AGENT SKILLS

Anthropic donated the Agent Skills standard to the Agentic AI Foundation on October 22, 2026. What moves, what stays the same, and what to check in your own SKILL.md files on Monday.

leanrea is an 8 KB skill pitched as a replacement for the REA (Reverse Engineer Anything) MCP server. What its benchmark shows, what it skips, and which to install.

Submit a plugin to the Claude directory: validate it, clear the security scan, publish, and read 90 days of usage analytics. Needs a paid plan.

Claude Files API and Skills API are GA: drop two beta headers, add file expiry up to 90 days, and switch to page cursors. Type-checked TS and Python steps.

Custom GPTs retire Dec 11, 2026. Instructions and files migrate to a ChatGPT plugin automatically; custom actions do not. Here is the developer plan.

Melty is a free Windows launcher for AI-built game mashups. How the Claude Code and Codex workflow works, the open skill pack, and the modder backlash.

Hermes Agent is Nous Research's open-source, self-improving AI agent. Run it locally with Ollama, see how its skills system works, and compare it with OpenClaw.

Claude Code plugin evals score a plugin against a no-plugin baseline, write JSON and HTML reports and gate CI, making plugins testable agent infrastructure.

Vercel Skill Packs bundle agent skills into one installable, unlisted pack on skills.sh. How packs work, what they mean for teams, and the trust questions.

Agent Plugins 1.0.0 is an open standard that packages Agent Skills and MCP servers into one plugin, with ChatGPT, Codex, Cursor and Copilot support at launch.

SkillSV is a Shapley framework that values the rules, examples and scripts inside an agent skill, cutting skills to 69% of tokens without significant loss.

SIGIL compiles prose SKILL.md files into typed agent harnesses. Prose runs execute 56% of mandated steps; compiled harnesses reach 86% with 0.58x the tokens.

MCP vs Agent Skills: MCP gives agents live access to tools and data, Skills give them packaged procedure. The decision rule for when to use which, or both.

Wiki skills add the missing graph layer to agent context: skills that link to each other let agents navigate knowledge instead of front-loading it all.

Resource2Skill, a Microsoft paper, turns tutorials, repos, articles, and reference artifacts into executable agent skills with provenance. What to copy from it.

SkillHone argues agent skills need decision history, not just the latest SKILL.md. Why saving the reasons behind each change helps future agents improve them.

Agent Studio lets you author subagents next to your skills and serve both over one MCP endpoint, plus REST and the dd CLI, with a community moderation loop.

A reference architecture for progressive disclosure: skills, files, memory and generation on one MCP endpoint, scoped by one API key and one credit balance.

MCP servers vs Agent Skills: MCP gives an agent access to a live system, Skills teach it how to do a task. A five-question framework for which one to build.

Skill Studio lets anyone author skills on the same progressive-disclosure MCP endpoint, and a skill file can be a link fetched only when an agent needs it.