How do I install the Cross Reference Claim skill?

Run npx skillmds add lyndonkl/cross-reference-claim in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Cross Reference Claim safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Cross Reference Claim?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Cross Reference Claim free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Cross Reference Claim?

lyndonkl (@lyndonkl) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Cross Reference Claim by lyndonkl — Agent Skill

Name: Cross Reference Claim
Rating: 4.2 (5 reviews)
Author: lyndonkl

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.

lyndonkl 7c1ae56 2.0 KB Updated Sep 9, 2026

File contents

Cross-Reference Claim

Source hierarchy (enforced)

Primary: original arXiv paper, official docs (PyTorch, CUDA, Linux), RFC, ACM/IEEE proceedings, canonical textbook (Deep Learning Goodfellow et al., DDIA Kleppmann, Jurafsky & Martin).
Secondary: author's own blog/slides when they are the primary authority; well-maintained official implementation source.
Tertiary: Wikipedia (orientation only, never as the cite).
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

Never cite a blog post as primary.
Never cite model's own recall as source.
Never invent a URL. could-not-verify with attempted-queries is better than fabrication.
48h wall-clock cap is enforced at the agent level; per-claim cap is 10 minutes of research.
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.
Primary source must contain the specific result/passage — not a reference to a result. Fetch the paper, not a blog that cites the paper.

---name: cross-reference-claimdescription: 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.--- # 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.

Frequently asked questions