DietrichGebert/ponytail
Ponytail enables AI agents to generate more concise, efficient, and cost-effective code by enforcing a "lazy senior dev" methodology, prioritizing existing solutions and minimal implementation.
Awesome AI Agents › AI Assistants
Spark-To-Paper-Skills/paperjury
PaperJury is packaged as a Claude Code plugin and skill for authors preparing a LaTeX manuscript. The author states a request in plain language, for example asking whether the experiments support the claims or asking for one section to be tightened without weakening its claims, and the skill selects between direct-edit, review and automatic modes rather than requiring a fixed command. The stated division of labour is that the model reads, judges and drafts, while deterministic scripts own state management, voting rules, patch application and stopping conditions. Instead of accumulating undifferentiated reviewer feedback, each raised point is sorted into one of three outcomes. Points that can be fixed safely, such as unclear phrasing, overstated claims or awkward structure, are patched without changing the underlying result. Points that require new experiments, missing ablations, absent data or evidence that only the author can supply are handed back to the author for a scientific decision. Points where the automated reviewer has misread the paper, or is objecting to something that should not change, are marked as not established. Contested items go through a deliberation stage, and edits carrying different levels of risk get different guardrails. The output is a list of reviewer-style problems, each with supporting evidence, a location in the manuscript and the resulting verdict, together with the applied patches for author confirmation. The repository ships a dogfood sample containing before and after PDFs of a real draft plus a manually checked run report, and an accompanying arXiv paper describes the engine. The README is written primarily in Chinese with an English translation provided. The maintainers state explicitly that the tool does not replace peer review or the scientific judgement of the author and must not be used to fabricate experiments or unsupported claims. A separate Codex port is available.
https://github.com/Spark-To-Paper-Skills/paperjury
Also in AI Assistants
HKUDS/DeepTutor
DeepTutor is an AI-powered personalized learning assistant that offers interactive knowledge Q&A, visualization, practice generation, and deep research capabilities to enhance education through a comprehensive and adaptive platform.
agentscope-ai/QwenPaw
QwenPaw is a personal AI assistant framework that provides local or cloud deployment, multi-channel connectivity, skill extensibility, and multi-agent collaboration for enhanced productivity and cr...
mukul975/Anthropic-Cybersecurity-Skills
A comprehensive, open-source library of 754 structured cybersecurity skills for AI agents, mapped across five prominent industry frameworks.
googleworkspace/cli
gws is a command-line tool that dynamically interfaces with Google Workspace APIs (Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin) and includes AI agent skills for automation.
nanocoai/nanoclaw
NanoClaw is a lightweight, secure AI assistant platform that runs agents in isolated containers, providing a customizable alternative to OpenClaw with native Anthropic Claude Code integration and m...
assafelovic/gpt-researcher
GPT Researcher is an autonomous AI agent that conducts deep web and local research to generate detailed, unbiased research reports with citations.
screenpipe/screenpipe
Screenpipe transforms your computer into a personal, local, and private AI that records, searches, and automates based on all your digital activities.