Individual skill

investigation-review-hub-gap-analysis

Produce a schema-conformant JSON gap-analysis / remediation dashboard from the Investigation Review Hub for a legal-discovery matter. Use when a task points at the Investigation Review Hub (base URL like http://task-env:PORT/) and asks for a structured-JSON deliverable (rolling production gap analysis, retention/preservation review, cross-system remediation dashboard, production-readiness review, etc.) conforming to a provided answer_template.json.

experiments/claude_code_glm_5_2_max/reports/skills/task_group_017/reflect-3/reflect-3_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.

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 · 8,607 bytes
SKILL.mdcore · 8,607 bytes
SKILL.mdcore · 8,607 bytes
references/hub_tables.mddoc · 5,023 bytes
references/metric_definitions.mddoc · 3,944 bytes
references/noise_and_material.mddoc · 5,332 bytes

Read excerpt


# Investigation Review Hub — Structured Gap Analysis

This skill solves tasks that ask for a **structured JSON** deliverable about a legal-discovery matter, using a shared **Investigation Review Hub** as the source of record. The hub exposes matter metadata, subpoena categories, production stats, custodian sources, review documents, privilege-log entries, QC findings, retention events, and remediation actions.

The deliverable is always **one JSON object** that must conform to a task-specific `answer_template.json` (field names, types, enum values, ordering rules, required keys, and numeric precision are all defined there). The hard parts are (1) pulling the right data from the hub, (2) separating the few **material** records from many **decoy/noise** records, and (3) conforming exactly to the schema.

## Source of record

Use **only** the Investigation Review Hub endpoints and the task-local payload files. Never inspect environment source files, database files, seeds, manifests, or setup scripts — the prompts explicitly forbid it. Each task provides the hub base URL and API key in its `environment_access.md` / payload files; read those for the current run's access (do not assume a fixed URL/key from memory).

The hub has two ways to read data:
- **REST list endpoints** (`GET /api/matters`, `/api/subpoena-categories`, `/api/productions`, `/api/custodian-sources`, `/api/documents/search`, `/api/privilege-log`, `/api/qc-findings`, `/api/retention-events`, `/api/remediation-actions`, and `GET /api/schema`).
- **A read-only SQL endpoint**: `POST /api/query` with header `X-API-Key` set to the task-provided key, body `{"sql": "<SELECT ...>"}`. **The body key is `sql`, not `query`.** It returns `{"columns": [...], "row_count": N, "rows": [...], "truncated": bool}`.