Agentic Harness Engineering
china-qijizhifeng
Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7%…
OPENAGENTSKILL / DIRECTORY
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
17–32 / 32
Candidates in this shortlist, not the full registry. GitHub stars belong to repositories, not individual skills.
Results: 32
china-qijizhifeng
Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7%…
OWASP
The OWASP Mobile Application Security Testing Guide (MASTG) is a comprehensive manual for mobile app security testing and reverse engineering. It describes technical pro…
Konloch
A Java 8+ Jar & Android APK Reverse Engineering Suite (Decompiler, Editor, Debugger & More)
kenn-io
Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 20 other agents.
langfuse
Agent Skills for Langfuse, the open source LLM engineering platform for tracing, prompt management, and evaluation
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…
lennney
Keep Codex from adding unneeded modules, subagents, dependencies, and hashes to small tasks.
Jeffallan
Creates Dockerfiles, configures CI/CD pipelines, writes Kubernetes manifests, and generates Terraform/Pulumi infrastructure templates. Handles deployment automation, Git…
dotnet
Simulate API failures, throttling, and chaos — all from your command line.
mozilla
Platform for Machine Learning projects on Software Engineering
Agent-Field
AI-Native multi-agent Code Reviewer Built on AgentField
alibaba
An Alibaba open-source multi-language benchmark for evaluating LLMs in repository-level automatic code review, featuring an AI-assisted and expert-verified dataset.
datacurve-ai
Measuring frontier coding agents on original, long-horizon engineering tasks
alinaqi
What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center