AGENT SKILLS

Melty is a free Windows launcher for AI-built game mashups. How the Claude Code and Codex workflow behind it works, the open skill pack people use, and the backlash from modders.

Hermes Agent is Nous Research's MIT-licensed, self-improving AI agent: it writes and refines its own skills, keeps memory across sessions, and talks to you from the terminal or Telegram, Discord, and Slack. Here is how to run it fully locally with Ollama, how its skills system works, and how it compares with OpenClaw.

Claude Code 2.1.269 adds plugin evals, baseline comparisons, JSON and HTML reports, and CI gates. That changes plugins from clever prompts into measurable agent infrastructure.

skills.sh now lets you bundle multiple agent skills into a shareable, unlisted pack and install it with one command. Packs mix public directory skills, private local files, and GitHub repos, then sync with a single update command. Here is how they work, what they mean for team standardization, and where the trust questions are.

Vercel, OpenAI, GitHub, Microsoft, AWS, and Cursor collaborated on Agent Plugins 1.0.0, an open standard that packages Agent Skills and MCP servers into one portable plugin. ChatGPT, Codex, Cursor, GitHub Copilot, Kiro, and VS Code load the format on day one.

Automated skill optimizers write long SKILL.md files whose credit is a black box. SkillSV attributes value to rules, examples, and scripts inside a skill: pruning to 69% of tokens without significant loss on four benchmarks.

A Michigan team measures prose SKILL.md files against compiled harnesses: agents execute only 56% of the steps their own skill mandates. SIGIL compiles skills into typed graph harnesses, hitting 86% compliance with 0.58x the tokens.

MCP gives an agent live access to tools and data. Agent Skills give it packaged procedure. They solve different halves of the same problem, and the MCP working group is now standardizing how skills ship over MCP. Here is the decision rule.

The Agent Skills spec gave agents progressive disclosure in three tiers - name, SKILL.md, bundled files. What it did not give them is a graph. Skills that link to each other, and say when to follow the link, let an agent navigate knowledge instead of front-loading it. Here is the argument, the measurements from our own 36-skill repo, and what to change.

Microsoft's Resource2Skill paper points at the next agent-skills problem: converting videos, repos, articles, and reference artifacts into executable skills without losing provenance.

SkillHone is a July 2026 paper about evolving agent skills across sessions. The useful takeaway for developers is simple: do not save only the latest SKILL.md. Save the decisions that explain why it changed.

Skills gave an agent what to know. The missing half is what role to play. Agent Studio lets you author subagents next to your skills in one place, serve both over the same MCP endpoint with the same progressive disclosure, browse them over REST and the dd CLI, and publish them to the community under a moderation loop. Here is the design and why the two belong in one studio.

Skills, files, memory, and generation do not need four integrations. They need one MCP endpoint with tiered disclosure, one API key that scopes everything to its owner, and one credit balance. The same tools answer to an MCP client, an in-product chat, and a CLI. Here is the whole architecture, and why it is the shape that makes a fleet of agents coherent.

A decision framework for 2026: MCP servers give an agent access to a live system, Agent Skills teach it how to do a task. Here is when to build each, when to build both, and the criteria that actually decide it, grounded in the MCP spec and Anthropic's skills docs.

The first version of skills-over-MCP served a fixed first-party catalog. Skill Studio extends it two ways: anyone can author skills that ride the same progressive-disclosure endpoint scoped to their own API key, and a skill file can be a link instead of a copy - a URL whose bytes are only fetched at the moment an agent decides it needs them. Progressive disclosure stops at the skill boundary no longer. It runs out to the open web.

SKILL.md solved knowledge packaging with progressive disclosure. MCP solved capability transport but ships flat, context-hungry tool lists. The next shape combines them - an MCP server whose tools are a skill directory, so an agent pays context only for what the task needs. Here is the argument and a working implementation.

A Hacker News thread on config files that run code points at the next AI coding risk: agent hooks, skills, and editor rules need review like executable dependencies.

GitHub trending is full of anti-slop, taste, and compound-engineering skills. The real signal is not that agents need more prompts. It is that teams are trying to make subjective review criteria executable.

GitHub trending is full of agent skill registries. The winning pattern is not more prompts. It is dependency governance for the instructions your coding agents inherit.

Claude Code's newer plugin URL and hard-deny controls are small release-note items with a big implication: agent extensions now need supply-chain discipline.