Menu

Individual skill

portfolio-environment-review

0upvotes

Produce schema-constrained JSON answers for task-env engineering portfolio reviews that require querying work items, mix targets, SLA policy, releases, milestones, blockers, and dependencies. Use for portfolio mix readouts, SLA aging and breach audits, and release-readiness assessments where prompts mention authoritative environment fields, stale mirror/export fields, duplicate clusters, cancelled/distractor records, exact ordering, and precise rounding.

experiments/codex_gpt5_5_xhigh/reports/skills/task_group_024/self/self_attempt_01/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

# Portfolio Environment Review

## Core Workflow

1. Read the user prompt and the answer template before querying data. Treat the template as the output contract; emit no prose when the prompt asks for JSON only.
2. Read `environment_access.md` for `GDPEVO_ENV_BASE_URL`, allowed endpoints, and the `X-Env-Token` value for restricted SQL. Do not use endpoints outside that file.
3. Query narrow slices whenever possible. Use direct GET endpoints for small reference sets and `POST /api/query` with `{"sql":"..."}` for filtered work-item slices.
4. Build all calculations from authoritative current fields such as `status`, `closed_at`, `created_at`, `due_at`, `duplicate_of`, `work_type`, `labels`, `release_id`, and `milestone_id`.
5. Ignore stale mirror/export fields as truth. `mirror_status`, `legacy_category`, and labels like `stale-export` are useful only when the template asks for acknowledgement flags or excluded distractors.
6. Exclude non-primary work from denominators: records with `status = "Duplicate"`, any non-null `duplicate_of`, and `status = "Cancelled"`. Report them only in the template fields that ask for duplicates, cancelled IDs, exclusion flags, or distractors.
7. Validate the completed object against the template shape: required keys, no extra keys when the schema says `additionalProperties: false`, exact enum strings, requested ordering, and requested decimal precision.

Useful query pattern:
Back to top