CLIP Image-Text Matching
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.
Design and execute computational social science analyses across 11 modules: text-as-data/NLP (STM, BERTopic, Wordfish, BERT, conText embedding regression, LLM annotation + DSL bias correction…
Install Scholar Compute
$ npx skills add joshzyj/open-scholar-skill --skill scholar-compute -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install joshzyj/open-scholar-skill scholar-compute --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/joshzyj/open-scholar-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/scholar-compute .claude/skills/scholar-compute && 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 "scholar-compute" agent skill from https://github.com/joshzyj/open-scholar-skill/tree/main/.claude/skills/scholar-compute into .claude/skills/scholar-compute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scholar-compute", 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/joshzyj/open-scholar-skill/tree/main/.claude/skills/scholar-computeType 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 joshzyj/open-scholar-skill --skill scholar-compute -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install joshzyj/open-scholar-skill scholar-compute --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/joshzyj/open-scholar-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/scholar-compute .agents/skills/scholar-compute && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "scholar-compute" agent skill from https://github.com/joshzyj/open-scholar-skill/tree/main/.claude/skills/scholar-compute into .agents/skills/scholar-compute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scholar-compute", 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 joshzyj/open-scholar-skill --skill scholar-compute -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install joshzyj/open-scholar-skill scholar-compute --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/joshzyj/open-scholar-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/scholar-compute .cursor/skills/scholar-compute && 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 "scholar-compute" agent skill from https://github.com/joshzyj/open-scholar-skill/tree/main/.claude/skills/scholar-compute into .cursor/skills/scholar-compute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scholar-compute", 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/joshzyj/open-scholar-skill.git --path .claude/skills/scholar-compute--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 joshzyj/open-scholar-skill --skill scholar-compute -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install joshzyj/open-scholar-skill scholar-compute --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/joshzyj/open-scholar-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/scholar-compute .gemini/skills/scholar-compute && 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 "scholar-compute" agent skill from https://github.com/joshzyj/open-scholar-skill/tree/main/.claude/skills/scholar-compute into .gemini/skills/scholar-compute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scholar-compute", 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 joshzyj/open-scholar-skill scholar-computeInstalls 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 joshzyj/open-scholar-skill --skill scholar-compute -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/joshzyj/open-scholar-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/scholar-compute .github/skills/scholar-compute && 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 "scholar-compute" agent skill from https://github.com/joshzyj/open-scholar-skill/tree/main/.claude/skills/scholar-compute into .github/skills/scholar-compute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scholar-compute", 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 joshzyj/open-scholar-skill --skill scholar-compute -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install joshzyj/open-scholar-skill scholar-compute --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/joshzyj/open-scholar-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/scholar-compute .opencode/skills/scholar-compute && 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 "scholar-compute" agent skill from https://github.com/joshzyj/open-scholar-skill/tree/main/.claude/skills/scholar-compute into .opencode/skills/scholar-compute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scholar-compute", 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.
Facts
- Skill name
scholar-compute- GitHub stars
- 168
- Token cost
- ~15k tokens
- SKILL.md length
- 4,632 words
- Files
- 50 (incl. references)
- Skills in repo
- 30
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Design and execute computational social science analyses across 11 modules: text-as-data/NLP (STM, BERTopic, Wordfish, BERT, conText embedding regression, LLM annotation + DSL bias correction…
- Works in 4 steps: Consolidate early. Write the module's… → Review: load and execute… → Fix loop:… → …
- Tasks that involve Test data and fixtures
- SKILL.md covers Arguments and Module Routing, MODULE 0: Setup (All Modules), MODULE 0.5: Data Safety Gate… and MODULE 0.7: Pre-Scale Review…, plus 5 more sections
- Calls bash, node and python3
What it does
Scholar Compute is an agent skill from joshzyj/open-scholar-skill. Design and execute computational social science analyses across 11 modules: text-as-data/NLP (STM, BERTopic, Wordfish, BERT, conText embedding regression, LLM annotation + DSL bias correction, XLM-R/mBERT); ML (supervised, Double ML, Causal Forests, Bayesian brms/Stan, conformal prediction); network analysis (ERGMs, SAOMs, relational event models, GNN via PyTorch Geometric); agent-based modeling (Mesa 3.x, NetLogo, LLM agents, ODD, SALib); computer vision (DINOv2, CLIP, ViT, multimodal LLMs, VideoMAE); LLM…
Its SKILL.md is about 15k tokens, which your agent loads only when the skill is triggered. The skill folder holds 52 other files, including reference files (for example `references/computer-vision.md`, `references/ml-methods.md` and `references/module-01-nlp.md`).
