Individual skill

investigation-review-hub-gap-analysis

Produce a structured JSON gap / remediation / readiness analysis for a legal investigation matter by querying the shared Investigation Review Hub over the network. Use when a task gives a matter ID, a per-task answer_template.json schema, and asks for production gaps, retention/preservation losses, privilege defects, responsiveness miscodes, QC findings, category coverage, metrics, and a prioritized action plan — returned as a single JSON object.

experiments/claude_code_glm_5_2_max/reports/skills/task_group_017/fewshot/fewshot_attempt_03/SKILL.md

Read pinned source

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: Instructions only
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 · 10,218 bytes
SKILL.mdcore · 10,218 bytes
SKILL.mdcore · 10,218 bytes
SKILL.mdcore · 10,218 bytes
SKILL.mdcore · 10,218 bytes
SKILL.mdcore · 10,218 bytes
references/hub_endpoints.mddoc · 4,381 bytes
references/issue_taxonomy.mddoc · 7,604 bytes
references/output_rules.mddoc · 3,878 bytes

Read excerpt


# Investigation Review Hub — Structured Gap / Remediation Analysis

This skill handles a family of tasks that all share one shape: a legal or regulatory
matter (grand jury subpoena, SEC subpoena, DOJ antitrust, environmental) needs a
**structured JSON** analysis of production gaps, preservation/retention losses, privilege
defects, responsiveness miscoding, and QC findings, plus a prioritized action plan. The
single source of record is the shared **Investigation Review Hub**, reached only over the
network. The output must be exactly one JSON object conforming to the task's own
`answer_template.json`.

The five task variants observed differ only in which top-level keys and enums the template
requires (rolling-production gap analysis, retention/hold gap review, cross-system
remediation dashboard, production-readiness review). The *method* below is the same for all
of them. **Treat the per-task `answer_template.json` as the schema authority** — read it