Agent Skills › Abilityai/trinity › dd-verification

dd-verification

GitHub

提供针对商业计划书和创始人陈述中声明的验证方法论，包括提取可测试主张、查找独立来源、交叉比对及输出结构化验证结果，以评估市场、团队等关键信息的真实性。

docs/demos/vc-due-diligence/skills/dd-verification/SKILL.md Abilityai/trinity

触发场景

分析商业计划书中的市场或财务数据核实创始人背景或公司竞争优势

安装

npx skills add Abilityai/trinity --skill dd-verification -g -y

更多选项

非标准路径

npx skills add https://github.com/Abilityai/trinity/tree/main/docs/demos/vc-due-diligence/skills/dd-verification -g -y

不安装直接使用

npx skills use Abilityai/trinity@dd-verification

指定 Agent (Claude Code)

npx skills add Abilityai/trinity --skill dd-verification -a claude-code -g -y

安装 repo 全部 skill

npx skills add Abilityai/trinity --all -g -y

预览 repo 内 skill

npx skills add Abilityai/trinity --list

SKILL.md

Frontmatter

{
    "name": "dd-verification",
    "description": "Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning."
}

Claim Verification Methodology

When analyzing claims from pitch decks, founder statements, or company materials, follow this rigorous verification process.

Verification Levels

Assign one of these confidence levels to every claim:

Level	Definition	Requirements
VERIFIED	Confirmed via 2+ independent sources	Multiple credible sources agree
PARTIALLY VERIFIED	Some evidence supports, gaps remain	One credible source + logical consistency
UNVERIFIED	Cannot confirm with available data	No independent sources found
CONTRADICTED	Evidence conflicts with claim	Sources disagree with stated claim

Verification Process

1. Identify the Claim

Extract the specific, testable assertion:

❌ "We're growing fast" (vague)
✅ "We grew 300% YoY in 2024" (specific, testable)

2. Find Independent Sources

Never rely solely on company-provided materials. Seek:

Public filings (SEC, state records)
Third-party data providers (Crunchbase, PitchBook, LinkedIn)
Press coverage (with dates)
Customer reviews and testimonials
Industry reports from analysts

3. Cross-Reference

Compare across sources:

Do numbers align within reasonable variance (±10%)?
Are timelines consistent?
Do different sources tell the same story?

4. Document Everything

For each verified claim, record:

{
  "claim": "The specific claim text",
  "confidence": "VERIFIED | PARTIALLY VERIFIED | UNVERIFIED | CONTRADICTED",
  "sources": [
    {"name": "Source name", "url": "URL if available", "date": "YYYY-MM-DD"}
  ],
  "notes": "Any caveats or context"
}

Red Flags

Watch for these warning signs:

Round numbers without context ("$10M ARR exactly")
Claims that can't be independently verified
Metrics that don't match industry standards
Vague timeframes ("recently", "soon")
Comparisons without clear methodology

Output Format

Include a verification summary in your analysis:

{
  "verification_summary": {
    "total_claims_analyzed": 15,
    "verified": 8,
    "partially_verified": 4,
    "unverified": 2,
    "contradicted": 1
  },
  "key_concerns": [
    "Market size claim contradicted by industry reports",
    "Founder employment dates don't match LinkedIn"
  ]
}