add-golden
Curate and add documents to the golden dataset with multi-agent validation. Use when adding test data, creating golden datasets, saving examples.
npx skills add majiayu000/claude-skill-registry --skill add-golden --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.
# Add to Golden Dataset Multi-agent curation workflow for adding high-quality documents. ## Quick Start ```bash /add-golden https://example.com/article /add-golden https://arxiv.org/abs/2312.xxxxx ``` ## Phase 1: Input Collection Get URL and detect content type: - article (blog post, tech article) - tutorial (step-by-step guide) - documentation (API docs, reference) - research_paper (academic, whitepaper) ## Phase 2: Fetch and Extract Extract document structure: - Title and sections - Code blocks - Key technical terms - Metadata (author, date) ## Phase 3: Parallel Analysis (4 Agents) | Agent | Task | |-------|------| | code-quality-reviewer | Quality evaluation | | Explore #1 | Difficulty classification | | Explore #2 | Domain tagging | | Explore #3 | Test query generation | ### Quality Dimensions | Dimension | Weight | |-----------|--------| | Accuracy | 0.25 | | Coherence | 0.20 | | Depth | 0.25 | | Relevance | 0.30 | ### Difficulty Levels - trivial: Direct keyword match (>0.85 score) - easy: Common synonyms (>0.70 score) - medium: Paraphrased intent (>0.55 score) - hard: Multi-hop reasoning (>0.40 score) - adversarial: Edge cases, robustness ## Phase 4: Validation Checks - URL v
- Quick Start
- Phase 1: Input Collection
- Phase 2: Fetch and Extract
- Phase 3: Parallel Analysis (4 Agents)
- Quality Dimensions
- Difficulty Levels
- Phase 4: Validation Checks
- Phase 5: Decision Thresholds
- Phase 6: User Approval
- Phase 7: Write to Dataset
- Summary
- Related Skills
- Key Decisions
- References
What does the add-golden skill do?
Curate and add documents to the golden dataset with multi-agent validation. Use when adding test data, creating golden datasets, saving examples.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill add-golden --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.