Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
borghei avatar

Nda Triage

  • 44 installs
  • 451 repo stars
  • Updated July 21, 2026
  • borghei/claude-skills

nda-triage is a Claude Code skill that rapidly screens incoming NDAs with a GREEN/YELLOW/RED classification and a 10-point checklist.

About

nda-triage is a skill for rapid screening of incoming NDAs, classifying each as GREEN (standard approval), YELLOW (counsel review), or RED (significant issues). It uses a 10-point checklist to evaluate structure, definitions, obligations, carveouts, and problematic provisions, then recommends routing. It is flagged experimental and does not constitute legal advice. A user runs it when triaging or routing NDAs for approval.

  • Rapid GREEN/YELLOW/RED classification of incoming NDAs
  • 10-point screening checklist with pass/fail per criterion
  • Routing recommendations by classification (business, counsel, senior counsel)

Nda Triage by the numbers

  • 44 all-time installs (skills.sh)
  • Ranked #1,686 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

nda-triage capabilities & compatibility

Capabilities
nda review · clause screening · contract triage
Use cases
research
From the docs

What nda-triage says it does

Rapid NDA screening with GREEN/YELLOW/RED classification.
SKILL.md
Uses a 10-point screening checklist to evaluate agreement structure, definitions, obligations, carveouts, and problematic provisions.
SKILL.md
GREEN (standard approval), YELLOW (counsel review), or RED (significant issues)
SKILL.md
npx skills add https://github.com/borghei/claude-skills --skill nda-triage

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs44
repo stars451
Last updatedJuly 21, 2026
Repositoryborghei/claude-skills

What it does

Screen an incoming NDA into GREEN/YELLOW/RED and route it to the right approver.

Who is it for?

Triaging incoming NDAs and routing them to business approvers or legal counsel.

Skip if: Deep clause-by-clause negotiation (use nda-review) or binding legal advice.

When should I use this skill?

You are triaging NDAs, screening non-disclosure agreements, or routing NDAs for approval.

What you get

A GREEN/YELLOW/RED classification with a 10-point checklist and a routing recommendation.

  • GREEN/YELLOW/RED classification
  • 10-point compliance checklist
  • Routing recommendation

By the numbers

  • 10-point screening checklist
  • 3-tier classification (GREEN/YELLOW/RED)
  • 5 standard carveouts checked

Files

SKILL.mdMarkdownGitHub ↗
⚠️ EXPERIMENTAL — This skill is provided for educational and informational purposes only. It does NOT constitute legal advice. All responsibility for usage rests with the user. Consult qualified legal professionals before acting on any output.

NDA Triage

Rapid NDA screening tool that classifies incoming NDAs as GREEN (standard approval), YELLOW (counsel review), or RED (significant issues). Uses a 10-point screening checklist to evaluate agreement structure, definitions, obligations, carveouts, and problematic provisions.

---

Table of Contents

---

Tools

NDA Screener

Scans NDA text for red flags and outputs GREEN/YELLOW/RED classification with reasoning.

# Screen an NDA file
python scripts/nda_screener.py nda_draft.txt

# JSON output for integration
python scripts/nda_screener.py incoming_nda.md --json

# Save screening results
python scripts/nda_screener.py nda_draft.txt --output screening.json --json

What it detects:

  • Missing standard carveouts (public knowledge, prior possession, independent development, third-party receipt, legal compulsion)
  • Non-solicitation and non-compete clauses
  • Perpetual confidentiality obligations
  • Overbroad definition of confidential information
  • Residuals clauses granting usage rights to ideas/concepts
  • IP assignment or license grants
  • Liquidated damages provisions
  • Unlimited audit rights
  • One-sided obligations

Classification Rules:

LevelCriteriaRouting
GREENAll 5 carveouts present, no problematic provisions, standard structureBusiness approver; no counsel needed
YELLOW1-2 missing carveouts, minor problematic provisions, or non-standard termsLegal counsel review within 48 hours
RED3+ missing carveouts, non-compete/non-solicitation, IP assignment, perpetual term with no exitSenior counsel review; do not sign

---

NDA Checklist

Generates a compliance checklist for an NDA, checking all 10 screening criteria with pass/fail status.

