Generates standalone interactive HTML "deal cards" that translate complex regulations into negotiation-ready reference tools, systematically distinguishing mandatory obligations from negotiable implementation choices. Use when the user needs an interactive regulatory guide for (1) contract negotiation support, (2) client education or internal training, (3) regulatory briefings for commercial stakeholders, or (4) structured comparison between required and flexible compliance paths. Primary focus on EU digital regulation (Data Act, AI Act, CRA, DORA, NIS2, GDPR) but the structural pattern transfers to any regulation where separating hard obligations from implementation choice is the point. Supports bilingual output where the jurisdiction calls for it.
npx skills add https://github.com/lawve-ai/awesome-legal-skills --skill regulatory-deal-card-generator-patrick-munro
Produces a single self-contained HTML file that presents a regulation as an interactive "deal card" for use in negotiation, advisory, or training settings. The output clearly separates what the law compels from what it leaves open to the parties. This matters because most regulatory guides collapse the two together, which wastes negotiation capital on obligations that are not negotiable and leaves genuine flexibility on the table.
A single HTML file, inline CSS and JS, no external dependencies beyond optional web fonts. Offline-capable. Print-friendly. Designed to be opened in a browser and used as a working tool, not a static reference.
Core visible components:
Every row in the deal card answers three questions, in this order:
A row that cannot distinguish (2) from (3) is a row that has not been thought through. Force the distinction even when it is uncomfortable, and flag genuine ambiguity explicitly rather than hiding it in neutral prose.
references/html-template.md. Keep the file self-contained.Translate legal language into three registers:
Always cite specific articles. Be precise about whether a provision sits in the main text, an annex, or an implementing act. Where the provision depends on a delegated act that has not yet been adopted, say so.
Aim for at least one example per major requirement. Where a regulation has been the subject of enforcement action or published guidance, incorporate it. Where the regulation is so new that no enforcement exists, say that too, rather than padding with hypotheticals presented as settled practice.
Every row carries a visible risk level:
| Severity | Meaning |
|---|---|
| HIGH | Material administrative fines, criminal penalties, or private rights of action on the table |
| MEDIUM | Administrative sanctions possible, supervisory action likely |
| LOW | Best practice; non-compliance unlikely to be directly sanctioned but may affect later enforcement posture |
Risk level is about the consequence of non-compliance, not about how easy compliance is.
See references/html-template.md for the full template, including:
The template is a starting point. Adapt the copy and structure to the specific regulation. Keep the visual consistency.
For jurisdictions where bilingual material is standard (German and English for DACH commercial work, French and English for dual-filing contexts, etc.), the template supports a language toggle. Two patterns:
Do not machine-translate legal text. If you cannot produce accurate parallel legal text in both languages, produce one language and note the translation gap.
Before finalizing:
The deal card is a negotiation and training aid. It is not legal advice and does not substitute for qualified counsel on specific matters. Include a visible disclaimer in the output along these lines:
> "This deal card reflects the regulation as of [date]. Regulations evolve; guidance and enforcement practice evolve faster. Verify current text before relying on this document for any binding decision. Specific matters require qualified legal counsel in the applicable jurisdiction."
Save generated files with a clear naming convention:
[regulation-short-name]-deal-card-[YYYY-MM-DD].html
Example: data-act-deal-card-2026-04-23.html
Generate Hugging Face Hub (huggingface_hub) release notes from cached PR JSON files. Use when asked to draft release notes from PR files.
> Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.
> Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment. Do NOT use for writing inference code, choosing models, or PhysicsNeMo questions.
Tokenize, tag, and analyze natural language text using Apple's NaturalLanguage framework and translate between languages with the Translation framework. Use when adding language identification, sentiment analysis, named entity recognition, part-of-speech tagging, text embeddings, or in-app translation to iOS/macOS/visionOS apps.
Use as stage 2 of the Butterbase journey, after journey-idea has written 01-idea.md. Translates the idea + capability map into a concrete Butterbase plan — tables (with columns/types/RLS shape), auth providers, function list (name + trigger), storage buckets, AI/RAG/realtime/durable usage, and the chosen frontend stack. In hackathon mode, ruthlessly cuts scope into a "ship now" vs "post-hackathon" split. Produces docs/butterbase/02-plan.md.
| Extract per-subsection “anchor facts” (NO PROSE) from evidence packs so the writer is forced to include concrete numbers/benchmarks/limitations instead of generic summaries.
Authors Apache Airflow DAGs declaratively from dag-factory YAML configs. Use when building DAGs declaratively from YAML via dag-factory; creating/editing dag-factory templates/YAML configs,reating/editing dag-factory YAML configs, defaults, dynamic tasks, datasets, or callbacks; or validating dag-factory configurations; upgrading or re-pinning dag-factory.
>- into writable context) under ~25k tokens, separate "read" from "edit", delegate breadth to a read-only repo-map, and drop files once edited. Use when an LLM coder-agent edits multiple files, when the working set must stay focused, or when the model starts editing the wrong file / missing targets because too much context dilutes attention. Search working file budget, context dilution, lost in the middle.
Take lawve-ai/regulatory-deal-card-generator-patrick-munro from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.