GitHub Trending Weekly

GitHub Repo Briefing

Twelve weekly trending repositories, summarized by what they do and how to test them
May 30, 2026
Issue 06
01
Creative Systems

MoneyPrinterTurbo

harry0703/MoneyPrinterTurbo

A Chinese and English tool that turns a topic or keyword into a short video with a script, images, subtitles, music, and generated voice.

71,432
Stars total / Python
11,147 stars this week

A first test

Generate one private test video from a factual topic. Check each claim, image license, voice, and subtitle timing before publishing or selling the result.

02
Agent Ops

Understand-Anything

Egonex-AI/Understand-Anything

A coding-agent plugin that analyzes a repository into an interactive knowledge graph, dashboard, and searchable explanations.

45,506
Stars total / TypeScript
26,685 stars this week

A first test

Install it in a disposable clone and run /understand. Compare one graph relationship with the source code, then use /understand-diff before accepting a change.

03
Open Source

ai-engineering-from-scratch

rohitg00/ai-engineering-from-scratch

A hands-on course that teaches AI engineering by building and shipping small projects with an agent as a tutor.

24,979
Stars total / Python
13,139 stars this week

A first test

Install its skills and run /start-learning for one topic. Make the smallest exercise yourself, run its test, and record what you changed before asking the agent for the next lesson.

04
Agent Ops

knowledge-work-plugins

anthropics/knowledge-work-plugins

A collection of plugins for knowledge-work tasks in Claude Cowork, with commands and workflows for roles such as research, writing, and analysis.

18,172
Stars total / Python
5,586 stars this week

A first test

Install one role-specific plugin and run it on a public source. Check the generated files and tool permissions, then remove commands that do not fit your actual workflow.

05
Agent Ops

codegraph

colbymchenry/codegraph

A local code knowledge graph that indexes a repository, syncs after code changes, and serves context to coding agents through CLI and MCP clients.

34,030
Stars total / TypeScript
17,309 stars this week

A first test

Run codegraph init in a disposable clone and index one module. Ask for a caller list, compare it with the language tools, and check what files the agent can read before enabling edits.

06
Agent Ops

stop-slop

hardikpandya/stop-slop

A writing skill that identifies common AI wording, repeated structures, and weak transitions so an agent can revise prose into clearer human language.

7,284
Stars total / None
3,018 stars this week

A first test

Run it on one paragraph you wrote and compare the original with the revision. Keep only changes that improve meaning, then add a fact check for every new claim.

07
Security

Anthropic-Cybersecurity-Skills

mukul975/Anthropic-Cybersecurity-Skills

A collection of structured cybersecurity skills mapped to MITRE ATT&CK, NIST CSF, MITRE ATLAS, D3FEND, NIST AI RMF, and MITRE F3.

12,380
Stars total / Python
5,241 stars this week

A first test

Install one skill and use it on a local lab finding. Check the mapped framework control and reproduce the finding yourself; use it only for authorised security work.

08
Agent Ops

taste-skill

Leonxlnx/taste-skill

A design-review skill for agent workflows that covers layout, typography, motion, image use, and checks for generic or repetitive interface output.

28,869
Stars total / JavaScript
8,999 stars this week

A first test

Install it and review one existing screen. Ask for three concrete changes, implement one, and compare the result at desktop and mobile widths before keeping the skill.

09
Open Source

markitdown

microsoft/markitdown

A Python tool that converts office files, PDFs, images, audio, HTML, and other formats into Markdown while preserving useful document structure.

131,380
Stars total / Python
4,810 stars this week

A first test

Install it and convert one sample DOCX and PDF. Compare headings, tables, links, and missing content with the originals before using the Markdown for search or analysis.

10
Agent Ops

claude-plugins-official

anthropics/claude-plugins-official

Anthropic's maintained directory of Claude Code plugins, including plugin manifests, skills, hooks, commands, and agent integrations.

28,701
Stars total / Python
4,858 stars this week

A first test

Choose one plugin from its manifest, install it in a test project, and read every hook it enables. Run one command before allowing it to edit files or call external services.

11
Security

ECC

affaan-m/ECC

A collection of engineering skills, memory, security checks, research-first workflows, and performance guidance for Claude Code, Codex, OpenCode, and Cursor.

199,038
Stars total / JavaScript
10,239 stars this week

A first test

Install one workflow in a disposable repository and run it on a small issue. Check the generated plan, tests, and permission requests before adding the full collection.

12
Open Source

plugins

cursor/plugins

Cursor's plugin specification and a set of official plugins that package skills, commands, agents, and integrations for the Cursor editor.

1,389
Stars total / TypeScript
632 stars this week

A first test

Read one plugin manifest and install it in a test project. Run its smallest command, inspect file and network access, and keep only the pieces that match your workflow.

End of Issue
Check the links. Test one repo.
GitHub Trending Weekly / Issue 06
Generated by Codex from SnailDev github-hot-hub weekly archive: https://raw.githubusercontent.com/SnailDev/github-hot-hub/main/archives/2026-05-30.md