Individual skill

investigation-review-hub-gap-analysis

Produce a structured-JSON legal e-discovery deliverable (production gap analysis, retention & litigation-hold gap review, cross-system remediation dashboard, or production-readiness review) for a single matter, sourced from a networked "Investigation Review Hub" API and conforming exactly to a provided answer_template.json. Use when a task references an Investigation Review Hub / review hub base URL, an X-API-Key, subpoena/request categories, custodian sources, privilege log, QC findings, retention events, or remediation actions, and asks for a JSON gap/remediation/readiness answer.

experiments/claude_code_opus_4_8_xhigh/reports/skills/task_group_017/fewshot/fewshot_attempt_01/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 · 15,487 bytes
SKILL.mdcore · 15,487 bytes
SKILL.mdcore · 15,487 bytes
SKILL.mdcore · 15,487 bytes
SKILL.mdcore · 15,487 bytes
SKILL.mdcore · 15,487 bytes
SKILL.mdcore · 15,487 bytes
reference/enum_crosswalks.mddoc · 5,991 bytes
reference/hub_data_model.mddoc · 4,837 bytes
reference/material_vs_noise.mddoc · 5,242 bytes
reference/metrics_and_action_plan.mddoc · 6,961 bytes
scripts/pull_matter.shruns · 2,091 bytes

Read excerpt


# Investigation Review Hub — matter gap / remediation analysis

You are acting as an e-discovery review analyst for outside counsel. A task names
one legal **matter** (e.g. `MTR-<CLIENT>-<GJ|SEC>`) and asks for a structured
**JSON** deliverable about production gaps, preservation/retention losses,
privilege defects, QC/coding defects, and a prioritized remediation plan. The
evidence lives in a read-only **Investigation Review Hub** HTTP API. Your job is
to pull that evidence, separate the **material** issues from seeded **noise**,
normalize each into the enums the task's `answer_template.json` defines, compute
the numeric metrics, and emit exactly one JSON object.

The output schema is **different for every task** (different top-level keys,
enums, and field names). Never assume the shape — read the task's
`answer_template.json` first and let it drive everything. This skill teaches the