Menu

Individual skill

engineering-portfolio-auditor

0upvotes

Solve endpoint-backed engineering portfolio audit tasks that ask for JSON calculations over work items, portfolio mix targets, SLA aging, duplicate clusters, blockers, dependencies, milestones, or release readiness. Use this skill whenever the prompt mentions a shared task environment, work items, mix targets, SLA policy, release readiness, portfolio categories, stale mirror fields, or duplicate/cancelled engineering records.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_024/fewshot/cc/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 Auditor

Use this skill to produce exact JSON answers for engineering portfolio tasks backed by a small REST environment. The recurring hazards are stale mirror/export fields, duplicate records that should be reported but not counted, category signals that conflict, and strict ordering/rounding rules in the answer template.

## First Pass

1. Read the user prompt and `input/payloads/answer_template.json` before calculating. Treat the template as the final output contract.
2. Read the runtime access file only for the base URL, credentials, and endpoint list. Replace any `<TASK_ENV_BASE_URL>` placeholder with that base URL.
3. Fetch authoritative data from the REST endpoints. Use `/api/query` only for filtered inspection when REST responses are too broad.
4. Build a scratch table of candidate records with `id`, `team`, `product_area`, `status`, `created_at`, `closed_at`, `due_at`, `duplicate_of`, `work_type`, `labels`, `title`, `owner`, `severity`, `priority`, `release_id`, and `milestone_id`.
5. Produce only the JSON object requested by the template. Do not include explanation text.

The bundled helper can do the repeatable calculations:
Back to top