SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

agent-vision-toolkitAnionex/agent-vision-toolkit

Adds image-understanding capability to text-only LLMs and coding agents so they can read screenshots and the text and vi…

No ratings yet Rate this skill
Stars1.2k
Forks49
Watchers1.2k
Open Issues8

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/Anionex/agent-vision-toolkit.git

OverviewOverview

Key Features

Adds image-understanding capability to text-only LLMs and coding agents so they can read screenshots and the text and visuals inside images. Key capabilities include: 1. Vision tool CLIs: provides multiple directly callable vision CLIs that send images to a vision model and return structured results, giving text-only models visual input without modification; 2. Skill packaging and seamless integration: ships a skill instruction file that teaches agents when and with which parameters to call these CLIs, and supports transpiled integration into coding agents such as Claude Code, Codex and OpenCode, making vision a regular agent tool; 3. Proxy-first invocation: a built-in --proxy-first mode routes requests to the vision model through a proxy first, bypassing direct-connection limits and unifying authentication and egress.

Use Cases

letting text-only models analyze UI screenshots and design mockups, agents reading error screenshots or charts, coding agents inspecting rendered pages during development, and calling vision models in restricted network environments.

Target Roles

AI / Algorithm Engineer, Full-stack / Indie Developer, Test / QA Engineer, Product Manager (PM).

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID937
Data sourceGitHub
RepositoryAnionex/agent-vision-toolkit
CategoryAI & Agent Skills / Multimodal & Vision
Primary languagePython
LicenseMIT License
Default branchmain
GitHub repository ID1319174653
Node IDR_kgDOTqEB_Q
Rank#649 (position within the source ranking)
Site-wide popularity rank#740 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

05001k1.5k2026-09-292026-10-112026-09-29 · 1,2182026-10-11 · 1,223
  • Now1,223
  • Previous point · 09-29 1,218
  • vs previous point +5
  • 2 data points 12 days
02040602026-09-292026-10-112026-09-29 · 482026-10-11 · 49
  • Now49
  • Previous point · 09-29 48
  • vs previous point +1
  • 2 data points 12 days

TimelineTimeline

Repository created2026-08-01 10:00:133 months ago
Data last updated2026-10-26 12:01:3422 days ago
Last commit2026-10-08 02:25:031 months ago

CommitLatest commit

Committed by Anionex. Update Category: Bug Fixes & Stability Improvements. Commit details: Merge pull request #43 from Anionex/fix/detect-fail-on-empty. This update resolves known runtime errors and enhances system reliability.

1384ef4 Anionex 2026-10-08

Next stepsNext steps