Menu

Individual skill

asteria-investment-office

Solve Asteria Investment Office JSON tasks that require using the shared environment as the current book of record for portfolio holdings, fixed-income trades, equity-index correlations, active allocation views, macro signals, policies, and committee/risk outputs. Use when prompts mention Asteria portfolios, PF-* ids, energy credit, fixed-income risk rebalance, international equity correlation, allocation view refreshes, or committee decision JSON.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_010/fewshot/deepagents/fewshot_attempt_03/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
121
Repository last updated
Oct 29, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Asteria Investment Office

## Core Workflow

1. Read the user prompt, every local payload JSON, and the answer template before calculating. Treat the template as the output contract: required keys, enum values, ordering rules, and rounding precision all come from it.
2. Read `environment_access.md` in the task workspace and use only the listed Asteria environment endpoints. Current environment records override local worksheet, memo, or stale payload values whenever the prompt says to use the shared environment as the book of record.
3. Run the helper at [scripts/asteria_env_helper.py](scripts/asteria_env_helper.py) when useful:

```bash
python scripts/asteria_env_helper.py analyze input
```

Pass the task input directory, task directory, or current directory. The helper prints a JSON fact pack with fetched portfolio data, enriched holdings, fixed-income metrics, pairwise correlations, allocation signal rows, and candidate bond facts. Use it as calculation support, not as the final answer.
4. Build the final JSON manually against the template. Return only JSON when requested; do not include commentary.