Individual skill

investigation-review-gap-analysis

Produce a structured-JSON e-discovery gap / remediation dashboard for a legal-investigation matter by reading evidence from a running "Investigation Review Hub" API. Use when a task asks for a production gap analysis, retention/litigation-hold gap review, cross-system remediation dashboard, or production-readiness review for a subpoena/grand-jury/SEC/DOJ matter, and the answer must be a single JSON object conforming to a provided answer_template.json. Triggers: "Investigation Review Hub", "gap analysis", "remediation dashboard", "production readiness", "retention/litigation-hold gap", "privilege log gap", "custodian sources", matter IDs like MTR-*-GJ / MTR-*-SEC.

experiments/claude_code_opus_4_8_xhigh/reports/skills/task_group_017/fewshot/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 · 7,794 bytes
SKILL.mdcore · 7,794 bytes
references/domain_playbook.mddoc · 6,890 bytes
references/hub_api.mddoc · 5,704 bytes
references/output_contract.mddoc · 4,202 bytes

Read excerpt


# Investigation Review Hub — gap / remediation dashboard

This skill turns raw records in a running **Investigation Review Hub** into the exact JSON
dashboard a task asks for. Every task in this family follows the same shape:

> Read the matter's evidence from the hub over the network → separate material issues from
> planted decoys → classify each issue with a fixed legal-review playbook → compute numeric
> metrics → emit **one** JSON object that conforms to the task's `answer_template.json`.

The output schema, enum names, category codes, and metric names **change per task**, so the
contract is always the `answer_template.json` shipped in that task's `input/payloads/`. The
*method* below is constant. Read the three reference files for depth:

- `references/hub_api.md` — endpoints, auth, the SQL endpoint, and every table's columns.