It sits in AI & LLM Engineering, covering Test data and fixtures, Geospatial analysis and Embeddings. It works with PyTorch. The repository describes itself as: Open scholar skill, a claude code plugin, for academic research.
When your agent uses it
- Tasks that involve Test data and fixtures
- Tasks that involve Geospatial analysis
- Tasks that involve Embeddings
Example prompts
- “/scholar-compute”
Requirements
- Docker
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Consolidate early. Write the module's planned pipeline into its self-contained script(s) NOW (the Script Archive Protocol's "After Each…
- Review: load and execute scholar-code-review in pre-execution mode, fast 3 subset (statistics data-handling correctness) — 3 SEPARATE…
- Fix loop: _shared/code-review-fix-loop.md on CRITICAL findings (max 2 iterations; re-review per scholar-code-review Step 6).
- Gate, then execute the reviewed scripts directly
What it can do on your machine
Read from SKILL.md and the folder at commit 6e5ac8e. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
bashnodepython3claude
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Scholar Compute loads about 15k tokens when it runs, and up to ~134k if it reads all its reference files. Until then it costs about 258 tokens; SKILL.md has 4,632 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.
Safety
Auto-check passed
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.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 4,632 words (~14,578 tokens).
“You are an expert computational social scientist. You run executable analyses, validate results, and produce publication-quality outputs with prose ready for the Methods and Results sections. You meet the reproducibility standards of Nature Computational Science, Science Advances, and top sociology…”
- name
- scholar-compute
- tools
- Read, Bash, Write, WebSearch, Agent
- argument-hint
- [text|network|ml|abm|reproduce|spatial|bayesian|dsl|audio|life2vec] [description of data and research question]
- user-invocable
- true
Files
SKILL.md and 49 other files (references) in .claude/skills/scholar-compute of joshzyj/open-scholar-skill.
- SKILL.md
- references/computer-vision.md
- references/ml-methods.md
- references/module-01-nlp.md
- references/module-02-ml.md
- references/module-03-network.md
- references/module-04-abm.md
- references/module-05-reproducibility.md
- references/module-06-cv.md
- references/module-07-llm-analysis.md
- references/module-08-synthetic-data.md
- references/module-09-geospatial.md
- references/module-10-audio.md
- references/module-11-life2vec.md
- references/network-analysis.md
- references/nlp-pipeline.md
- references/prompt-optimization-demo/README.md
- references/prompt-optimization-demo/dspy-demo/CODEBOOK.md
- … and 32 more
Open the folder on GitHubat commit 6e5ac8e
Compare with similar skills
Scholar Compute 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 |
|---|---|---|---|---|---|---|
| Scholar Compute this skilljoshzyj/open-scholar-skill | 168 | — | ~15k | Automated safety check: Pass | Custom licence | |
| CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs | 13k | 7 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Sentence Transformers EmbeddingsOrchestra-Research/AI-Research-SKILLs | 13k | 2 repos | ~1.6k | Automated safety check: Pass | MIT | |
| Video Camera DemosVectorSpaceLab/AREX-Skill | 330 | — | ~626 | Automated safety check: Pass | Apache-2.0 | |
| Deep Learning NLPDrchronx/ai-agent-research-starter-kit | 137 | — | ~516 | Automated safety check: Pass | Custom licence | |
| Text Analysis BasicDrchronx/ai-agent-research-starter-kit | 137 | — | ~737 | Automated safety check: Pass | Custom licence |
Similar skills
Sentence Transformers Embeddings
Orchestra-Research/AI-Research-SKILLs
Generates text embeddings locally with the sentence-transformers library for RAG, semantic search, clustering and similarity, with model picks for general, multilingual and legal text.
Video Camera Demos
VectorSpaceLab/AREX-Skill
Guide safe video-file, webcam, and optional half-precision demo use for pytorch-yolo-v3.
