# Skills Articoli collegati

Il Centro Notizie HTX fornisce gli articoli più recenti e le analisi più approfondite su "Skills", coprendo tendenze di mercato, aggiornamenti sui progetti, sviluppi tecnologici e politiche normative nel settore crypto.

Open-source Claude Science is here: zero dependencies, MIT license, built-in 30+ research Skills

OpenAI4S (Open AI for Scientist), an open-source, MIT-licensed research agent, has been released as a public replication of the closed-source Claude Science. Developed by the Peking University & Yuankong AI Agent Joint Laboratory, it adopts a "Code-as-Action" approach, where the AI directly generates and executes Python/R code within a persistent kernel, enabling complex, multi-step scientific workflows like data retrieval, analysis, visualization, and report generation. The platform functions as a collaborative research workbench. It comes pre-built with over 30 scientific "Skills" for tasks such as protein structure analysis, molecular docking, and literature review—14 of which require GPU/professional compute. A key principle is its strict "no-fabrication policy": it uses real data from sources like UniProt and RCSB, performs actual computations (e.g., protein folding on GPU servers), and reports errors rather than generating simulated results. OpenAI4S supports connecting to users' own computing environments (e.g., GPU clusters) to handle demanding tasks while maintaining workflow integration. The project is open-sourced to encourage community contribution, inviting researchers and developers to expand its Skills, core architecture, and applications across diverse scientific fields.

marsbit17 h fa

Open-source Claude Science is here: zero dependencies, MIT license, built-in 30+ research Skills

marsbit17 h fa

Claude Doesn't Submit Code Directly After Writing It: Runs 4 Skills for Self-Check, Fixes Issues, Then Comes Back to You

Claude No Longer Submits Code Directly: 4 Self-Check Skills to Run Before Coming Back to You AI already writes code, but the burden of reviewing it still falls on you. To address this, Anthropic has built a "verification loop" into Claude Code. After writing code, Claude now runs four self-check skills before delivering the work: * `/code-review`: Finds potential bugs and provides review feedback. * `/simplify`: Cleans up the diff, removing redundant or over-complex implementations to reduce future maintenance costs. * `/verify`: Performs end-to-end validation, actually running the application to confirm the feature works, not just appears to. * `/design`: Used only for UI changes; cross-references the implementation against the project's DESIGN.md file. This loop extends the AI agent's workflow from "gather context → execute" to "gather context → execute → auto-verify → fix → re-verify." It tackles the new bottleneck in AI-assisted development: the speed of verifying code now outpaces human review. These skills are built on Claude Code's existing verification foundation (like running apps and using linters). Teams can create their own custom verification skills by documenting their repetitive manual checks in plain language as Markdown files. Verification can be triggered at four levels: manually (Standalone), embedded in a task, chained with other skills, or automatically on every PR (On every PR). The shift signifies that competition in AI programming is moving from code generation to robust verification and self-correction. Well-built verification loops allow AI agents to run longer and more autonomously with less human supervision. Skills, which encapsulate team knowledge and workflows, are becoming a cross-vendor standard, meaning a team's efficiency gap will depend less on the AI model and more on their investment in these automated workflows and verification mechanisms.

marsbit07/27 10:23

Claude Doesn't Submit Code Directly After Writing It: Runs 4 Skills for Self-Check, Fixes Issues, Then Comes Back to You

marsbit07/27 10:23

Why Are There Increasingly More Indian Executives in the Global Payments Circle?

