Menu

Individual skill

engineering-portfolio-review

0upvotes

Solve engineering portfolio environment analysis tasks that require JSON answers from a shared task API. Use for portfolio mix reviews, SLA aging audits, release-readiness assessments, work item classification, duplicate exclusion, stale mirror-field handling, mix target comparison, blocker/dependency analysis, and exact answer-template shaping.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_024/fewshot/codex/fewshot_attempt_03/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

# Engineering Portfolio Review

Use this skill when a task asks for a JSON answer from the shared engineering portfolio environment. The recurring task families are portfolio mix, SLA aging, and release readiness.

## Core Workflow

1. Read the user prompt, `environment_access.md`, and the requested answer template before fetching data.
2. Use the base URL and allowed endpoints from `environment_access.md`. Prefer REST endpoints. Use `POST /api/query` only when the runtime notes provide the required token or headers.
3. Build the answer from authoritative fields:
   - Trust `status`, `closed_at`, `created_at`, `due_at`, `release_id`, `milestone_id`, `duplicate_of`, `work_type`, `labels`, `title`, `team`, `product_area`, `owner`, `severity`, and `priority`.
   - Do not use `mirror_status` or `legacy_category` as truth for status, release membership, or category classification.
4. Separate primary work from duplicates and cancelled records before counting. A primary item has no `duplicate_of` and is not in `Duplicate` or `Cancelled` status.
5. Classify every included item into exactly one portfolio category using the precedence and field rules in [engineering_portfolio_rules.md](references/engineering_portfolio_rules.md).
6. Compute numeric results from counts, not story points, unless the prompt explicitly says otherwise.
Back to top