Individual skill
engineering-portfolio-analysis
Analyze engineering portfolio environments for exact JSON portfolio mix reviews, SLA aging audits, and release-readiness assessments. Use when a task provides a shared environment with work-item, mix-target, SLA-policy, release, blocker, dependency, or milestone APIs and asks for duplicate/cancelled exclusions, stale mirror-field handling, portfolio category classification, SLA breach calculations, or release readiness scoring.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_024/fewshot/fewshot_attempt_02/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
- Yes
- 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.
Browse files
SKILL.mdcore · 8,337 bytes
Read excerpt
# Engineering Portfolio Analysis
## Core Workflow
1. Read the user prompt, `environment_access.md`, and the requested answer template before calculating.
2. Replace `<TASK_ENV_BASE_URL>` with the base URL from `environment_access.md`.
3. Fetch only the documented endpoints needed for the task. Use `GET /api/work-items` for broad filtering and per-item endpoints only to verify specific records. Use `POST /api/query` only when direct endpoints are insufficient, and include the documented `X-Env-Token` header.
4. Treat the answer template as the output contract. Match required keys, ordering notes, enum values, rounding, and whether arrays are sorted by ID, date, category order, or priority.
5. Return only the JSON object unless the prompt explicitly allows prose.
## Authoritative Fields
- Use `status`, `created_at`, `closed_at`, `due_at`, `duplicate_of`, `team`, `product_area`, `work_type`, `labels`, `title`, `owner`, `severity`, `priority`, `release_id`, and `milestone_id` as source-of-truth fields.
- Ignore stale mirror/export fields such as `mirror_status` for state and `legacy_category` for portfolio category.