Tag
Recommend 6 top AI video production plugins and skills for 2026, installable via AI Agents like Claude Code and Cursor, no subscription to 剪映SVIP needed.
Startup Founder Skills is an open-source project that organizes 50 common repetitive tasks for founders into AI skill packs, covering fundraising, sales, product planning, and more. It can be used with multiple AI agents.
A discussion on how companies should measure the real-world impact of AI agents and skills in production environments, rather than relying solely on benchmark results.
The article discusses how a new skill-based approach has disrupted the established multi-agent system paradigm in AI research, potentially marking a significant shift in the field.
Recommends four open-source paper writing skill packs suitable for machine learning/computer vision/NLP and other fields, focusing on structure standardization, polishing and review, complete research workflow, and Chinese collaboration, supporting AI assistants such as Codex, Claude Code, and Gemini.
A detailed guide on using Claude Code effectively, including setup, CLAUDE.md configuration, four-layer architecture, hooks, and daily workflow patterns.
Introduces 10 Codex Skills suitable for Chinese content creators, covering topic selection, research, eliminating AI-generated feel, cover design, cards, infographics, and other aspects, and provides installation sequence recommendations to help creators build an efficient content production line.
Cursor introduces a leaderboard of popular plugins, skills, and MCPs across teams, with one-click add from the new Customize page.
Introduce 5 Codex Skills to improve research efficiency, including paper framework construction, image to PPT conversion, scientific diagram editing, academic writing assistance, and learning high-level paper structures, emphasizing turning repetitive processes into reusable skills.
A new study reveals early results suggesting that AI is negatively affecting human skills, raising concerns about cognitive decline.
A PM at an internal developer platform highlights the challenge of tracking which AI agent skills are actually invoked and effective, and asks the community if there are existing tools or solutions for this observability problem.
Matt Pocock released v1 of mattpocock/skills, a tool for creating and managing AI agent skills with features like /ask-matt and writing best practices.
Recommended the agentic coding skills suite v1.0.0 released by @mattpocockuk, which includes the 'grill me' skill capable of multiple rounds of detailed questioning. It is considered extremely concise in programming skill descriptions.
Sharing ten skills on removing traces of AI, possibly covering how to make AI-generated content more natural or reduce the AI flavor.
This article lists 25 abilities worth long-term training for ordinary people in the next ten years, including personal IP, AI application, sales, self-media, etc., emphasizing the accumulation of core abilities rather than chasing hotspots.
Membrane released over 3,000 integration skills for AI agents, simplifying SaaS app interactions by handling auth, actions, and glue code. The skills are built on an open spec and include examples like Gmail and Slack.
Introducing Skills, a feature that allows users to define reusable instructions for AI agents, such as brand rules or formatting preferences, to avoid rebuilding context each time.
SkillsBench 1.1 is a benchmark for evaluating AI agents' ability to use skills, now fully audited and error-free.
LlamaIndex's blog post describes building a custom LiteParse skill for Claude agents that reduced cost per question by 37% and improved answer quality by analyzing agent traces to fix inefficiencies in PDF parsing.
Anthropic quietly released the official plugin claude-code-setup, which scans your project and recommends configurations such as Hooks, Skills, MCP servers, etc., upgrading Claude Code into a complete AI development environment.