菜单
Minimal-frontmatter test fixture (no lq_ai namespace).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
A synthetic skill used to test C5 tool_usage surfacing; not for production use.
Use when the user asks to find, read, or cite U.S. case law on a question — locating controlling or persuasive decisions via CourtListener, reading the opinion text, and grounding any statement in what the source actually says.
Use when the user wants to compare the same handful of terms across N contracts side-by-side in a grid — what is the term, survival period, carveouts, and governing law in each of these 5 NDAs? Returns a row-per-document × column-per-question grid with citations per cell. Reference skill for the M3-C output_format - table mode; intended as a starting point for operators to fork and tune for their own contract types.
Use when the user wants to compare the substantive commercial terms across N master services agreements side-by-side — term and renewal, payment terms, limitation of liability, and indemnification posture across each agreement. Returns a row-per-document × column-per-question grid with citations per cell. MSA-tuned reference skill for the M3-C `output_format - table` mode; intended as a fork-and-tune starting point for operators reviewing MSA portfolios.
Use when the user wants to compare the substantive NDA-specific terms across N non-disclosure agreements side-by-side — the definition of Confidential Information, permitted recipients, return/destruction obligation, and remedies clause across each agreement. Returns a row-per-document × column-per-question grid with citations per cell. NDA-tuned reference skill for the M3-C `output_format - table` mode; intended as a fork-and-tune starting point for operators reviewing NDA portfolios.
Use when extracting the negotiated positions from a single prior contract as input to the Easy Playbook auto-generation pipeline. Reads a contract's text, identifies the clauses that take a substantive position on a contract issue (definition of confidential information, limitation of liability, indemnification, payment terms, etc.), and emits a structured list of {issue, clause_text, source_offsets} for downstream clustering. Output is intermediate; the in-house attorney evaluates the final assembled playbook, not this stage.
| name | beta-minimal |
| description | Minimal-frontmatter test fixture (no lq_ai namespace). |
A synthetic test skill with only name and description in the
frontmatter — mirrors the skill-creator pattern in the M1 corpus,
which predates the formal authoring guide.
This skill is loaded to verify the loader's permissive mode.
