# Agent Skills

Third-party skills in public registries can be exploited by a poisoning method that edits only decision rules while leaving the task and interface intact. Without real user requests or ground-truth answers, StealthyPoison uses synthetic requests and clean executions by a surrogate agent as references to iteratively rewrite formulas, thresholds and branches. Across 566 eligible skills, 5,244 requests and more than 26,000 registry entries, the frozen poisoned skills reached micro-averaged attack success of 31.0%–31.9% on three held-out models, close to the surrogate's 32.9%.

Third-party skills in public registries can be exploited by a poisoning method that edits only decision rules while leaving the task and interface intact. Without real user requests or ground-truth answers, StealthyPoison uses synthetic requests and clean executions by a surrogate agent as references to iteratively rewrite formulas, thresholds and branches. Across 566 eligible skills, 5,244 requests and more than 26,000 registry entries, the frozen poisoned skills reached micro-averaged attack success of 31.0%–31.9% on three held-out models, close to the surrogate's 32.9%.

Anthropic has donated Agent Skills, the open standard it published in December 2025, to the Agentic AI Foundation under the Linux Foundation, transferring the name, logo, GitHub organization and agentskills.io domain. A skill is a folder holding a SKILL.md file that teaches an agent a specific task or domain; the format grew out of Claude Code, which handled general knowledge work but often lacked the procedural knowledge real business tasks need. Since the October 2025 launch, one million skills have been published and installed nearly 280 million times, and more than 70 agent platforms including ChatGPT, Cursor, GitHub Copilot and VS Code have integrated the standard.

Anthropic has donated Agent Skills, the open standard it published in December 2025, to the Agentic AI Foundation under the Linux Foundation, transferring the name, logo, GitHub organization and agentskills.io domain. A skill is a folder holding a SKILL.md file that teaches an agent a specific task or domain; the format grew out of Claude Code, which handled general knowledge work but often lacked the procedural knowledge real business tasks need. Since the October 2025 launch, one million skills have been published and installed nearly 280 million times, and more than 70 agent platforms including ChatGPT, Cursor, GitHub Copilot and VS Code have integrated the standard.

Anthropic has published a repository of example skills for the skills system Claude uses: a skill is a folder of instructions, scripts and resources that Claude loads dynamically to complete a specialized task repeatably, such as producing documents under a company's brand guidelines, analyzing data with an organization's workflows, or automating personal tasks. The repository also open-sources, under Apache 2.0, the docx, pdf, pptx and xlsx document skills that power Claude's document capabilities, as a reference for more complex skills in a production AI application; the skills are for demonstration and education only, and behavior received from Claude may differ from what they show, so they should be tested thoroughly before critical use.

Anthropic has published a repository of example skills for the skills system Claude uses: a skill is a folder of instructions, scripts and resources that Claude loads dynamically to complete a specialized task repeatably, such as producing documents under a company's brand guidelines, analyzing data with an organization's workflows, or automating personal tasks. The repository also open-sources, under Apache 2.0, the docx, pdf, pptx and xlsx document skills that power Claude's document capabilities, as a reference for more complex skills in a production AI application; the skills are for demonstration and education only, and behavior received from Claude may differ from what they show, so they should be tested thoroughly before critical use.

Cloudflare's Agents SDK now treats Agent Skills as files in the agent's workspace: write a folder containing SKILL.md under /workspace/.agents/skills/ and the agent can use it on its next turn, with no build step or deploy, and the agent can write its own skills. Skills load from a workspace, an R2 bucket, or code, and Think lists every source again before each turn; each SKILL.md is checked against the Agent Skills specification, and a skill that breaks a rule still loads with a logged warning. This is a breaking change: direct agents/skills use, the Vite import, SkillRegistry, and Think's skillWorkspace are removed.

Cloudflare's Agents SDK now treats Agent Skills as files in the agent's workspace: write a folder containing SKILL.md under /workspace/.agents/skills/ and the agent can use it on its next turn, with no build step or deploy, and the agent can write its own skills. Skills load from a workspace, an R2 bucket, or code, and Think lists every source again before each turn; each SKILL.md is checked against the Agent Skills specification, and a skill that breaks a rule still loads with a logged warning. This is a breaking change: direct agents/skills use, the Vite import, SkillRegistry, and Think's skillWorkspace are removed.

Anthropic has published a skills repository that turns Claude's skills for specialized tasks into self-contained folders, each holding a SKILL.md file with instructions and metadata that Claude loads dynamically when needed. The repository collects example skills across creative, development and testing, and enterprise communication work, and also releases the docx, pdf, pptx and xlsx document skills that power Claude's document capabilities; those four are source-available rather than open source. The skills are presented for demonstration and educational purposes, and Anthropic notes that actual implementations and behaviors may differ, so they should be tested thoroughly before critical use.

Anthropic has published a skills repository that turns Claude's skills for specialized tasks into self-contained folders, each holding a SKILL.md file with instructions and metadata that Claude loads dynamically when needed. The repository collects example skills across creative, development and testing, and enterprise communication work, and also releases the docx, pdf, pptx and xlsx document skills that power Claude's document capabilities; those four are source-available rather than open source. The skills are presented for demonstration and educational purposes, and Anthropic notes that actual implementations and behaviors may differ, so they should be tested thoroughly before critical use.

Anthropic's Claude Platform release notes raise the maximum request size for the Messages API and the Token Counting API from 32 MB to 128 MB on the first-party Claude API. Before this change, both endpoints stopped at 32 MB, so larger inputs could not be submitted as a single request. The change covers request size on the first-party Claude API only, and the notes report no throughput, latency or cost measurements.

Anthropic's Claude Platform release notes raise the maximum request size for the Messages API and the Token Counting API from 32 MB to 128 MB on the first-party Claude API. Before this change, both endpoints stopped at 32 MB, so larger inputs could not be submitted as a single request. The change covers request size on the first-party Claude API only, and the notes report no throughput, latency or cost measurements.