Menu

Individual skill

portfolio-env-review

Use when answering engineering portfolio environment tasks that require JSON-only portfolio mix, SLA aging, or release readiness analysis from work item, mix target, SLA, release, milestone, blocker, dependency, and restricted SQL endpoints.

experiments/codex_gpt5_5_xhigh/reports/skills/task_group_024/fewshot/fewshot_attempt_03/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.

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

# Portfolio Environment Review

Use this skill for tasks that ask for a structured JSON answer from the shared engineering portfolio environment. The common task families are portfolio-mix reviews, SLA aging audits, and release-readiness assessments.

## Core Workflow

1. Read the user prompt, every file in the current task input payloads, and the answer template/schema before querying data.
2. Read the runtime access file for the environment base URL, token, and allowed endpoints. Do not hardcode training-run values.
3. Fetch authoritative data from the API. Prefer endpoint JSON for full objects; use `POST /api/query` with body `{"sql": "SELECT ..."}` for focused filters or joins. The query endpoint accepts only SELECT statements and returns `columns`, `rows`, `row_count`, and `truncated`.
4. Treat `work_items.status`, `closed_at`, `duplicate_of`, `release_id`, `milestone_id`, labels, and `work_type` as authoritative. Ignore `mirror_status` and `legacy_category` for truth unless the prompt explicitly asks to audit stale fields.
5. Build the requested answer from current environment data, then validate it exactly against the provided template: required keys, enum values, ordering, rounding precision, and JSON-only output.

## Work Item Conventions