Individual skill
asteria-investment-office-solver
Solve Asteria Investment Office JSON tasks by combining local payload contracts with the live read-only Asteria environment.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_010/fewshot/naive/fewshot_attempt_03/SKILL.md
Source commit 5082a777379156a048881e94940d640702e5e09a
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- 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.
- agent Repository topic
- ai Repository topic
- benchmark Repository topic
- llm Repository topic
- self-evolving Repository topic
- self-learning Repository topic
- skills Repository topic
- finance Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 5,437 bytesSKILL.mdcore · 5,437 bytesasteria_helper.pyruns · 46,535 bytes
Read excerpt
# Asteria Investment Office Solver
Use this skill for tasks that ask for Asteria Investment Office portfolio, credit-risk, correlation, allocation-view, or committee JSON answers. The local task files define the requested shape and focus; the shared environment is the current book of record.
## Workflow
1. Read `prompt.txt`, every JSON file in `input/payloads/`, and especially `answer_template.json`.
2. Fetch current data from `http://task-env:9010/` unless the task gives another base URL. Use only read-only endpoints. Never call a judge or write endpoint.
3. Treat the environment as authoritative for portfolio holdings, marks, policy thresholds, security master data, issuer watchlist status, macro signals, and index levels. Use local payloads for requested portfolio ids, windows, focus sets, ticket counts, ordering, and schema constraints. If a local payload says it is stale or has an older as-of date, the correct precedence is current environment over stale payload.
4. Build the answer exactly to `answer_template.json`: no extra prose, no missing required fields, declared ordering, and numeric rounding at the requested precision.
5. Prefer deterministic calculation over narrative inference. When the template is one of the common Asteria patterns, run the helper:
```bash
python3 skill/asteria_helper.py /path/to/task/input