research-chinese-law

DeepLaw 2.0 Chinese-Law Research

DeepLaw 2.0 is a read-only Agent legal-knowledge substrate. Use its official catalog to collect bounded, version-aware evidence. It may also read a physically separate user-private legal-reference library, but those results are user-provided and never official DeepLaw sources. Do not use either scope to decide case facts, replace legal review, or inject a general legal corpus into every conversation.

Enforce the invocation gate

Proceed only when the user explicitly invokes this skill:

• Codex: $research-chinese-law
• Claude Code: /deeplaw:research-chinese-law
• OpenCode: an explicit @deeplaw request that loads research-chinese-law

If that gate is absent, continue the user's non-legal work without DeepLaw. Do not infer legal intent from a project name, a case existing in the workspace, or a lone domain word.

Even after explicit invocation, do not call DeepLaw for:

• application code, SQL, statistics, dashboards, or ordinary data work;
• OCR, PDF/DOCX extraction, summarization, rewriting, or translation alone;
• storing, searching, or summarizing case-private evidence or chat history;
• UI, session, SQLite, DuckDB, attachment, or project-management questions;
• a keyword that is only data, such as a 诈骗 category or fraud_score column.

Use exactly one tool

Use the DeepLaw MCP tool whose leaf name is exactly law_support. Hosts may add their own server or plugin prefix to that name. The prefix is not a second tool.

Do not use any other DeepLaw tool. If the server advertises a different leaf name or more than one tool, stop and report an adapter/runtime contract mismatch.

law_support routes thirteen read-only operations:

• search: return a bounded evidence-card set;
• get: fetch one exact segment selected by segment_id;
• verify: verify one segment_id and receipt_id pair;
• release_info: inspect the active immutable release.
• private_search: search only the user-private legal-reference snapshot;
• private_get: fetch one exact private segment;
• private_verify: verify one private snapshot receipt;
• private_info: inspect the current private snapshot;
• federated_context: compile separately admitted official, private, and explicitly enabled Agent-interpretation partitions under one bounded plan.
• capabilities: read deterministic evidence capabilities for one exact segment_id;
• challenge_trace: build one bounded deterministic Authoritative Pack trace for a query;
• challenge_get: fetch one exact retained trace by trace_id;
• challenge_replay: replay and verify one supplied closed trace.