Agent skill
truth-finder
Fact verification, source validation, confidence scoring
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/truth-finder-skill
SKILL.md
Truth Finder Skill
Procedures for verifying factual claims before publication.
Claim Extraction Types
- Numerical: Statistics, percentages, costs
- Temporal: Timeframes, dates, frequencies
- Causal: X causes Y
- Comparative: Better than, more than
- Regulatory: Required by law
- Attribution: According to experts
- Absolute: Always, never, all, none
Source Tier Reference
Tier 1 (95-100%): .gov.au, courts, standards, peer-reviewed Tier 2 (80-94%): .edu.au, industry bodies Tier 3 (60-79%): TED Talks (verified), industry pubs Tier 4 (40-59%): News media, Wikipedia (leads only) NEVER USE: AI-generated without verification
Confidence Scoring Formula
Base = Source Tier Score
+ Multiple sources: +10% each (max +30%)
+ Primary source: +15%
+ Recent (<1 year): +10%
+ Peer-reviewed: +15%
- Single source: -20%
- Outdated (>3 years): -15% to -30%
- Known bias: -25%
Publishing Thresholds
- 95%+: Publish with "Verified" badge
- 80-94%: Publish with citations
- 60-79%: Publish with disclaimer
- 40-59%: Human review required
- <40%: DO NOT PUBLISH
Citation Formats
- Marketing: Hover reveal
- Blog: "According to [Source], [claim]"
- Technical: Footnotes¹
- Legal: Full academic citation
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?