Individual skill

asteria-portfolio-json

Use this skill for Asteria Investment Office tasks that require strict JSON portfolio, credit, correlation, allocation, rebalance, or committee decisions from the shared Asteria environment. Trigger when prompts mention Asteria, PF-* portfolio ids, answer_template.json, current environment records, energy-credit trades, fixed-income rotations, HY/watchlist constraints, non-US equity correlations, index levels, macro signals, active allocation views, or committee decision files.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_010/fewshot/cc/fewshot_attempt_02/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
Yes
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.

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 Portfolio JSON

Use this skill to produce schema-conforming JSON decisions for Asteria Investment Office tasks. These tasks are data exercises, not writing exercises: the correct answer comes from combining the local request/template with current environment records and deterministic calculations.

## Required Workflow

1. Read the user prompt, every local payload, and the answer template before calculating. Treat the template as the output contract: required keys, enum values, field order, item order, and rounding precision all come from it.
2. Read [references/asteria-workflow.md](references/asteria-workflow.md) before using environment data, computing portfolio metrics, calculating correlations, or deriving allocation views.
3. Use the shared Asteria environment as the current book of record. Local payloads often contain stale snapshots, prior-week shortlists, or desk notes; use them for scope and preferences only unless the template explicitly says otherwise.
4. Fetch current data only from endpoints documented by the task or environment access file. Do not inspect test answers, evaluator code, hidden tasks, or unrelated paths.
5. Build the answer from current records, then validate it against the template:
   - Include exactly the requested JSON object and no narrative text.
   - Preserve requested top-level key order and row order.
   - Sort pairs, instruments, sleeves, or actions exactly as the template says.