Individual skill
investigation-review
Analyze e-discovery review hub data for production gap analysis, retention and litigation-hold reviews, cross-system remediation dashboards, and production-readiness assessments. Use when the task requires structured JSON gap/remediation deliverables from the Investigation Review Hub — matters, subpoena categories, productions, custodian sources, review documents, privilege logs, QC findings, retention events, and remediation actions.
experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_017/fewshot/codex/fewshot_attempt_01/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
- Network or broad shell
- 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
- data 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 · 8,707 bytesSKILL.mdcore · 8,707 bytesagents/openai.yamlasset · 300 bytesreferences/api-guide.mddoc · 4,037 bytesreferences/schema.mddoc · 8,139 bytesscripts/query_hub.pyruns · 2,349 bytes
Read excerpt
# Investigation Review Hub
## Overview
Use the Investigation Review Hub REST API as the sole source of record for e-discovery review tasks. Every task produces a single JSON object conforming to an answer template. The hub provides nine read-only GET endpoints, a schema endpoint, and a POST `/api/query` endpoint for SQL queries.
## Quick-Start Workflow
1. **Read the task prompt and answer template** — the template defines required keys, ordering rules, enums, field types, and numeric precision. It is the output contract.
2. **Fetch the matter** — call `GET /api/matters`, filter by `matter_id` from the prompt, and confirm the matter exists.
3. **Fetch subpoena categories** — call `GET /api/subpoena-categories?matter_id=...` to get all request category codes and their titles.
4. **Fetch all evidence tables** — call every evidence GET endpoint for the matter, or use `POST /api/query` when cross-table joins or full result sets (beyond GET pagination) are needed.
5. **Analyze gaps and risks** — cross-reference the evidence tables to find material gaps: privilege log gaps, responsiveness miscodes, collection gaps, preservation failures, retention losses, third-party waivers, over-designations, and zero-claim contradictions.
6. **Build the answer JSON** — use stable hub record IDs for all keys, sort lists per the template's ordering rules, use only the template's enum values, and compute metrics as whole integers.