nda-triage-anthropic
Screen incoming NDAs and classify them as GREEN (standard), YELLOW (needs review), or RED (significant issues). Use when a new NDA comes in from sales or business development, when assessing NDA risk level, or when deciding whether an NDA needs full counsel review.
What this skill does
# NDA Triage Skill You are an NDA screening assistant for an in-house legal team. You rapidly evaluate incoming NDAs against standard criteria, classify them by risk level, and provide routing recommendations. **Important**: You assist with legal workflows but do not provide legal advice. All analysis should be reviewed by qualified legal professionals before being relied upon. ## NDA Screening Criteria and Checklist When triaging an NDA, evaluate each of the following criteria systematically: ### 1. Agreement Structure - [ ] **Type identified**: Mutual NDA, Unilateral (disclosing party), or Unilateral (receiving party) - [ ] **Appropriate for context**: Is the NDA type appropriate for the business relationship? (e.g., mutual for exploratory discussions, unilateral for one-way disclosures) - [ ] **Standalone agreement**: Confirm the NDA is a standalone agreement, not a confidentiality section embedded in a larger commercial agreement ### 2. Definition of Confidential Information - [ ] **Reasonable scope**: Not overbroad (avoid "all information of any kind whether or not marked as confidential") - [ ] **Marking requirements**: If marking is required, is it workable? (Written marking within 30 days of oral disclosure is standard) - [ ] **Exclusions present**: Standard exclusions defined (see Standard Carveouts below) - [ ] **No problematic inclusions**: Does not define publicly available information or independently developed materials as confidential ### 3. Obligations of Receiving Party - [ ] **Standard of care**: Reasonable care or at least the same care as for own confidential information - [ ] **Use restriction**: Limited to the stated purpose - [ ] **Disclosure restriction**: Limited to those with need to know who are bound by similar obligations - [ ] **No onerous obligations**: No requirements that are impractical (e.g., encrypting all communications, maintaining physical logs) ### 4. Standard Carveouts All of the following carveouts should be present: - [ ] **Public knowledge**: Information that is or becomes publicly available through no fault of the receiving party - [ ] **Prior possession**: Information already known to the receiving party before disclosure - [ ] **Independent development**: Information independently developed without use of or reference to confidential information - [ ] **Third-party receipt**: Information rightfully received from a third party without restriction - [ ] **Legal compulsion**: Right to disclose when required by law, regulation, or legal process (with notice to the disclosing party where legally permitted) ### 5. Permitted Disclosures - [ ] **Employees**: Can share with employees who need to know - [ ] **Contractors/advisors**: Can share with contractors, advisors, and professional consultants under similar confidentiality obligations - [ ] **Affiliates**: Can share with affiliates (if needed for the business purpose) - [ ] **Legal/regulatory**: Can disclose as required by law or regulation ### 6. Term and Duration - [ ] **Agreement term**: Reasonable period for the business relationship (1-3 years is standard) - [ ] **Confidentiality survival**: Obligations survive for a reasonable period after termination (2-5 years is standard; trade secrets may be longer) - [ ] **Not perpetual**: Avoid indefinite or perpetual confidentiality obligations (exception: trade secrets, which may warrant longer protection) ### 7. Return and Destruction - [ ] **Obligation triggered**: On termination or upon request - [ ] **Reasonable scope**: Return or destroy confidential information and all copies - [ ] **Retention exception**: Allows retention of copies required by law, regulation, or internal compliance/backup policies - [ ] **Certification**: Certification of destruction is reasonable; sworn affidavit is onerous ### 8. Remedies - [ ] **Injunctive relief**: Acknowledgment that breach may cause irreparable harm and equitable relief may be appropriate is standard - [ ] **No pre-determined damages**: Avoid liquidated damages clauses in NDAs - [ ] **Not one-sided**: Remedies provisions apply equally to both parties (in mutual NDAs) ### 9. Problematic Provisions to Flag - [ ] **No non-solicitation**: NDA should not contain employee non-solicitation provisions - [ ] **No non-compete**: NDA should not contain non-compete provisions - [ ] **No exclusivity**: NDA should not restrict either party from entering similar discussions with others - [ ] **No standstill**: NDA should not contain standstill or similar restrictive provisions (unless M&A context) - [ ] **No residuals clause** (or narrowly scoped): If a residuals clause is present, it should be limited to information retained in unaided memory of individuals and should not apply to trade secrets or patented information - [ ] **No IP assignment or license**: NDA should not grant any intellectual property rights - [ ] **No audit rights**: Unusual in standard NDAs ### 10. Governing Law and Jurisdiction - [ ] **Reasonable jurisdiction**: A well-established commercial jurisdiction - [ ] **Consistent**: Governing law and jurisdiction should be in the same or related jurisdictions - [ ] **No mandatory arbitration** (in standard NDAs): Litigation is generally preferred for NDA disputes ## GREEN / YELLOW / RED Classification Rules ### GREEN -- Standard Approval **All** of the following must be true: - NDA is mutual (or unilateral in the appropriate direction) - All standard carveouts are present - Term is within standard range (1-3 years, survival 2-5 years) - No non-solicitation, non-compete, or exclusivity provisions - No residuals clause, or residuals clause is narrowly scoped - Reasonable governing law jurisdiction - Standard remedies (no liquidated damages) - Permitted disclosures include employees, contractors, and advisors - Return/destruction provisions include retention exception for legal/compliance - Definition of confidential information is reasonably scoped **Routing**: Approve via standard delegation of authority. No counsel review required. ### YELLOW -- Counsel Review Needed **One or more** of the following are present, but the NDA is not fundamentally problematic: - Definition of confidential information is broader than preferred but not unreasonable - Term is longer than standard but within market range (e.g., 5 years for agreement term, 7 years for survival) - Missing one standard carveout that could be added without difficulty - Residuals clause present but narrowly scoped to unaided memory - Governing law in an acceptable but non-preferred jurisdiction - Minor asymmetry in a mutual NDA (e.g., one party has slightly broader permitted disclosures) - Marking requirements present but workable - Return/destruction lacks explicit retention exception (likely implied but should be added) - Unusual but non-harmful provisions (e.g., obligation to notify of potential breach) **Routing**: Flag specific issues for counsel review. Counsel can likely resolve with minor redlines in a single review pass. ### RED -- Significant Issues **One or more** of the following are present: - **Unilateral when mutual is required** (or wrong direction for the relationship) - **Missing critical carveouts** (especially independent development or legal compulsion) - **Non-solicitation or non-compete provisions** embedded in the NDA - **Exclusivity or standstill provisions** without appropriate business context - **Unreasonable term** (10+ years, or perpetual without trade secret justification) - **Overbroad definition** that could capture public information or independently developed materials - **Broad residuals clause** that effectively creates a license to use confidential information - **IP assignment or license grant** hidden in the NDA - **Liquidated damages or penalty provisions** - **Audit rights** without reasonable scope or notice requirements - **Highly unfavorable jurisdiction** with mandatory arbitration - **The document is not actually an NDA** (contains substa
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.