Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lawve-ai/legal-diagram
Use when a user needs a legal or legal-adjacent Mermaid diagram from a document, pasted text, matter description, process, timeline, party map, obligation map, corporate structure, funds flow, or compliance workflow. Trigger on: "diagram this contract", "visualise this deal/matter", "map the parties", "create a timeline of events", "make an org chart", "obligation checklist", "export as HTML diagram". Not for general-purpose non-legal diagrams, pure graphic design, image generation, or legal adv
Passed 6 of 13 test cases with the skill, and 4 of 13 without it.
and 5 more in the full report
8 fixed3 passed either way9 still failing5 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
I've pasted the indemnification and dispute resolution clauses from our service agreement below. Could you create a procedural flowchart diagram that maps out the step-by-step notice timelines, cure windows, and required actions?
| Checked | Without skill | With skill |
|---|---|---|
| Presents routing gate options before drawing the flowchart. | Missed | Passed |
| Withholds the completed Mermaid diagram code prior to user confirmation. | Passed | Passed |
The instructions your model reads when the skill loads.
Standalone skill: turn legal material into a context-appropriate Mermaid diagram, with an optional downloadable HTML figure. A structure-preserving Python engine extracts a typed ground truth; directive-driven LLM enrichment fills the gaps; a selector picks the diagram type; the diagram is generated natively.
Every real diagram request runs in this fixed order: first-run check, ingest, build-mode gate, generate, report gate. Non-diagram intents short-circuit at Step 0.
Three human gates = mandatory hard stops: GATE 0 (tutorial offer), GATE A (build mode), GATE B (HTML report). Gate discipline, no exceptions:
--direct/--guided (GATE A), --html (GATE B), --tutorial (tutorial). Nothing else counts.Check explicit short-circuits first:
--tutorial. → Load workflows/tutorial.md. Stop here.shared/setup-check.md, run check_setup.py, report. Stop here.Otherwise this is a real diagram request (a file, pasted text, or a matter description). Detect first-run:
Run python scripts/first_run.py. Parse {state}: returning, first_run, or unknown. Script absent, non-zero exit, or no JSON → treat as unknown.
returning (confirmed) → no offer; user ran skill before. Continue to Step 1.first_run, unknown, or anything not a confirmed returning → GATE 0 (hard stop): "First time here. Want a quick tutorial, or go straight to your diagram?" Options: Start tutorial (recommended, list first) / Skip, straight to my diagram. Present as structured choice, or numbered plain-text list if host has no choice tool, then STOP, wait for reply. After answer, run python scripts/first_run.py --mark to record offer (best-effort; on unknown state with no writable disk, mark may not persist, fine). Then: tutorial → load workflows/tutorial.md, stop; skip → continue to Step 1.unknown defaults to offering, not suppressing: surface the choice, do not decide for user. Suppress only on confirmed returning. Tutorial stays reachable any time by keyword.
Detect input: file path, pasted text, or conversation/matter description. Load shared/setup-check.md (session-cached).
Multi-file scope gate (2+ files) ⛔: mandatory hard stop unless user already stated scope. Present as structured choice, or numbered plain-text list if host has no choice tool, then STOP, wait for reply. Options: One combined diagram / One per document. Never infer scope from wording. Store diagram_scope. Single file, or scope user explicitly stated → skip.
Run Pass 1 only (deterministic manifest, no LLM): workflows/extract.md Steps 0-2. Store the result as manifest_cache and pass it to the chosen lane so Pass 1 never re-runs. Matter-description-only input (no docs) has no Pass 1 counts; proceed without them.
test cases passed, vs 4 / 13 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.