Deep Learning NLP
Drchronx/ai-agent-research-starter-kit
Paddle-based deep learning workflows from the course materials, including DNN/RNN text-style baselines and the CNN/LeNet image classification case using folder-labeled digit images.
Text Analysis Basic
Drchronx/ai-agent-research-starter-kit
Basic Chinese NLP and text analysis workflows for PDF text/table extraction, jieba tokenization, word and sentence frequency, word clouds, TF-IDF, Word2Vec, sentence embeddings, and text similarity.
AI ML Skills
wentorai/research-plugins
27 ai & machine learning skills. An agent skill from wentorai/research-plugins.
More from joshzyj/open-scholar-skill
All 30 skills in this repoScholar Annotate
joshzyj/open-scholar-skill
Turn unstructured text into validated, structured variables at corpus scale with LLMs: codebook design, dev/gold-set construction, DSPy prompt optimization, a hard reliability gate (Cohen κ ≥ 0.70)…
Scholar Auto Research
joshzyj/open-scholar-skill
Stable, deterministic social-science research-paper pipeline from idea or data to verified manuscript, citations, replication package, and final md/docx/tex/pdf outputs.
Scholar RAG
joshzyj/open-scholar-skill
Build and query a local vector database + GraphRAG over your entire reference library (Zotero or a PDF folder) for literature review.
Scholar Causal
joshzyj/open-scholar-skill
Comprehensive causal inference toolkit for social science research.
Scholar Data
joshzyj/open-scholar-skill
Comprehensive open data directory (100+ datasets across 14 categories) with auto-fetch capability, plus data collection instrument design, variable dictionaries, data management, IRB materials, and…
Scholar Eda
joshzyj/open-scholar-skill
Conduct exploratory data analysis (EDA) before hypothesis testing.
Related
Works with
Categories
Questions about Scholar Compute
What does Scholar Compute do?
Design and execute computational social science analyses across 11 modules: text-as-data/NLP (STM, BERTopic, Wordfish, BERT, conText embedding regression, LLM annotation + DSL bias correction…. Scholar Compute is an agent skill from joshzyj/open-scholar-skill.
When should I use Scholar Compute?
Scholar Compute fits situations like: tasks that involve Test data and fixtures; tasks that involve Geospatial analysis; tasks that involve Embeddings.
How do I install Scholar Compute in Claude Code?
Run `npx skills add joshzyj/open-scholar-skill --skill scholar-compute -a claude-code`. Or copy the skill folder (.claude/skills/scholar-compute in joshzyj/open-scholar-skill) into .claude/skills/scholar-compute in your project. Claude Code loads it when a task matches its description.
How do I install Scholar Compute in Codex?
Run `npx skills add joshzyj/open-scholar-skill --skill scholar-compute -a codex`. Or copy the skill folder (.claude/skills/scholar-compute in joshzyj/open-scholar-skill) into .agents/skills/scholar-compute in your project. Codex loads it when a task matches its description.
Can I use Scholar Compute in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add joshzyj/open-scholar-skill --skill scholar-compute -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scholar-compute, .gemini/skills/scholar-compute, .github/skills/scholar-compute and .opencode/skills/scholar-compute in your project.
What does Scholar Compute need to run?
Going by SKILL.md and its folder, Scholar Compute needs the command-line tools its instructions call (bash, node, python3 and claude). Our summary lists: Docker.
Does Scholar Compute access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Scholar Compute safe to install?
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.
What licence does Scholar Compute use?
Scholar Compute has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Scholar Compute use?
About 15k tokens (SKILL.md is roughly 58k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 119k tokens, read only when the agent opens those files.
What are the alternatives to Scholar Compute?
Skills that share tags, products or a category with Scholar Compute: CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars), Sentence Transformers Embeddings (Orchestra-Research/AI-Research-SKILLs, 13k stars), Video Camera Demos (VectorSpaceLab/AREX-Skill, 330 stars) and Deep Learning NLP (Drchronx/ai-agent-research-starter-kit, 137 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Scholar Compute?
joshzyj (a GitHub user) maintains it in joshzyj/open-scholar-skill, which has 168 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on September 18, 2026.
Source: joshzyj/open-scholar-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.