Agentic skills for Claude Code and Codex, built from published social-science methods sources. Covers experimental design, computational text analysis, manuscript QA, and transparent reporting.
Source
GitHub
Language
Markdown
Last activity
Oct 22, 2026
Stars69Measured · Oct 23, 2026
Momentum22.67 days · Measured · +2.99% relative change
Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it tells you. Deterministic-first, tool-agnostic.
Source
GitHub
Language
Python
Last activity
Sep 21, 2026
Stars20Measured · Oct 23, 2026
Momentum22.67 days · Measured · +5.26% relative change
Governed multi-agent SDLC pipeline for Claude Code and Qwen Code — plan → adversarial plan review → proven-red TDD → security scan → PR, with tamper-evident evidence at every step. Azure DevOps, Jira, GitHub, GitLab, Zoho, and local-markdown providers. Language-agnostic, discovery-driven.
Source
GitHub
Language
Python
Last activity
Aug 27, 2026
Stars20Measured · Oct 23, 2026
Momentum22.67 days · Measured · +5.26% relative change
This repository demonstrates how to use Claude Code to do real engineering work, not just writing code. 本项目是极客时间专栏 《Claude Code 工程化实战》 的官方配套示例仓库,目标就是: 👉 把 Claude Code 从“对话式编码工具”,变成 可设计、可复用、可治理的工程系统。
Source
GitHub
Language
JavaScript
Last activity
Jul 23, 2026
Stars1,144Measured · Oct 23, 2026
Momentum22.57 days · Measured · +0.53% relative change