agent-ops-article-verification
Systematically deconstruct written content into verifiable claims, validate each using search/documentation, and facilitate informed discussion through structured interviewing.
npx skills add majiayu000/claude-skill-registry --skill agent-ops-article-verification --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Article Verification Workflow ## Purpose Help writers produce high-integrity content by identifying and validating every factual claim, opinion, and assertion in an article. Systematically deconstructs content into verifiable components, validates each claim, and facilitates informed discourse through structured interviewing. ## When to Use - **Pre-publication review**: Verify content before publishing - **Editor fact-checking**: Flag concerns before content goes public - **AI output verification**: Validate LLM-generated text before use - **Content audit**: Retrospective verification of published content - **Quality assurance**: Automated claim extraction + selective human verification ## Input - Raw article text (provided directly), OR - File path to markdown/text file to analyze ## Output - Verification report saved to `.agent/docs/verification-report-{timestamp}.md` - Summary in `.agent/focus.md` --- ## Phase 1: Claim Extraction & Atomization ### Purpose Break content into granular, verifiable units for systematic analysis. ### Process 1. **Read the entire text** for full context 2. **Extract claims** using the Claimify framework: - **Selection**: Filter out unverifiable cont
- Purpose
- When to Use
- Input
- Output
- Phase 1: Claim Extraction & Atomization
- Process
- Claim Categories
- Extraction Output Format
- Phase 2: Verification & Investigation
- Verification Statuses
- Documentation Requirements
- Special Handling Rules
- Phase 3: Report Generation
- Report Template
What does the agent-ops-article-verification skill do?
Systematically deconstruct written content into verifiable claims, validate each using search/documentation, and facilitate informed discussion through structured interviewing.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill agent-ops-article-verification --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.