Why are we seeing more Indian executives rising in the global payments industry? This article explores the phenomenon from the perspective of Chinese professionals working abroad. Contrary to perceptions of India as a complex and difficult market, a highly competitive and globalized cohort of Indian talent is excelling in international finance and tech hubs. These individuals represent a filtered elite, having undergone rigorous educational and professional selection. The article argues that the key advantage of many Indian leaders lies not in pure technical expertise, but in superior organizational and stakeholder management skills. In global payment networks—involving banks, regulators, card schemes, and partners—success often depends on the ability to align diverse interests, build consensus, and navigate complex bureaucracies. Indian executives frequently demonstrate strength in pre-emptively engaging stakeholders, managing expectations, and forming alliances. Furthermore, strong communication and presentation skills are reframed not as mere showmanship but as essential leadership tools for building visibility, securing resources, and creating organizational buy-in within large multinationals. The professional network or "ecosystem" cultivated by the Indian diaspora is another significant factor, creating long-term career momentum through mutual support, referrals, and partnerships across companies like JPMorgan, Visa, and Stripe. Singapore serves as a key regional amplifier for this talent in Asian finance. Many Indian entrepreneurs are also founding companies in payment infrastructure (e.g., cross-border payments, B2B solutions), leveraging their blended experience in technology, finance, and regulation. The conclusion posits that while Chinese payment talent possesses world-class executional and product skills from scaling massive markets like mobile payments, the next phase of global competition requires complementing this with "global organizational capability." This means shifting from individual execution to becoming enablers who can influence, connect, and lead complex, cross-cultural systems to action. The rise of Indian executives signals an evolution in the industry where the ability to get things done *through a global organization* is paramount.

链捕手07/27 10:03

Why Are There Increasingly More Indian Executives in the Global Payments Circle?

链捕手07/27 10:03

Racking Up 24,000 Stars: With One Command, AI Can Now Find Its Own Skills

Vercel, known for its developer tools like Next.js, has launched 'skills', a package manager for AI coding agents, garnering 24,000 GitHub stars. It allows developers to add specialized capabilities, such as React best practices, to AI assistants like Claude Code or Cursor with a single command: `npx skills add <package>`. Skills are shareable, reusable modules that define an AI agent's behavior for specific tasks, moving beyond one-off prompt engineering towards standardized 'capability engineering'. A key innovation is the 'find-skills' skill, which acts as an internal search engine, allowing an agent to autonomously find and install the right skill for a user's request. This lowers the barrier for non-developers to leverage advanced AI coding assistance. However, this 'npm moment' for AI brings significant security risks. Security audits of thousands of skills on platforms like skills.sh and ClawHub found over 30% contained security flaws, with about 13% classified as severe. Threats include malicious scripts that can access local files and credentials, and prompt injection hidden within skill documentation. Unlike traditional code packages, skills blend instructions, code, and system access, posing a direct risk to user machines and data. Experts advise treating skills like code—reviewing them carefully before installation, especially their scripts, and being wary of excessive permissions. Ultimately, Vercel's initiative represents a major shift towards modular, reusable AI capabilities, but its rapid adoption requires developers to bring the same caution used in managing traditional software dependencies.

marsbit07/06 00:19

Racking Up 24,000 Stars: With One Command, AI Can Now Find Its Own Skills

marsbit07/06 00:19

Dan Koe's New Article: Escape the Fate of the Wage Slave, How to Survive in the Tide of AI Replacement?

Dan Koe's article argues that the real threat in the AI era is not technology itself, but financial dependency on employers. He critiques the "wage slavery" of unfulfilling work and identifies five core skills for resilience: agency, taste, persuasion, persistence, and iteration. These are developed not by consuming content, but by starting your own venture. The key to escaping the "employee mindset" is a radical identity shift. This requires: 1) Drastically changing your environment and daily inputs, 2) Choosing a creative medium (like content or code) that provides real-world feedback through trial and error, and 3) Using that feedback to learn and adapt. Koe strongly advocates for content creation over coding for beginners, as it builds irreplaceable subjective taste and audience connection. The practical starting point is a 15-minute self-inquiry to define your "life's work." Answer: What do you know deeply? What innate abilities do you have? What childhood interests were suppressed? Then, identify your contrarian beliefs—what does the mainstream get wrong in your area? The overlap is your unique direction. The final, non-negotiable step is to publish your first piece of content tomorrow. Embrace that it will be bad; the goal is to enter the feedback loop of creation, learning, and iteration, which is the true path to independence.

