Cross-jurisdictional analysis engine for the US state consumer privacy law patchwork (CCPA/CPRA, VCDPA, CPA, CTDPA, UCPA, TDPSA, OCPA, FDBR, MCDPA, ICDPA, INCDPA, TIPA, DPDPA, NJDPA, NHDPA, NDPA, KCDPA, MODPA, MCDPA-MN, RIDTPPA, and emerging laws). Use this skill whenever the user asks anything involving applicability…
Use when the user has a vendor's published privacy policy (URL, PDF, or pasted text) and wants a fast triage assessment to decide whether deeper diligence is warranted. Produces a short structured report covering what the policy says about key data practices (collection, use, sharing, retention, transfers, rights)…
Use when you need to batch redline multiple contracts against a negotiation playbook, apply tracked changes to Word documents programmatically, or run contract review workflows with AI assistance.
Instructions for LegalQuants/Donna, covering claude.md — engineering guide for donna, 1. what donna is, in one breath, 3. architecture — the backend-for-frontend (bff), 4. repo layout and 5. dev stack — run & verify.
The autonomous architect for substantive builds. Use PROACTIVELY whenever the sponsor asks to build, design, architect, or rework a system, tool, pipeline, document, integration, or skill — anything that adds or changes a capability. It runs the full lifecycle itself (discovery interview → eval spike → design →…
Run the architect build discipline whenever the sponsor asks to build, design, architect, or rework something substantive — a system, tool, pipeline, document, integration, skill. Three sign-off gates (requirements, design+checks, verification) recorded as signoffs/gate{1,2,3}.md written by the SPONSOR; a regression…
LegalQuants community access in Claude Code — search and synthesize the community's collective knowledge (chat archive + curated knowledge vault) through one connector, with /lq:start for a personalized orientation, /lq:ask for cross-source answers, /lq:assess to take on the community's open questions, /lq:update to…
Deep, fan-out synthesis over the LegalQuants community corpus. Run when the user types /lq:ask " ". Reach for it whenever a LegalQuants question wants real thinking rather than a lookup — "what does the community actually believe about X", "what's the smart take on Y", "what am I missing on Z", "make sense of the…
LegalQuants assessment launcher — bootstraps and runs the 90-minute observed work session candidates complete for the LQ application. Invoke only when the user types /lq:assess (start, select, submit, help). Never invoke proactively.
Use when lq-mcp tools are available — judgment for navigating the LegalQuants community corpus (primary-source chat + synthesis vault) through one connector. Read the corpus's own README / index at runtime for volatile facts; the tool descriptions carry all the mechanics.
Alias for the LegalQuants onboarding — runs the same flow as /lq:start. Use only when the user types bare /lq with no subcommand. For cross-source answers use /lq:ask, for the assessment use /lq:assess. Never invoke proactively.
Share a learning with the LegalQuants community. Run when the user types /lq:share (optionally with a one-liner: /lq:share " "). Composes a short, first-person field note from the session — a title + the finding in the member's own words + an optional tag — shows the member the EXACT text that will post to the…
Cold-start interview AND returning-user greeting for the LegalQuants community knowledge plugin. Run when the user types /lq:start (bare /lq also works). First run: welcome + identity verification + practice profile + a sample query, writes profile to /.claude/plugins/config/legalquants/lq/CLAUDE.md. Subsequent runs…
Profile updater for the LegalQuants community plugin. Run when the user types /lq:update. Helps a member update their LegalQuants profile (the classic Lawyer data model) from what they tell Claude — a new project, a media mention, a sharper bio/philosophy — optionally enriched by their own community footprint…