Individual skill

peopleops-evidence-json

Resolve PeopleOps Console evidence tasks and produce strict JSON answers. Use when a task asks Codex to verify onboarding closeout, remote-work case readiness, leave source precedence, payroll/accrual readiness, recruitment reconciliation, folder/notice defects, audit scope, or normalized People Ops control labels from an answer_template.json file.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_012/fewshot/naive/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
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.

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

# PeopleOps Evidence JSON

Use this skill for PeopleOps Console tasks that require reading HR evidence and returning a single JSON object matching a provided `answer_template.json`.

## Core Workflow

1. Read the user prompt and `input/payloads/answer_template.json` before collecting evidence.
2. Identify the target entity from the prompt: employee id, case id, opening id, candidate id, audit id, or policy area.
3. Collect evidence from the configured task environment. Prefer the read-only API when available, then use the UI only to inspect anything the API does not expose.
4. Resolve business facts by source precedence, not by case summary alone.
5. Fill every template key with the exact requested JSON type and exact enum labels from the template.
6. Validate the JSON against the template before final response. Return only JSON unless the prompt explicitly asks otherwise.

Do not call disabled judge endpoints. Do not create comments or mutate case state unless the task explicitly asks for that side effect.
Back to top