Individual skill
advisory-planning-json
Generate structured JSON outputs for private wealth advisory planning tasks that use the task-group advisory API, including Roth/RMD conversion summaries, ILIT Crummey funding cycles, GRAT versus CRAT trust comparisons, and combined estate liquidity action plans. Use when the prompt provides API_BASE or an advisory API base URL, a client ID, request memo, and answer_template.json.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_008/fewshot/codex/fewshot_attempt_02/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
- engineering 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 · 4,450 bytesSKILL.mdcore · 4,450 bytesSKILL.mdcore · 4,450 bytesSKILL.mdcore · 4,450 bytesagents/openai.yamlasset · 229 bytesscripts/advisory_planning_solver.pyruns · 24,136 bytes
Read excerpt
# Advisory Planning JSON
## Core Workflow
1. Read `prompt.txt`, `payloads/request_memo.md`, and `payloads/answer_template.json`.
2. Infer `client_id`, `task_id`, requested `analysis_type`, and any memo horizon year before querying the API.
3. Query only the advisory API records needed for that client. Prefer client-filtered calls such as `/api/source-documents?client_id=...`, `/api/retirement-accounts?client_id=...`, `/api/life-insurance?client_id=...`, and `/api/trust-candidates?client_id=...`, plus `/api/clients/{client_id}`, `/api/policies/tax`, and `/api/rmd-factors`.
4. Resolve conflicting facts by source priority: `SIGNED_PROFILE`, then `ATTORNEY_MEMO`, then `CUSTODIAN_EXPORT`, then `CRM_NOTE`, then `STALE_MARKETING_INTAKE`. Retirement account values control from `CUSTODIAN_EXPORT`; trust candidate asset assumptions control from `ATTORNEY_MEMO`; life insurance policy records are treated as `SIGNED_PROFILE` unless the record carries a source.
5. Return only the final JSON object. Use JSON numbers for money rounded to cents, booleans for boolean fields, and ISO `YYYY-MM-DD` strings for dates.
## Helper Script
Use the bundled solver for the known advisory task family: