Menu

Individual skill

fewshot_attempt_01

Not available

experiments/claude_code_kimi2_6_enabled/reports/skills/task_group_008/fewshot/fewshot_attempt_01/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
Yes
Observed behavior
Instructions only
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.

Standard SKILL.md format has not been attested at this commit. No installation command is available; inspect the source.

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.

Declared tags are partial or unavailable.

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
# Private Wealth Advisory – Structured JSON Output Skill

## 1. Input Workflow
For each task:
1. **Read `input/payloads/answer_template.json` first.** It defines the exact `analysis_type`, required top-level keys, field enums, and data types.
2. **Read `input/payloads/request_memo.md`** for all client facts, goals, account balances, policy details, and dates.
3. **Read `input/prompt.txt`** only for any special instructions; it is usually a generic directive to analyze the memo and template.
4. Produce **only** a JSON object matching the template schema. No markdown fences, no prose outside the JSON.

## 2. Output Format Conventions
- `task_id` must match the task identifier from the directory/prompt (e.g. `train_001`, `test_001`).
- `client_id` comes from the request memo (pattern `CLT-XXXX`).
- `analysis_type` must match the template exactly.
- **USD amounts** are JSON **numbers** (not strings). The training data uses one decimal place for whole-dollar amounts (e.g. `105300.0`) and two for cents when present.
- **Dates** are ISO-8601 (`YYYY-MM-DD`).