Python · MIT
microsoft/SkillOpt
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
★ 18.9k
Stars
1.8k forks · 74 open issues
+21/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
53.0
Momentum / 100
see the breakdown below
6mo ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 25.6 | +21/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.78× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 12.4 | 18.9k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 53.0 | sum of the above |
Detail
| Topics | agent-skillsself-evolving-agents |
| Matched on | Agent Skills & MCP (agent-skills) |
| Short window | +146 stars over 7 days = 20.9/day |
| Long window | +697 stars over 26 days = 26.8/day |
| Lifetime average | 104.32 stars/day over 181 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |