Agent Skills
No written verdict yet. Here is what commenters said.
Why people recommend it
“It seems to me he could have use an skill like using-agent-skills from https://github.com/addyosmani/agent-skills go generate the specs”
“A good example is the agent skills open standard”
Show 3 more
Caveats and dissent
“it feels like AGENTS.md adherence is higher than Skill adherence”
“the discoverability of these skills will be difficult without a rename”
Show 1 more
Often compared with
Who recommends it in their own words
From the makers not counted in the ranking
Recently, “skills” have been blowing up. I collected 60k+ open-source agent skills from GitHub, then curated 1,000+ Claude Code skills that are actually useful. The directory is updated daily. To me, Claude Code skills aren’t that different from agents or other automation tools—the big difference is that they lower the barrier so more people (including beginners) can use them. There are tons of skills in every indust
Threads where it came up
- Agent Skills 5 mentions
- Agent Skills 3 mentions
- Ask HN: How do you manage skills files? 1 mention
- Sol Loves to Cheat 1 mention
- The new rules of context engineering for Claude 5 generation models 1 mention
- I Still Prefer MCP over Skills 1 mention
Also written as agent-skills. Data: agent-skills.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 14
“it feels like AGENTS.md adherence is higher than Skill adherence”
“It seems to me he could have use an skill like using-agent-skills from https://github.com/addyosmani/agent-skills go generate the specs”
“A good example is the agent skills open standard”
“I’ve had some success with agent skills”
“I commend them for a clean, simple approach.”
“the discoverability of these skills will be difficult without a rename”
“I thought about distributing some CLIs with Skills instead.”
“Agent Skills [2] appear to be the common format across most of the tools”
“(an allegory for Skills -vs- MCP)”
“Skills work differently. Once loaded into context”
“I recently switched to using only AGENTS.md and SKILLS. I appreciate the standardization from this perspective.”
“Vercel ran a study where they said that skills underperform putting a docs index in AGENTS.md”
“In 56% of eval cases, the skill was never invoked.”
“they're certainly superior to MCP in ways, being much easier to implement”