Individual skill
investigation-review-hub-json
Structured investigation and eDiscovery review workflow for producing schema-conformant JSON answers from an Investigation Review Hub. Use when a task asks for subpoena, agency, litigation-hold, retention, production-readiness, privilege, QC, collection-gap, or remediation dashboards that rely on task-local payload schemas and hub endpoints as the source of record.
experiments/codex_gpt5_5_xhigh/reports/skills/task_group_017/self/self_attempt_03/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
- No
- 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
- operations 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
Read excerpt
# Investigation Review Hub JSON
## Core Rules
Read the user prompt and every file in the task-local `input/payloads/` directory before querying evidence. Treat local payloads as scope, labels, access hints, and output contracts only; factual business evidence must come from the running Investigation Review Hub.
Use only the access path provided by the task. If an `environment_access.md` file is present, read it for the base URL, credentials, and allowed endpoints; do not use local environment files, source code, database files, generated manifests, seeds, answer files, evaluation files, hidden notes, or setup scripts. If the prompt provides a base URL and API header directly, use those values rather than inferring from the runtime environment.
Return exactly the requested structured output. For JSON deliverables, produce one JSON object and no prose outside it.
## Evidence Workflow
1. Identify the matter ID, client-facing review type, audience, category family, and schema file from the prompt and payloads.
2. Read the answer template as the output contract: required top-level keys, item keys, enum values, field types, precision rules, and ordering rules.