Individual skill
engineering-portfolio-audits
Analyze engineering portfolio task environments and produce strict JSON answers for portfolio mix, SLA aging, and release-readiness reviews. Use when prompts mention work items, mix targets, SLA policies, releases, milestones, blockers, dependencies, stale mirror/export fields, duplicate or cancelled records, <TASK_ENV_BASE_URL>, environment_access.md, or answer_template.json.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_024/self/self_attempt_02/SKILL.md
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
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 Audits
## Core Workflow
1. Read the user prompt and the referenced `answer_template.json` before querying data. Treat schema descriptions as requirements for sorting, rounding, field names, and enum choices.
2. Read `environment_access.md` for the base URL, allowed endpoints, and any query token. Use only the listed endpoints. Prefer REST endpoints; use `/api/query` only for targeted checks, passing the runtime token header from `environment_access.md`.
3. Fetch the needed datasets once and keep their top-level wrappers in mind: endpoints return objects such as `work_items`, `mix_targets`, `sla_policy`, `releases`, `milestones`, `dependencies`, and `blockers`.
4. Use authoritative fields on the core records. Do not use `mirror_status` as truth, and do not let `legacy_category` or labels such as `stale-export` override authoritative `status`, `work_type`, `release_id`, `milestone_id`, `closed_at`, or `duplicate_of`.
5. Return exactly the JSON object requested by the template. Do not include prose outside the JSON.
## Shared Record Rules
- Treat these statuses as complete: `Closed`, `Done`, `Deployed`, `Verified`.
- Treat primary/canonical work as records where `status` is not `Duplicate`, `duplicate_of` is empty, and `status` is not `Cancelled`.