Menu

Individual skill

investigation-review-hub

0upvotes

Use for legal investigation review tasks that require structured JSON from an Investigation Review Hub, including production gap analysis, retention and litigation-hold loss review, SEC/DOJ remediation dashboards, privilege-log/QC production-readiness reviews, and cross-system action plans based on hub endpoints plus task-local answer templates.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_017/fewshot/deepagents/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

# Investigation Review Hub

## Workflow

1. Read the task prompt and every task-local payload, especially `answer_template.json` and any `request_context.json`, `review_scope.json`, or `matter_context.json`.
2. Treat `answer_template.json` as the output contract. Preserve required top-level keys, item keys, enum values, nullability, ordering rules, and numeric precision exactly. Return one JSON object only.
3. Use only the task-local payloads and the running Investigation Review Hub. Do not inspect environment source, database files, generated data files, hidden manifests, task answers, or evaluator files.
4. Determine the hub base URL from the task. If the prompt uses `<TASK_ENV_BASE_URL>`, use the environment access information supplied with the task only to get the base URL. Use any task-provided SQL API header exactly as given.
5. Pull all hub evidence for the requested `matter_id`. Prefer [scripts/fetch_hub_matter.py](scripts/fetch_hub_matter.py) when SQL access is available. Run it from the skill package directory, or replace the script path with the resolved path to the skill resource:

```bash
python scripts/fetch_hub_matter.py --base-url "$TASK_ENV_BASE_URL" --matter-id "$MATTER_ID" --api-key "$API_KEY" > hub.json
```
Back to top