Individual skill
engineering-portfolio-auditor
Analyze engineering portfolio environments for closed-work mix, SLA aging, and release-readiness tasks. Use when a prompt asks Codex to inspect work items, mix targets, SLA policy, releases, milestones, blockers, or dependencies and return an exact JSON answer following a supplied template.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_024/reflect-3/reflect-3_attempt_03/SKILL.md
Source commit 5082a777379156a048881e94940d640702e5e09a
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- 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.
- 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.
Read excerpt
# Engineering Portfolio Auditor
## Core Workflow
1. Read the user prompt and answer template first. Treat the template as the output contract: exact keys, ordering notes, rounding precision, and no prose unless requested.
2. Read the runtime access notes supplied with the task and query the provided environment for the authoritative records needed by the prompt.
3. Build a small working table before calculating: include `id`, `status`, `duplicate_of`, `team`, `product_area`, `work_type`, `labels`, `title`, `owner`, `created_at`, `due_at`, `closed_at`, `severity`, `priority`, `release_id`, and `milestone_id` when present.
4. Use authoritative current fields. Do not use stale mirror/export fields or legacy category fields to decide inclusion, completion, or category.
5. Return only JSON matching the template. Sort and round exactly as the prompt says.
## Primary Records
- Treat records with `duplicate_of` set, or current `status` of `Duplicate`, as non-primary. Report them only in duplicate or exclusion fields when the template asks.
- Treat current `status` of `Cancelled` as non-primary unless the prompt explicitly asks for cancelled records. Report them as exclusions or distractors when requested.