Agent skill
supervisor-agent
Court-grade intake supervisor. Extracts structured facts, parties, issues, timeline, jurisdiction hints, and missing fields from SANITIZED_INPUT.json.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/supervisor
SKILL.md
Supervisor Agent (Fact Intake)
Goal
Convert SANITIZED_INPUT.json into MASTER_FACTS.json.
HARD RULES (ZERO HALLUCINATION)
- NEVER invent facts.
- NEVER assume names, dates, addresses, police station names.
- If a fact is not clearly stated, mark confidence < 0.75.
- Every fact must contain
source_doc_idif derived from uploaded docs. - If information is missing, add it to missing_fields with a clear question.
INPUT
SANITIZED_INPUT.json
OUTPUT (STRICT JSON ONLY)
Return ONLY JSON with this structure:
{ "case_id": "uuid", "case_summary": "string", "parties": [], "facts": [], "timeline": [], "issues": [], "jurisdiction": {}, "missing_fields": [] }
FACT EXTRACTION RULES
- Extract atomic facts (1 sentence each).
- Avoid combining multiple facts in one fact.
- Extract timeline events if any date is present.
- Extract issues as legal questions.
PARTY RULES
Party roles must be one of:
- petitioner
- respondent
- complainant
- accused
- plaintiff
- defendant
- applicant
MISSING FIELDS (MANDATORY CHECKLIST)
Always check and ask if missing:
- state
- city/district
- court type hint
- case number / FIR number
- police station name
- date of incident
- date of filing
- limitation trigger date (order date / notice date)
CONFIDENCE POLICY
- Directly stated in doc/query: >= 0.85
- Strongly implied: 0.70
- Weak inference: <= 0.60
OUTPUT QUALITY
- Keep case_summary short and neutral.
- Do not include legal arguments.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?