when the user wants AAAI template setup, migration, or formatting/compilation fixes.
nanoAgentTeam/research-claw
ACL-family venue paper formatting (ACL, EMNLP, NAACL, EACL, AACL, COLING, ARR, Findings) — activate when the user wants any ACL-series template setup, migration, or format fixes.
nanoAgentTeam/research-claw
COLM (Conference on Language Modeling) paper formatting — activate when the user wants COLM template setup, migration, or formatting/compilation fixes.
nanoAgentTeam/research-claw
Academic venue paper discovery — activate when you need to find papers accepted at specific conferences or journals (ACL, EMNLP, NeurIPS, ICML, ICLR, MLSys, etc.), analyze venue acceptance…
nanoAgentTeam/research-claw
ICLR (International Conference on Learning Representations) paper formatting — activate when the user wants to submit to ICLR, follow ICLR template, or fix ICLR format issues.
nanoAgentTeam/research-claw
ICML (International Conference on Machine Learning) paper formatting — activate when the user wants to submit to ICML, follow ICML template, or fix ICML format issues.
Categories
CVPR / ICCV / ECCV paper formatting — activate when the user wants to submit to CVPR, ICCV, or ECCV, follow their template, or fix format issues for these computer vision conferences. Cvpr Iccv Eccv is an agent skill from nanoAgentTeam/research-claw. CVPR / ICCV / ECCV paper formatting — activate when the user wants to submit to CVPR, ICCV, or ECCV, follow their template, or fix format issues for these computer vision conferences.
Cvpr Iccv Eccv fits situations like: wants to submit to CVPR; follow their template; fix format issues for these computer vision conferences.
Run `npx skills add nanoAgentTeam/research-claw --skill cvpr-iccv-eccv -a claude-code`. Or copy the skill folder (config/.skills/cvpr-iccv-eccv in nanoAgentTeam/research-claw) into .claude/skills/cvpr-iccv-eccv in your project. Claude Code loads it when a task matches its description.
Run `npx skills add nanoAgentTeam/research-claw --skill cvpr-iccv-eccv -a codex`. Or copy the skill folder (config/.skills/cvpr-iccv-eccv in nanoAgentTeam/research-claw) into .agents/skills/cvpr-iccv-eccv in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nanoAgentTeam/research-claw --skill cvpr-iccv-eccv -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cvpr-iccv-eccv, .gemini/skills/cvpr-iccv-eccv, .github/skills/cvpr-iccv-eccv and .opencode/skills/cvpr-iccv-eccv in your project.
SKILL.md names no scripts, command-line tools or credentials: Cvpr Iccv Eccv is instructions for the agent only. Its frontmatter pre-approves these tools: read_file, write_file, str_replace, bash, latex_compile.
SKILL.md names 5 domains. As links in the text: overleaf.com, cvpr.thecvf.com, iccv.thecvf.com, eccv.ecva.net and springer.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Cvpr Iccv Eccv is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Cvpr Iccv Eccv: AI Research Writing (Citrus-bit/Anaxa, 120 stars), Matlab Process Images (matlab/matlab-agentic-toolkit, 1.1k stars), Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars) and CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
nanoAgentTeam (a GitHub organization) maintains it in nanoAgentTeam/research-claw, which has 293 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on June 8, 2026.
Source: nanoAgentTeam/research-claw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.