Individual skill

investigation-review-hub

Collect evidence from the Investigation Review Hub REST API, analyze structured answer templates, and produce strictly-typed JSON outputs for legal/regulatory review workflows. Use when the task provides an Investigation Review Hub base URL, a template JSON schema, and asks for a gap analysis, remediation dashboard, retention review, privilege review, or production-readiness deliverable. Trigger on prompts containing TASK_ENV_BASE_URL, Investigation Review Hub, answer_template.json, or structured investigation deliverables with enumerated JSON schemas.

experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_017/fewshot/deepagents/fewshot_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.

agent Repository topic
ai Repository topic
benchmark Repository topic
llm Repository topic
self-evolving Repository topic
self-learning Repository topic
skills Repository topic
legal 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 · 5,516 bytes
SKILL.mdcore · 5,516 bytes
SKILL.mdcore · 5,516 bytes
references/analysis_patterns.mddoc · 8,372 bytes
references/hub_api_reference.mddoc · 5,149 bytes

Read excerpt


# Investigation Review Hub

## Workflow

Every investigation task follows the same sequence:

1. **Read all task payloads** — `prompt.txt`, every file under `input/payloads/`, especially the request-context JSON and `answer_template.json`. The template defines the exact output schema, enums, ordering rules, and numeric precision.

2. **Discover hub resources** — Call `GET /` and `GET /api/schema` at the base URL to confirm available endpoints and data shapes.

3. **Gather evidence** — Call the relevant GET endpoints (matters, subpoena-categories, productions, custodian-sources, documents/search, privilege-log, qc-findings, retention-events, remediation-actions). Use `POST /api/query` with SQL when cross-entity joins are needed.

4. **Build the answer** — Construct a single JSON object conforming exactly to the template. Return no prose outside the JSON.