← All skills

blip-2-vision-language

75 / 100 · Review before installing

Check before installing. Some of what it can do is expected: a media skill usually calls an AI service over the internet.

By hashgraph-online/awesome-codex-plugins (GitHub) · media · 1,573 stars · scanned at commit 70b6a3a

Explains how to use Salesforce BLIP-2 (Q-Former bridging a frozen image encoder and an LLM such as OPT or FlanT5) through HuggingFace Transformers and LAVIS for image captioning, visual question answering, image-text matching, and feature extraction. Use when generating captions for images, building a VQA system, doing zero-shot image-text understanding without task-specific training, matching or retrieving images against text, or fitting a BLIP-2 model into limited GPU memory with INT8/INT4 qu…

Works with any agent that supports SKILL.md skills.

What this skill can do

Safer alternatives

Low-risk skills in the same category (media) that look related. Check that one does what you need.

• 100 Low riskazure-ai-vision-imageanalysis-javamicrosoft/skills · 3,193 stars
• 95 Low risksenior-computer-visionCongDon1207/AGENTS.md · 18 stars
• 97 Low riskconfiguring-visionoxbshw/watch-skill · 577 stars

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'blip-2-vision-language' ] || [ -L ~/.agents/skills/'blip-2-vision-language' ]; then echo 'A skill folder named blip-2-vision-language already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/hashgraph-online/awesome-codex-plugins' "$d" && git -C "$d" checkout --quiet '70b6a3a3a7c774671e45af646306e1448baf0511' -- 'plugins/KalarisLabs/research-agent-skills/skills/blip-2-vision-language' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/KalarisLabs/research-agent-skills/skills/blip-2-vision-language' ~/.agents/skills/'blip-2-vision-language' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'blip-2-vision-language' ~/.claude/skills/'blip-2-vision-language' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for hashgraph-online/awesome-codex-plugins shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/hashgraph-online/awesome-codex-plugins.svg)](https://zalavijaysinh.github.io/skilltrust/repos/hashgraph-online/awesome-codex-plugins/)

Score history