7Anthropic News·
Anthropic launches Agent Skills: composable, portable capability packages for Claude
Anthropic introduced Agent Skills, a system allowing users and developers to package instructions, scripts, and resources into reusable folders that Claude loads contextually when relevant to a task. Skills are composable, portable across Claude apps, Claude Code, and the API, and can include executable code for tasks where deterministic programming outperforms token generation. The feature is available to Pro, Max, Team, and Enterprise users, with an API endpoint for programmatic management, and has been published as an open standard for cross-platform portability. Partner integrations with Box, Canva, and Notion are already live, and an open GitHub marketplace exists for community-built skills.
Related guides (5)
Enterprise Deployment PatternsTopic guide
Enterprise Deployment Patterns: How Organizations Are Moving LLMs from Demo to Production
Read asIn-depth
Anthropic
Anthropic: Frontier AI Lab at the Intersection of Capability and Safety Governance
Read asIn-depth
Related events (8)
claude-skills: 313+ Skill/Plugin Collection for Claude Code and Multi-Agent Coding Tools
A GitHub repository providing 313+ reusable skills, agent plugins, and workflow templates targeting Claude Code, Codex, Gemini CLI, Cursor, and eight other coding agents. Coverage spans engineering, marketing, compliance, C-level advisory, finance, and productivity domains. The project has accumulated 15,476 stars with 157 added today, indicating strong community traction. It represents a growing ecosystem of structured prompt/skill libraries designed to extend AI coding agents beyond pure code generation.
Claude Tag: Anthropic launches multiplayer, proactive, persistent agent capabilities in Slack
Anthropic has introduced 'Claude Tag,' a Slack integration enabling multiplayer, proactive, and persistent agent behavior for Claude. The deployment allows Claude to be tagged in Slack conversations, take initiative, and maintain context across sessions. This represents a meaningful step in agentic deployment patterns for enterprise collaboration tools.
Anthropic launches Claude Tag: persistent, multiplayer Claude agent for Slack teams
Anthropic has released Claude Tag in beta for Enterprise and Team customers, a Slack-native agentic product that allows teams to tag @Claude in channels where it operates as a shared, persistent team member with memory, tool access, and asynchronous task execution. Claude Tag builds on Claude Code and Cowork, adding multiplayer context (one Claude per channel visible to all), ambient proactive updates, and the ability to schedule and pursue tasks autonomously over hours or days. Anthropic reports that 65% of its own product team's code is now generated by an internal version of Claude Tag. The product runs on Claude Opus 4.8 and allows administrators to scope tool access, data permissions, and token spend per channel.
Anthropic Launches Claude for Life Sciences with New Connectors, Agent Skills, and Benchmark Improvements
Anthropic has announced a dedicated life sciences offering for Claude, targeting the full drug discovery and commercialization pipeline rather than individual tasks. Claude Sonnet 4.5 achieves 0.83 on the Protocol QA benchmark (above the human baseline of 0.79) and shows improvements on BioRench bioinformatics evaluations. The launch includes new connectors to platforms such as Benchling, BioRender, PubMed, Synapse.org, and 10x Genomics, plus a new Agent Skills framework starting with a single-cell RNA QC skill. Anthropic is partnering with major consultancies (Deloitte, Accenture, KPMG, PwC) and cloud providers (AWS, Google Cloud), with Sanofi cited as a flagship enterprise customer.
Anthropic Publishes 'Agent Skills' Public Repository
Anthropic has made a public GitHub repository called 'skills' available, described as a public repository for Agent Skills. The repository has accumulated 136,679 total stars with 514 added today, suggesting significant community interest. The project appears to be a Python-based resource related to agent capabilities, though specific technical details are sparse from the available description.
Anthropic Releases Claude Opus 4.5 with State-of-the-Art Coding, Agent, and Computer Use Capabilities
Anthropic has released Claude Opus 4.5, positioning it as the best model in the world for coding, agentic workflows, and computer use, with pricing reduced to $5/$25 per million input/output tokens. The model demonstrates significant token efficiency gains—up to 65% fewer tokens than prior models on equivalent tasks—alongside improvements in long-horizon autonomous task execution, multi-step reasoning, and self-improving agent behavior. The release is accompanied by updates to Claude Code, the Claude Developer Platform, and integrations with Excel, Chrome, and desktop environments. Early partner feedback from GitHub Copilot, Cursor, Notion, Warp, and others reports measurable benchmark improvements and new use cases previously out of reach.
SkillKit: Portable Skills Layer for AI Coding Agents
SkillKit is an open-source TypeScript project that provides a portable skills abstraction for AI coding agents, enabling installation, translation, and sharing of skills across tools like Claude Code, Cursor, Codex, GitHub Copilot, and 40+ others. The project has accumulated 1,112 stars with 32 added today, indicating moderate community traction. It targets the interoperability gap between the growing ecosystem of AI coding assistants.
Anthropic Releases Claude Sonnet 4.5: Top Coding and Computer-Use Model with Agent SDK
Anthropic has released Claude Sonnet 4.5, claiming it is the best coding model and strongest model for building complex agents, with a 61.4% score on OSWorld (up from 42.2% for Sonnet 4) and state-of-the-art performance on SWE-bench Verified. The release is accompanied by major product upgrades including checkpoints in Claude Code, a native VS Code extension, a Claude Agent SDK giving developers access to the same infrastructure powering Claude Code, and new context editing and memory tools in the Claude API. Pricing is unchanged from Sonnet 4 at $3/$15 per million input/output tokens. Early enterprise customers including Cursor, GitHub Copilot, Devin, Canva, and Figma report significant gains in coding, agentic, and long-context tasks.