Menu

Individual skill

investigation-review-gap-dashboard

0upvotes

Create structured JSON legal investigation gap, remediation, retention, privilege, QC, and production-readiness dashboards from an Investigation Review Hub style source of record and a task-local answer template. Use when a prompt asks for matter-specific production gap analysis, subpoena category coverage, retention or preservation gap review, privilege-log corrections, QC remediation, available archive/source analysis, or prioritized action plans in a prescribed JSON schema.

experiments/codex_gpt5_5_xhigh/reports/skills/task_group_017/reflect-3/reflect-3_attempt_02/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 Gap Dashboard

## Core Workflow

1. Read the prompt, task-local answer template, and any task-local matter or request context. Extract the matter ID, deliverable type, required top-level keys, enum choices, required item fields, metric definitions, and ordering rules.
2. Use the task-designated Investigation Review Hub as the source of record. Do not inspect local environment source files, database files, generated manifests, hidden notes, answer files, or evaluation artifacts.
3. Filter every evidence pull by the requested matter ID. Treat similarly named records from other matters as contamination for the answer.
4. Build the answer from stable hub IDs. Prefer records targeted by non-noise remediation actions, explicit issue tags, exception notes, QC findings, privilege entries, retention events, and source records over routine production noise.
5. Populate only the schema requested by the local answer template. Use enum values exactly as written in the template, use integers for counts, use `null` for unknown scalar values, and use empty arrays where a list has no values.
6. Sort every list exactly as the template says before final output. Return one JSON object and no prose.

## Evidence Selection

Start with remediation/action targets when present. Exclude rows marked as routine, noise, ordinary variance, resolved, no unresolved production impact, or not immediate remediation unless the prompt or metric definition explicitly asks for broad rollups.
Back to top