Individual skill
engineering-portfolio-env
Solve JSON-only engineering portfolio analysis tasks against the shared task environment. Use this skill when a prompt mentions work items, portfolio mix targets, SLA aging, release readiness, milestones, blockers, dependencies, duplicate clusters, stale mirror/export fields, or asks for an answer matching input/payloads/answer_template.json from <TASK_ENV_BASE_URL>.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_024/fewshot/opencode/fewshot_attempt_01/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
- Yes
- 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.
Browse files
SKILL.mdcore · 10,155 bytes
Read excerpt
# Engineering Portfolio Environment
Use this skill to answer data-analysis prompts over the shared engineering portfolio API. The task usually asks for a single JSON object matching `input/payloads/answer_template.json`; build the answer from the environment, not from stale mirror/export fields.
## Workflow
1. Read the user prompt and the local `input/payloads/answer_template.json` before querying data. Treat the template as the required output contract: field names, enum values, ordering, rounding, and whether prose is forbidden.
2. Read `environment_access.md` only for the base URL, endpoint list, and any query-token instructions. Replace `<TASK_ENV_BASE_URL>` with that base URL.
3. Fetch the narrowest useful data. Prefer direct endpoints such as `/api/work-items/{item_id}` and `/api/releases/{release_id}` when IDs are known. If using collection endpoints, filter immediately by the prompt scope.
4. Use canonical fields from API records. For work items, prefer `status`, `closed_at`, `duplicate_of`, `team`, `product_area`, `release_id`, `milestone_id`, `work_type`, `labels`, `title`, `owner`, `severity`, `priority`, `created_at`, and `due_at`. Do not let `mirror_status` or `legacy_category` override canonical fields; only mention/report them when the answer schema explicitly asks for an ignored-stale-fields flag.
5. Separate primary records from duplicate/cancelled/distractor records before computing counts. A primary record has no `duplicate_of`, is not in `Duplicate` or `Cancelled` status, and belongs to the prompt's scope.
6. Compute using exact arithmetic, then round only at the output boundary. Emit JSON only when requested; do not include explanatory prose.
Complete statuses for this environment are `Closed`, `Done`, `Verified`, and `Deployed`. Treat `Open`, `Backlog`, `In Progress`, `Review`, `Blocked`, `Duplicate`, and `Cancelled` as non-complete or excluded according to the task.