# Generate checklist for an NDA
python scripts/nda_checklist.py nda_draft.txt

# JSON output
python scripts/nda_checklist.py nda_draft.txt --json

# Save checklist
python scripts/nda_checklist.py nda_draft.txt --output checklist.json --json

10-Point Screening Criteria:

#CriterionWhat It Checks
1Agreement StructureMutual vs. one-way; parties identified; purpose stated
2Definition of Confidential InfoScope, specificity, marking requirements
3ObligationsStandard of care, use restrictions, disclosure limits
4Standard Carveouts5 required: public knowledge, prior possession, independent development, third-party receipt, legal compulsion
5Permitted DisclosuresRepresentatives, advisors, affiliates with need-to-know
6Term & DurationReasonable term, survival period, obligations after expiry
7Return/DestructionObligation to return or destroy upon request/termination
8RemediesInjunctive relief, damages, indemnification scope
9Problematic ProvisionsNon-solicitation, non-compete, exclusivity, residuals, IP assignment, audit rights
10Governing LawJurisdiction, dispute resolution mechanism

---

Reference Guides

NDA Screening Criteria

references/nda_screening_criteria.md

Complete evaluation reference covering:

  • All 10 screening criteria with detailed sub-items
  • GREEN/YELLOW/RED classification rules with specific examples
  • Common NDA issues with standard positions
  • Redline approaches for common problems

---

Workflows

Standard NDA Triage

1. Receive NDA -- Save as .txt or .md file 2. Screen -- Run nda_screener.py for quick RED/YELLOW/GREEN classification 3. Checklist -- Run nda_checklist.py for detailed 10-point evaluation 4. Route -- Follow routing recommendations based on classification 5. Track -- Log screening result and routing decision

Bulk NDA Processing

# Screen multiple NDAs
for nda in ndas/*.txt; do
  echo "=== $nda ==="
  python scripts/nda_screener.py "$nda"
  echo ""
done

# Generate JSON report for all NDAs
for nda in ndas/*.txt; do
  python scripts/nda_screener.py "$nda" --json --output "results/$(basename $nda .txt).json"
done

---

Routing Recommendations

ClassificationApproverTimelineEscalation
GREENBusiness owner or designated approverSame day; sign within 24 hoursNone required
YELLOWLegal counsel review48-hour turnaroundEscalate to senior counsel if no response in 72 hours
REDSenior legal counsel5 business day turnaroundEscalate to General Counsel if deal-critical

GREEN Fast-Track Conditions

All of the following must be true for GREEN classification:

  • Mutual NDA (both parties bound)
  • All 5 standard carveouts present
  • No non-solicitation, non-compete, or exclusivity clauses
  • No IP assignment or license grants
  • No residuals clause
  • Term is 2-5 years (not perpetual)
  • Return/destruction obligation present
  • Standard remedies (injunctive relief, no liquidated damages)

RED Escalation Triggers

Any one of the following triggers RED classification:

  • Non-compete clause of any scope
  • Non-solicitation clause covering employees or customers
  • IP assignment or broad license grant
  • Missing 3 or more standard carveouts
  • Perpetual obligations with no termination right
  • Liquidated damages for breach
  • Exclusivity provision

---

Troubleshooting

ProblemCauseSolution
Screener classifies everything as YELLOWNDA uses non-standard formatting that breaks pattern matchingEnsure NDA is clean plain text; remove PDF artifacts and headers/footers
Missing carveouts false positiveCarveouts are present but use unusual languageReview the full "Exceptions" or "Exclusions" section manually; the screener checks common phrasings
Non-compete not detectedNon-compete is embedded in definitions or obligations section rather than standaloneSearch the full document for "compete", "competitive", "restrict" manually
Checklist shows PASS but screener shows REDChecklist evaluates presence; screener evaluates content qualityUse both tools together; the screener's RED overrides checklist PASS
Script errors on large filesNDA text exceeds expected size (>100KB)Ensure the file contains only the NDA text, not appendices or exhibits

---

Success Criteria

  • NDA triage under 5 minutes: Automated screening replaces 30-minute manual review.
  • Zero missed RED-severity issues: Every non-compete, IP assignment, and missing carveout is flagged.
  • GREEN NDAs signed within 24 hours: Fast-track routing eliminates bottleneck for standard agreements.
  • YELLOW NDAs resolved within 48 hours: Counsel review turnaround meets SLA.
  • Consistent classification across reviewers: 10-point checklist eliminates subjective "looks fine" approvals.
  • 100% of NDAs screened before routing: No NDA reaches an approver without automated triage.