marsbit06/24 05:33

Dan Koe's New Article: Escape the Fate of the Wage Slave, How to Survive in the Tide of AI Replacement?

marsbit06/24 05:33

PANews Column Registration and Article Submission Guide

"PANews Column Registration and Submission Guide" provides instructions for users to register as columnists and publish articles on the PANews platform. Key application requirements are emphasized: content should focus on in-depth analysis within Crypto, Web3, blockchain, data, and viewpoints. Content primarily for brand/product introductions will not be approved, and heavily AI-generated content will be rejected. Promotional (PR/soft) content is directed to the business channel. **Registration Process:** * **Web:** Go to the official website footer, click "Apply for Column," and register with a phone number or email (login via verification code, no password). Fill in the column name, description, upload an avatar, and submit links to previously published work. * **Mobile:** Navigate to "My" -> "Contribute & Create" and complete the form. **Article Submission Tutorial:** 1. Log in to the PANews website. 2. Access the "Creator Center" from your personal homepage. 3. Use the editor to create and publish articles. **Video Upload:** The platform supports embedding videos from third-party sites (e.g., Bilibili). Copy the embed code from the source video, use the editor's "Insert/Edit media" button, paste the code under the "Embed" tab, and adjust the display size (recommended: width 100%, height 560px). **PANews Skills (AI Agent Tool):** PANews offers an official AI Agent skill set called PANews Skills, enabling AI tools to query platform content, track trends, and publish column articles directly. It includes three main skills: 1. `panews`: For tracking daily must-read lists, popular articles, and funding news. 2. `panews-creator`: For managing columns, publishing articles, and uploading images. 3. `panews-web-viewer`: For parsing PANews webpages into Markdown. These skills are compatible with various AI Agent tools (OpenClaw, Cursor, Claude Code, ChatGPT, Gemini, etc.). To use the `panews-creator` skill, users must obtain a specific authentication value from the PANews website after logging into their columnist account.

marsbit06/16 06:38

PANews Column Registration and Article Submission Guide

marsbit06/16 06:38

How to Do Research Well: Deliberately Practice the Real Skills That Matter

No one truly teaches you how to do research. You're often given a desk, a pre-selected problem, and vague instructions to "create something new." Consequently, many people reverse-engineer the job based on visible outputs—papers, posts, announcements—learning only how to *appear* like a researcher rather than how to *become* one. True research capability is built from stacking small, trainable skills, nearly all of which can be developed through deliberate practice. **Pick Your Own Problem:** Most researchers absorb problems from advisors or trends, lacking the underlying reasoning. Choosing a problem you genuinely care about, as John Schulman advises, leads to original work. Develop "taste" like a muscle: predict experiment outcomes, guess paper results from methods, and track which findings remain important over time. **Upgrade Your Inputs:** Relying on shared reading lists (arXiv hot lists, filtered group chats) leads to unoriginal conclusions. Undervalued old literature often holds crucial insights (e.g., MoE, LSTM, backpropagation). Richard Sutton's "The Bitter Lesson" or Claude Shannon's 1952 talk on creative thinking are more predictive than lengthy modern surveys. Breadth matters as much as depth: draw from neuroscience, mechanism design, hardware knowledge, and honest statistics. Read papers directly, especially appendices and limitations sections. **Write Everything Down:** As Paul Graham noted, writing exposes flaws in seemingly mature ideas. Writing is the cheapest defense against self-deception. Following Feynman's principle, Darwin programmatically wrote down facts contradicting his theory to combat memory bias. Maintain a detailed log of hypotheses, setups, predictions, results, and updated understandings. Reviewing past logs fosters essential humility.

