ai-inventory
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer,…
Open gaps tracker — what's flagged and not yet closed. Use when the user asks "what gaps are open", "gap tracker", "remediation status", or wants to close (--close GAP-ID) or risk-accept (--accept GAP-ID) a tracked gap.
$ npx -y skills add anthropics/claude-for-legal --skill gaps --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/gapsContext preview
The summary Claude sees to decide when to auto-load this skill.
Open gaps tracker — what's flagged and not yet closed. Use when the user asks "what gaps are open", "gap tracker", "remediation status", or wants to close (--close GAP-ID) or risk-accept (--accept GAP-ID) a tracked gap.
name: gaps description: Open gaps tracker — what's flagged and not yet closed. Use when the user asks "what gaps are open", "gap tracker", "remediation status", or wants to close (--close GAP-ID) or risk-accept (--accept GAP-ID) a tracked gap. argument-hint: "[optional: --close GAP-ID | --accept GAP-ID]"
1. Read the gap tracker at `~/.claude/plugins/config/claude-for-legal/regulatory-legal/gap-tracker.yaml`. 2. If `--close`: mark gap closed with resolution note. 3. If `--accept`: record the risk-acceptance rationale and acceptor, status → risk-accepted. 4. Otherwise: report open gaps by age and materiality.
> Detailed tracker schema, status-report format, owner-notification logic (per-send confirmation, no exceptions), reminder cadence, the close/risk-accept modes, and the consequential-action gate live in the **gap-surfacer** reference skill — load it before doing substantive work.
Reference agents, skills, and data connectors for the legal workflows we see most — in-house commercial, privacy, product, corporate, employment, litigation, regulatory, AI governance, IP, and the learning side of the practice (law school clinics and
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer,…
Run an AI impact assessment — structured intake, risk analysis, regulatory classification per…
Run the cold-start interview — learns your AI governance practice and writes…
Guided customization of your AI governance practice profile — change one thing without…
Manage matter workspaces — new, list, switch, close, or detach (practice-level).…
Keep the AI policy current with practice — weekly sweep of saved AIAs, triage results, and…