575GitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “vision-llm”
33–43 / 43
More filters · 1
Candidates in this shortlist, not the full registry. GitHub stars belong to repositories, not individual skills.
Results: 43
Bugbug
mozilla
Platform for Machine Learning projects on Software Engineering
CodingSkill source unconfirmed
565GitHub
Claw Compactor
open-compress
14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
CodingSkill source unconfirmed
2.2KGitHub
Pr Af
Agent-Field
AI-Native multi-agent Code Reviewer Built on AgentField
CodingSkill source unconfirmed
442GitHub
Lowfat
zdk
lowfat - slim your command output. strips noise, saves tokens.
CodingSkill source unconfirmed
535GitHub
365GitHub
open-code-review-delegate
alibaba
Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only…
22.1KGitHub
run-load-test
omnigent-ai
Run the Omnigent load test and produce a results file explaining the latencies. Load when the user wants to load-test / stress-test / benchmark Omnigent under concurrenc…
9.6KGitHub
Honey For Devs
Green-PT
Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, less prose, and denser agent-to-…
211GitHub
Agent Tools
kairyou
Reusable Agent Skills, plus integrations (statusline, provider usage, vision) that install into Codex, Claude Code, and opencode.
159GitHub
VTCode
vinhnx
VT Code is an open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient…
CodingSkill source unconfirmed
694GitHub