---

Scope & Limitations

Covers:

  • Pattern-based screening of NDA text for structural issues and problematic provisions
  • 10-point compliance checklist against standard NDA requirements
  • GREEN/YELLOW/RED classification with routing recommendations
  • Detection of non-solicitation, non-compete, IP assignment, residuals, and other problematic clauses
  • Missing carveout identification

Does NOT cover:

  • Legal advice -- classification is a screening aid, not a legal opinion
  • Negotiation or redlining -- use nda-review for deep clause analysis and redline generation
  • Multi-party NDAs -- optimized for bilateral (two-party) agreements
  • Industry-specific NDA requirements (healthcare, defense, government) -- patterns target commercial NDAs
  • Non-English NDAs -- pattern matching is English-language only

---

Anti-Patterns

Anti-PatternWhy It FailsBetter Approach
Signing GREEN-classified NDAs without any human reviewAutomated screening cannot catch business-context risks (e.g., NDA with a direct competitor)GREEN classification means low legal risk, not zero risk; business approver must still review
Using triage as a substitute for deep NDA review on complex dealsTriage checks structure and red flags, not clause quality or negotiation positionRun nda-review skill for M&A, joint venture, or high-value partnership NDAs
Ignoring YELLOW classifications because "it's just an NDA"YELLOW items like missing carveouts or residuals clauses create real legal exposureRoute all YELLOW NDAs to counsel; missing independent development carveout alone can cost millions
Treating all NDAs as equal regardless of counterparty relationshipNDA with a startup partner requires different scrutiny than NDA with a Fortune 500 vendorAdjust review depth based on counterparty, deal value, and information sensitivity

---

Tool Reference

nda_screener.py

Purpose: Scans NDA text for red flags and problematic provisions. Outputs GREEN/YELLOW/RED classification with detailed reasoning.

Usage:

python scripts/nda_screener.py <nda_file> [--json] [--output FILE]

Flags:

FlagShortDefaultDescription
nda_file(positional)Path to NDA text file (.txt or .md)
--jsonoffOutput in JSON format
--output-o(stdout)Write output to file

Example Output (JSON):

{
  "file": "vendor_nda.txt",
  "classification": "YELLOW",
  "red_flags": [
    {
      "id": "missing_carveout_independent_development",
      "severity": "YELLOW",
      "description": "Missing independent development carveout",
      "recommendation": "Add standard independent development exception"
    }
  ],
  "carveouts": {
    "public_knowledge": true,
    "prior_possession": true,
    "independent_development": false,
    "third_party_receipt": true,
    "legal_compulsion": true
  },
  "summary": "1 missing carveout; no critical issues. Route to counsel for review."
}

---

nda_checklist.py

Purpose: Generates a 10-point compliance checklist for an NDA, evaluating each screening criterion as PASS/FAIL with notes.

Usage:

python scripts/nda_checklist.py <nda_file> [--json] [--output FILE]

Flags:

FlagShortDefaultDescription
nda_file(positional)Path to NDA text file (.txt or .md)
--jsonoffOutput in JSON format
--output-o(stdout)Write output to file

Example Output:

NDA COMPLIANCE CHECKLIST
========================
File: vendor_nda.txt
Overall: YELLOW (8/10 PASS)

 #  Criterion                    Status  Notes
 1  Agreement Structure          PASS    Mutual NDA; both parties identified
 2  Definition of Confidential   PASS    Reasonably scoped with marking requirement
 3  Obligations                  PASS    Standard of care; use restrictions present
 4  Standard Carveouts           FAIL    Missing: independent development
 5  Permitted Disclosures        PASS    Representatives and advisors covered
 6  Term & Duration              PASS    3-year term with 2-year survival
 7  Return/Destruction           PASS    Return or destroy within 30 days
 8  Remedies                     PASS    Injunctive relief; no liquidated damages
 9  Problematic Provisions       FAIL    Residuals clause detected
10  Governing Law                PASS    Delaware law; state courts

Related skills

FAQ

How does nda-triage classify an NDA?

It outputs GREEN (business approval), YELLOW (counsel review within 48 hours), or RED (senior counsel; do not sign).

What are the 5 standard carveouts it checks?

Public knowledge, prior possession, independent development, third-party receipt, and legal compulsion.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.