Cross Reference Claim

Finds and cites a primary source for each substacker draft claim — original arXiv paper, official documentation, RFC, canonical textbook. Source hierarchy enforced — primary > secondary > tertiary > not-a-source. Records URL, title, passage/result that settles the claim. Use after classify-claim; runs once per claim unless classification is simplified-correct with high confidence on standard undergrad material. Trigger keywords — cross-reference, primary source, citation, arXiv, RFC, paper lookup, source hierarchy.

200 stars 25 forksResearch & Science Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add lyndonkl/claude

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add lyndonkl/claude --skill cross-reference-claim
Manual install
git clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/cross-reference-claim ~/.claude/skills/cross-reference-claim

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Cross-Reference Claim

## Source hierarchy (enforced)

1. **Primary**: original arXiv paper, official docs (PyTorch, CUDA, Linux), RFC, ACM/IEEE proceedings, canonical textbook (*Deep Learning* Goodfellow et al., DDIA Kleppmann, Jurafsky & Martin).
2. **Secondary**: author's own blog/slides when they are the primary authority; well-maintained official implementation source.
3. **Tertiary**: Wikipedia (orientation only, never as the cite).
4. **Not a source**: random blog posts, Medium, X threads, unreviewed tutorials, other LLM outputs.

## Workflow

```
Per claim:
- [ ] Step 1: WebSearch with claim + likely source terms
- [ ] Step 2: WebFetch top candidate; extract specific result/passage
- [ ] Step 3: If paywalled, fall back one tier; note fallback explicitly
- [ ] Step 4: If nothing authoritative within 10 min on one claim, mark could-not-verify
- [ ] Step 5: Return {url, title, passage_or_result, tier}
```

## Guardrails

1. Never cite a blog post as primary.
2. Never cite model's own recall as source.
3. Never invent a URL. `could-not-verify` with attempted-queries is better than fabrication.
4. 48h wall-clock cap is enforced at the agent level; per-claim cap is 10 minutes of research.
5. `could-not-verify` doesn't block GO. It lands in the Could-Not-Verify section of the review; the writer decides whether to ship anyway.
6. Primary source must contain the specific result/passage — not a reference to a result. Fetch the paper, not a blog that cites the paper.
Read the full skill on GitHub

Details

Skill name
cross-reference-claim
Path
skills/cross-reference-claim/SKILL.md
Repo updated
1 September 2026

FAQ

What does the Cross Reference Claim skill do?

Finds and cites a primary source for each substacker draft claim — original arXiv paper, official documentation, RFC, canonical textbook. Source hierarchy enforced — primary > secondary > tertiary > not-a-source. Records URL, title, passage/result that settles the claim. Use after classify-claim; runs once per claim unless classification is simplified-correct with high confidence on standard undergrad material. Trigger keywords — cross-reference, primary source, citation, arXiv, RFC, paper lookup, source hierarchy.

How do I install the Cross Reference Claim skill?

Claude Code plugin: /plugin marketplace add lyndonkl/claude. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Cross Reference Claim popular?

It lives in lyndonkl/claude, which has 200 GitHub stars and 25 forks.

Related skills

Abstraction Concrete Examples

200

lyndonkl/claude

Builds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.

Testing & QA25

Academic Letter Architect

200

lyndonkl/claude

Guides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.

Research & Science25

Adr Architecture

200

lyndonkl/claude

Documents significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.

Software Development25

Design Evaluation Audit

200

lyndonkl/claude

Systematically evaluates existing designs against cognitive science principles using repeatable checklists, scoring rubrics, and severity-classified fix recommendations. Use when conducting design reviews or critiques, evaluating designs for cognitive alignment, performing quality assurance before launch, diagnosing usability issues, or choosing between design alternatives with objective criteria.

Research & Science25

Conf Abstract Enrichment

200

lyndonkl/claude

Thicken a thin or missing conference-session abstract through targeted web research so short, noisy text becomes classifiable — pulling the speaker's recent work, the linked repo or paper, and the company/product to add signal. Every enriched claim carries provenance (source URL + retrieval date) and a confidence, the enriched text is stored separately from the original (never overwriting it), and enrichment is gated so already-rich abstracts are left alone. Conference-agnostic. Use when an event record has been flagged thin by program extraction, when a session lacks enough text to classify,

Research & Science25

Discovery Interviews Surveys

200

lyndonkl/claude

Designs structured interview guides, survey instruments, and JTBD probes to learn from users while avoiding common research biases (leading questions, confirmation bias, selection bias). Use when validating product assumptions before building, discovering unmet user needs, understanding customer problems and workflows, testing concepts or positioning, researching target markets, identifying jobs-to-be-done and hiring triggers, or uncovering pain points and workarounds.

Research & Science25

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.