Cio Ensemble
This skill should be used when the user asks to "combine portfolio proposals", "build a CIO ensemble", "select an SAA recommendation", or "write a portfolio board memo" from reviewed candidates.
Install
$ agentstack add skill-nutdnuy-self-driving-portfolio-skill-cio-ensemble ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-nutdnuy-self-driving-portfolio-skill-cio-ensemble) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
cio-ensemble
Stage 6 of the agentic SAA pipeline (Ang/Azimbayev/Kim 2026, §3.1 step 6).
Combination methods
| ID | Definition | | ------------------- | -------------------------------------------------------- | | simple_mean | Equal-weight average of survivor weights, renormalised. | | borda_weighted | Per-asset weighted average; survivor weights ∝ Borda points. | | confidence_weighted | Survivor weights ∝ mean CMA confidence × Borda points. | | median | Per-asset median across survivors, renormalised. | | trimmed_mean | 20% trimmed mean per asset, renormalised. | | sharpe_weighted | Survivor weights ∝ ex-ante Sharpe. | | regime_weighted | Survivor weights ∝ regime-fit (TPA-style). |
Selection rule (regime → method)
| Regime | Combiner | | --------------- | --------------------- | | expansion | sharpe_weighted | | recovery | sharpe_weighted | | late_cycle | confidence_weighted | | recession | regime_weighted | | any (low conf.) | trimmed_mean |
If top1_confidence_low=true, the override fires regardless of label.
Outputs
final_portfolio.json— recommended weights + all seven candidate
ensembles for transparency.
board_memo.md— human-readable summary.
Escalation
escalate_to_human=true if any of:
- Recommended vol within 50bps of IPS hard cap.
- Fewer than the IPS-defined minimum feasible proposal count survived review.
- Adversarial diversifier won the head-to-head.
- Top-1 regime confidence below 0.4.
Run through pipeline/orchestrator.py to commit the final JSON and board memo atomically, then verify the complete run with pipeline/verify.py.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: nutdnuy
- Source: nutdnuy/self-driving-portfolio-skill
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.