Individual skill

engineering-portfolio-audits

Analyze engineering portfolio work-item datasets for portfolio mix, SLA aging, and release-readiness answers. Use when Codex must produce strict JSON from work items, mix targets, SLA policy data, releases, milestones, blockers, and dependencies, especially when records contain duplicates, cancelled items, stale mirror fields, or conflicting category signals.

experiments/codex_gpt5_5_xhigh/reports/skills/task_group_024/reflect-3/reflect-3_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.

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
data 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 · 6,958 bytes
SKILL.mdcore · 6,958 bytes

Read excerpt


# Engineering Portfolio Audits

## Core Workflow

1. Read the user prompt and the supplied answer template before calculating. Match the template exactly: required keys, casing, ordering, precision, and no extra prose.
2. Load the relevant runtime access notes and retrieve the authoritative records named by the prompt. Prefer structured queries for cross-checking filters and joins.
3. Build the primary population from explicit scope fields such as team, product area, release, quarter, as-of date, and category. Do not infer scope from ID prefixes.
4. Exclude non-primary records before calculating metrics:
   - Exclude `status == "Duplicate"` and any record with `duplicate_of` set.
   - Exclude `status == "Cancelled"`.
   - Report duplicates, cancellations, or distractors only when the template asks for them.
5. Use authoritative fields for truth. Treat `mirror_status` and `legacy_category` as stale/export fields unless the prompt explicitly asks to flag that they were ignored.

## Portfolio Mix