Agent Skills (SKILL.md)

“SKILL.md or AGENT.md is genuinely easier to use, with a low barrier to entry for building custom workflows”

“It feels a bit like the most likely outcomes are increased token burn, review surface, and time per task”

“Letting an instruction following llm deep research and iterate has given fantastic results before.”

“I tried it on my macOS apps and I noticed some improvements codewise and updated some deprecations I didn’t know existed in Swift.”

“I experimented with skills, but they were skipped too often for the tool to work as reliably as it now does”

“I still get a lot of results where they are ignored even after spending time trying to tighten them up.”

“The real issue is that prompts are not tightly coupled with capabilities. If we admit that, then skills are over hyped.”

“everything i would have done over hours on a bugged web dashboard, i saw opencode just deploy the structure in one go with api calls.”

“implementing skills to manually call and use while working side by side with an AI is definitely nice”

“Despite my previous efforts with skills, I've found agents will still do things like call help on CLIs”

“Skills are better than MCP because they basically encode the API docs/context in an LLM friendly manner.”

“they have progressive disclosure so you don't bloat your context with an inefficietly designed MCP”

“cli tool+skill can perfectly replace it with less token overhead and better matching due to skill's front matter”

“Skills are great for pure knowledge and teaching an LLM how to use an existing tool”

“Skills are good for instilling non-repeatable, yet intuitive or institutional knowledge.”

“OCI packaged, verifiable skills for Flux that should progressively discovery instead of loading everything into context”

“skills use progressive disclosure. The AI agent does not load up the entire context, if the skill is not being used.”

“You've just reversed the context benefits because the content of the skill...goes into context.”

“The reason SKILLs work so well is because there's 50 years of accumulated knowledge of how to run rudimentary Unix tools.”

“a markdown doc that tells the agent what CLI tools are available and when to use them”

“Existing paradigms like Skills already mitigate context bloat and selection overhead pretty well”

“It's a great idea: really neat take on programmability, and can be reloaded while the agent is running”

“Everyone else is using skills to provide updating knowledge and cli tools for extra functionality.”

“With these Skills in place, the agent is able to do things it would really struggle with otherwise”

“most of the more than 100,000 skills on GitHub don't have any secure verification processes”

“I do see other comments speculating these skills work more efficiently but I'm not sure I have seen any evidence for that”

“it smells like a hack, just like "think extra hard and I'll tip you $200" was a few years ago”

“Is any of this standardization really needed? Who does it benefit, except the people who enjoy writing specs and establishing standards like this?”

“this feels like a grift or more charitably trying to build a presence/market around nothing”

“Sometimes they reach for skills, sometimes they don’t and just try to do the thing on their own.”

“Experimenting with skills over the last few months has completely changed the way I think about using LLMs.”

“the key advantage of the SKILLs is that they get loaded to the end of the context when needed”

“As someone who has found skills useful, seeing skills like this raises the same question about (a subset of) skills as did MCP”

“they're certainly superior to MCP in ways, being much easier to implement and reducing context usage by being discoverable”

“I found a bunch of potential vulnerabilities in the example Skills .py files provided by Anthropic.”

“You've effectively flattened that MCP server into some Markdown and Bash, only the thing you have now is more flexible”

“We built a universal installer with the most popular claude skills that you can now install into any agent directly”

“I think that they often do solve the problem, just maybe they have some other side effects/trade offs.”

“Skills also have a nicer way of working with the context, by default (and in the main web uis), with their overview-driven lazy loading.”

“Skills seem to me like the simplest possible design for a mechanism for adding extra capabilities to an existing coding agent.”