Submit OraClaw decision intelligence skills for directory listing

[Whatsonyourmind]

Hi! I built OraClaw — a set of 14 decision intelligence skills for MoltBot/OpenClaw agents:

Skill	What it does	Latency
oraclaw-bandit	A/B testing via UCB1/Thompson/LinUCB	<1ms
oraclaw-solver	LP/MIP optimization (HiGHS)	<2ms
oraclaw-forecast	ARIMA + Holt-Winters time series	<3ms
oraclaw-anomaly	Z-score/IQR outlier detection	<0.05ms
oraclaw-graph	PageRank, Louvain communities	<1ms
oraclaw-cmaes	Continuous parameter optimization	<5ms
oraclaw-simulate	Monte Carlo (5K iterations)	<2ms
oraclaw-risk	VaR/CVaR with correlations	<1ms
+ 6 more	bayesian, ensemble, evolve, calibrate, pathfind, decide	<5ms

These fill the "math/computation" gap — things LLMs are bad at: optimal scheduling, anomaly detection, risk quantification, resource allocation. All sub-5ms, zero LLM cost.

Each skill is packaged with a SKILL.md and ready for ClawHub publishing. Would love to get them listed in the directory.

Repo: https://github.com/Whatsonyourmind/oraclaw
MCP server: 12 tools for AI agents
API: https://oraclaw-api.onrender.com (deploying)

Happy to adjust the packaging to match your directory format. Let me know!

[Whatsonyourmind]

Update: OraClaw API is now live! Try it:

# Health check — 19 algorithms, 17 endpoints
curl https://vigilant-rotary-phone-97r5w6j6964pcp4gr-3001.app.github.dev/api/v1/health

# Multi-Armed Bandit example
curl -X POST https://vigilant-rotary-phone-97r5w6j6964pcp4gr-3001.app.github.dev/api/v1/optimize/bandit   -H 'Content-Type: application/json'   -d '{"arms":[{"id":"a","name":"A","pulls":50,"totalReward":35},{"id":"b","name":"B","pulls":50,"totalReward":30}]}'

All endpoints verified and sub-5ms. Full docs: https://github.com/Whatsonyourmind/oraclaw

[Whatsonyourmind]

Update: OraClaw is now live and installable!

API (live): https://oraclaw-api.onrender.com

curl https://oraclaw-api.onrender.com/api/v1/health
# → 19 algorithms, 17 endpoints, v2.3.0

npm packages (5 published, 10 more coming):

npm install @oraclaw/bandit @oraclaw/solver @oraclaw/decide @oraclaw/graph @oraclaw/calibrate

ClawHub skills (5 published, 9 more coming):

clawhub install oraclaw-bandit

Quick test — Multi-Armed Bandit:

curl -X POST https://oraclaw-api.onrender.com/api/v1/optimize/bandit   -H 'Content-Type: application/json'   -d '{"arms":[{"id":"a","name":"Option A","pulls":100,"totalReward":65},{"id":"b","name":"Option B","pulls":100,"totalReward":72}]}'

All sub-5ms, zero LLM cost. Remaining packages publishing automatically over the next few hours.