Individual skill
investigation-review-hub-gap-analysis
Use this skill whenever a task asks for a structured JSON legal or eDiscovery analysis from an Investigation Review Hub, especially subpoena, grand jury, SEC, DOJ, production readiness, remediation dashboard, retention gap, privilege-log, QC, or custodian-source gap tasks with TASK_ENV_BASE_URL and input/payloads/answer_template.json. It guides Codex to query the hub as source of record, normalize stable IDs and category impacts, compute metrics, and return schema-valid JSON only.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_017/fewshot/cc/fewshot_attempt_03/SKILL.md
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 · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesSKILL.mdcore · 10,531 bytesscripts/hub_dump.pyruns · 6,723 bytesscripts/validate_template_answer.pyruns · 9,091 bytes
Read excerpt
# Investigation Review Hub Gap Analysis
Use this skill to produce a final JSON object for legal investigation review tasks where the evidence lives in a running Investigation Review Hub and the required shape is defined by `input/payloads/answer_template.json`.
The winning behavior is systematic evidence collection, schema-first normalization, and strict final validation. Do not rely on narrative summaries or partial endpoint browsing when the task asks for structured production, retention, privilege, QC, or remediation analysis.
## Source Boundary
Use only:
- The current task prompt.
- Files under the task input directory, especially `input/payloads/answer_template.json` and any local context payloads.
- The running Investigation Review Hub endpoints named in the prompt or context payloads.
- `environment_access.md`, when present, only to obtain the base URL or network access details for the running hub.