marsbit06/15 12:25

How to Do Research Well: Deliberately Practice the Real Skills That Matter

marsbit06/15 12:25

Founder of Baixing.com: My Fourteen Claude Code Usage Experiences

Founder of Baixing.com Shares 14 Personal Tips for Using Claude Code The author outlines his personal, non-universal strategies for maximizing Claude Code. Key points include: focusing deeply on one primary tool (Claude Code) rather than constant comparison; mastering essential shortcuts for the editor and command line; utilizing voice input like HoldSpeak; starting projects with a structured PROJECT.md file; defaulting to Claude agents for most tasks; and leveraging integrations with GitHub and Cloudflare for build, deployment, and infrastructure. He emphasizes a clear separation between human and machine work: manually maintain a core CLAUDE.md file, and understand AI-generated content by asking the AI, not reading its raw code. Efficient communication involves dragging files (screenshots, audio, documents) directly into the interface. For knowledge management, he recommends a centralized, Git-synced memory system based on ~/.claude/CLAUDE.md to ensure permanence and avoid scattered project memories. Other practices include writing and continuously refining "Skills," using the expensive but reliable ultracode for complex dynamic workflows, and employing Git documentation as handoff points between agents. The overarching philosophy is to treat Claude Code like a horse (or a person) with its own pathfinding abilities—setting goals and boundaries rather than micromanaging every turn.

链捕手06/08 12:54

Founder of Baixing.com: My Fourteen Claude Code Usage Experiences

链捕手06/08 12:54

The Right Way to Use Skills: 5 Reflections After Anthropic Publicly Shared Its Internal Methodology

A deep dive into Anthropic's internal methodology for building effective AI "Skills" reveals five key insights for maximizing their value. First, Skills should focus on capturing "Gotchas" and tacit organizational knowledge—like common pitfalls and undocumented rules—rather than restating general information the AI already knows. Second, think of Skills as a form of "Context Engineering"; they are best structured as folders, not monolithic documents. A core `SKILL.md` file should act as a navigational index, progressively pulling in detailed references, examples, and assets only as needed to avoid overwhelming the model's context window. Third, whenever possible, automate repetitive tasks with scripts. This preserves the model's reasoning capacity for judgment and analysis, while scripts reliably handle the execution, saving tokens and improving accuracy. Instructions within a Skill provide the "why" and the expert judgment, while scripts provide the concrete "how." Fourth, a Skill's description is critical and often misunderstood. It should not be a list of features but a routing rule that clearly signals *when* the Skill should be triggered based on user intent and common phrasing. Finally, as Skills scale from personal tools to team-wide assets, management is crucial. Anthropic advocates for a lightweight, organic approach: let new Skills spread organically within small groups first. Those that prove genuinely useful through adoption naturally graduate to a formal marketplace, ensuring the curated library contains only high-value, battle-tested tools.

marsbit06/08 09:06

The Right Way to Use Skills: 5 Reflections After Anthropic Publicly Shared Its Internal Methodology

marsbit06/08 09:06

After 540,000 Lines of Code, Garry Tan Realizes the Old Game of AI Programming Is Over

YC President Garry Tan's project "Garry's List" involved over 540,000 lines of Rails code, but he concluded this approach is outdated. He argues the software industry is stuck in a "Foxconn factory" mindset: building excessive tests, validators, and control logic to constrain LLMs, which have become cheap and capable enough to work autonomously. The old paradigm treated LLM calls as expensive and code as cheap, leading to complex systems to "manage" the AI. This has now reversed. The future lies in "just-in-time software"—using natural language instructions (Markdown-based "skill packs") and minimal code, letting the AI handle the work. Tan advocates for "skillifying" workflows: after an agent completes a task, it packages the process into a reusable, tested skill pack. This shifts value from writing code to designing capabilities. For example, his agent reviewed 85 hackathon submissions in 30 minutes, a task that previously took days. He emphasizes "tokenmaxxing"—willingly spending on LLM tokens to gain a years-long competitive advantage, as costs are plummeting. The core shift is from measuring output in lines of code to focusing on clarity, taste, and judgment. The best future engineers won't write the most code, but will know what to build and how to unlock the most intelligence with the least code.

marsbit06/02 21:38

After 540,000 Lines of Code, Garry Tan Realizes the Old Game of AI Programming Is Over

marsbit06/02 21:38

活动图片

Trading Strategiesright-arrow

Project Updatesright-arrow