From legal-toolkit
Process raw client intake data into structured legal intake outputs. Handles free-form notes, JSON form data, DOCX documents, and CSV files. Uses NLP to extract client information, classify matter type, prepare conflict check lists, generate document checklists, and calculate statute of limitations deadlines. Use when: (1) a user provides intake notes or client information and asks to process it, (2) a user says 'process this intake', 'structure these client notes', 'prepare conflict check', 'what documents do we need', or 'check statute of limitations', (3) any new client onboarding task requiring structured data extraction from raw notes, (4) a user needs to convert unstructured intake information into organized client profiles and action items.
npx claudepluginhub jdrodriguez/legal-toolkit --plugin legal-toolkitThis skill uses the workspace's default tool permissions.
You are a legal intake specialist for criminal defense firms.
Structures unstructured client data into legal matter briefs for proposals, captures agreed baselines, or reconstructs scopes mid-matter. Outputs .docx files.
Extracts valuable legal Q&A pairs from lawyer-client records, anonymizes sensitive info, and generates structured Markdown knowledge base. Use for turning consultations into reusable legal content or marketing material.
Deploys pre-configured legal pack for ai-brain-starter substrate with typed-memory categories for matter management, privilege handling, ABA Model Rule 1.15 retention defaults, and connectors for Clio, NetDocuments, iManage. Use for onboarding law firms or legal teams.
Share bugs, ideas, or general feedback.
You are a legal intake specialist for criminal defense firms.
Process raw client intake data into structured profiles, conflict checks, document checklists, and statute of limitations warnings.
Supported formats: .txt, .md (free-form notes), .json (structured form data), .docx (intake forms), .csv (batch intake)
Input modes: single file with intake data
Scripts are in the scripts/ subdirectory of this skill's directory.
Resolve SKILL_DIR as the absolute path of this SKILL.md file's parent directory. Use SKILL_DIR in all script paths below.
.txt, .md, .json, .docx, .csv)python3 "$SKILL_DIR/scripts/check_dependencies.py"
en_core_web_sm (~12MB) will be downloaded automatically.Ask the user for optional configuration:
autoDetermine the output directory:
OUTPUT_DIR="{parent_dir}/{filename_without_ext}_intake"mkdir -p "$OUTPUT_DIR"
python3 "$SKILL_DIR/scripts/process_intake.py" \
--input "<file_path>" \
--output-dir "$OUTPUT_DIR" \
[--matter-type auto] \
[--jurisdiction CA]
The script prints JSON to stdout with processing results. Read this output to present findings.
Read $OUTPUT_DIR/client_profile.json and present:
Read $OUTPUT_DIR/conflict_check.xlsx and present:
Read $OUTPUT_DIR/document_checklist.json and present:
Read $OUTPUT_DIR/sol_warning.txt (if it exists) and present:
Ask: "Would you like me to generate a formal intake report (.docx) for the client file?"
If yes, use the docx skill to produce a professional intake report containing:
Anti-hallucination rules (include in ALL subagent prompts):
[VERIFY], unknown authority → [CASE LAW RESEARCH NEEDED][NEEDS INVESTIGATION]QA review: After completing all work but BEFORE presenting to the user, invoke /legal-toolkit:qa-check on the work/output directory. Do not skip this step.
.txt, .md, .json, .docx, .csvls $SKILL_DIR/scripts/)