Claim Extractor

Extracts atomic technical claims from a substacker essay draft, converting flowing intuition-first prose into a numbered list where each item is a statement that could in principle be verified or falsified. Skips non-technical sections (personal anecdote, motivation, call-to-action). Use when the Technical Reviewer starts a per-draft review. Trigger keywords — extract claims, atomic claims, technical claim list, fact-check prep.

200 stars 25 forksWriting & Content 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 claim-extractor
Manual install
git clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/claim-extractor ~/.claude/skills/claim-extractor

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

From the SKILL.md

# Claim Extractor

## Workflow

```
Per draft:
- [ ] Step 1: Segment draft by heading / section
- [ ] Step 2: Within each section, split by sentence
- [ ] Step 3: Flag sentences containing technical claims:
    - Math symbols / formulas
    - Named systems, components, algorithms
    - Quantitative assertions
    - Universal quantifiers ("always", "never", "all models")
    - Named papers / results
- [ ] Step 4: Coalesce adjacent claim sentences that argue the same thing into one claim
- [ ] Step 5: Output numbered list: {id, excerpt (≤200 chars), location}
```

## Non-claim content (skip)

- Personal anecdotes without technical assertion
- Motivation / framing
- Calls to action
- Closing maxims (unless they assert a technical fact)

## Worked example

Draft paragraph:
> Attention is O(n²). This is why context windows are expensive. Each token looks at every other token, and the matrix is n-by-n.

Extraction:
1. "Attention is O(n²) in compute and memory in a naive implementation." [§2 ¶1]
2. "Context windows are expensive because of attention's complexity." [§2 ¶1]
3. "Each token attends to every other token via an n-by-n matrix." [§2 ¶1]

## Guardrails

1. Never paraphrase aggressively. Preserve the writer's hedges.
2. Excerpts ≤200 chars verbatim.
3. Coalesce adjacent claims only if they argue the same thing.
4. Respect `[contrarian]` annotations — still extract the claim, but flag it for `classify-claim` to treat specially.
Read the full skill on GitHub

Details

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

FAQ

What does the Claim Extractor skill do?

Extracts atomic technical claims from a substacker essay draft, converting flowing intuition-first prose into a numbered list where each item is a statement that could in principle be verified or falsified. Skips non-technical sections (personal anecdote, motivation, call-to-action). Use when the Technical Reviewer starts a per-draft review. Trigger keywords — extract claims, atomic claims, technical claim list, fact-check prep.

How do I install the Claim Extractor 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 Claim Extractor 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

Classify Post to Section

200

lyndonkl/claude

Assigns a substacker draft or published post to the best-fitting section (or to unassigned) based on content + section promises in section-map.md. Used by the Editor on every draft review (to load the right voice overlay) and by the Curator in batch mode. Trigger keywords — classify post, section assignment, which section, route post, per-draft section.

Writing & Content25

Check Analogy Novelty

200

lyndonkl/claude

Cross-references each proposed analogy in a 5-framing set against substacker shared-context/analogy-catalog.md to flag reuse. Classifies each analogy as new, reused-from-catalog (and which entry), or adjacent-to-catalog (close to an existing entry but not identical). Prevents the writer from recycling "imagine a library" for the twentieth time. Use after generate-analogy-set and before presenting framings to the writer. Trigger keywords — novelty, catalog, analogy reuse, already used, imagine a library.

Writing & Content25

Claude Content Pack

117

Peiiii/skild

Content toolkit: research, writing, summarization, and insights.

Writing & Content10

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