Introducing EvoSkill V1, an open-source toolkit that takes a benchmark and a coding agent, and…
@SentientAGI508K followers
30,234 views
56 Comments
Comments from the original post on X (Twitter)

@SentientAGI
1/ How does it work? Using a pattern similar to @karpathy, EvoSkill V1 acts as autoresearch for AI agent skills. It takes a benchmark, a scoring function, and a coding agent, and first evaluates the agent on that benchmark. From there, it uses the agent's failure traces as feedback to propose, test, and iterate on its prompts and skills. Read the full technical breakdown ↓
12 likes

@SentientAGI
2/ Who is EvoSkill V1 for? > Devs who want to turn their agent into a task specialist without manually writing prompts > Teams building specialized solutions for customers with custom environments > Researchers working on benchmarks, agent evaluation, or autoresearch-style self-improvement
10 likes

@SentientAGI
3/ Does it actually work? Yes. We ran EvoSkill on the hardest reasoning benchmarks and the results speak for themselves: > EvoSkill pushed Claude Code to SOTA performance on OfficeQA, from 60.6% to 68.1% > SealQA benchmark increased from 26.6% to 38.7%, with no human involvement, and the same skills zero-shot transferred to BrowseComp with a 5% gain > We also had similar gains with @opencode, @OpenHandsDev, @goose_oss, and @OpenAI's Codex CLI
8 likes

@SentientAGI
4/ What's next? This is the first production release from Sentient Labs' AI evolution research, where we're actively exploring how to make agents self-improve across prompts, skills, memory, and the harness itself. In short, EvoSkill V1 is just the beginning. Until then, please watch & star the repo ↓
15 likes

@SentientEco
So who else is clearing their weekend? 🙋♂️
5 likes

@FileCityAI
Great Work! @SentientAGI Here is a visual map + narrated walkthrough of EvoSkill
5 likes

@ThuyTrang108
If implemented effectively, tools like these can significantly shorten the time from idea --> demo --> production.
3 likes

@SentientAGI
When AI starts to build AI, so does the pace of progress!
1 like

@sentient_found
self-learning at it's best!
3 likes

@SentientAGI
and it's only going to get better!

@0xniccomi
sick video 🕶️
3 likes

@SentientAGI
We think so too ✨
2 likes

@j0hncrypt013
cloning this tonight, gonna point it at my own lil benchmark and see what specialist pops out
2 likes

@SentientAGI
Look forward to seeing it!

@halaltrader_
evolving agents against a benchmark hits different than just tuning prompts
2 likes

@SentientAGI
The days of manual tuning your prompts are numbered
1 like

@Based__SOL
SPECIALISTS ON TAP
2 likes

@SentientAGI
It's time to let the tap flow!
1 like

@ZhugeLyang
back to back bangers
2 likes

@SentientAGI
we ain't done yet
2 likes




















