claim-extraction
Decomposes complex text into atomic propositions and documents rebuttals.
Install
mkdir -p .claude/skills/claim-extraction-yogsoth-ai && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16125" && unzip -o skill.zip -d .claude/skills/claim-extraction-yogsoth-ai && rm skill.zipInstalls to .claude/skills/claim-extraction-yogsoth-ai
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Strategy for extracting claims from source material — identify propositions,Key capabilities
- →Identify propositions from source material
- →Decompose compound claims into atomic statements
- →Classify claim types
- →Create structured claim pages in the vault
- →Document rebuttals and counter-claims
How it works
The skill processes source material to identify claims, breaks down complex claims into simpler propositions, classifies them by type, and then creates dedicated pages in a knowledge vault for each claim.
Inputs & outputs
When to use claim-extraction
- →Decompose research arguments
- →Map logical claims
- →Document debate counter-claims
About this skill
Claim Extraction
Identify and extract claims from source material. Decomposes compound statements into atomic propositions, classifies claim types, and creates structured claim pages in the vault.
Budget Slice
| Metric | Small | Medium | Large |
|---|---|---|---|
| Sources processed | 5 | 12 | 25 |
| Claims extracted | 10 | 25 | 50 |
| Compound claims decomposed | 3 | 8 | 15 |
State Ledger
<HARD-GATE> Print before every iteration:| Metric | Target | Current | % |
|---|---|---|---|
| Sources processed | — | — | — |
| Claims extracted | — | — | — |
| Compound claims decomposed | — | — | — |
Budget Gate
Cannot exit until 80% of budget targets met.
Adversarial Completeness Probe
After budget gate passes, self-check:
- Have all major positions in the debate been captured?
- Are there implicit claims that sources assume but don't state?
- Are there claims from minority/dissenting positions?
Max 2 extra iterations if gaps found.
Tactics Available
- claim-decomposition — break compound claims into atomic propositions
SOPs Available
- claim-page-creation — create a claim page in the vault
- rebuttal-documentation — document counter-claims and rebuttals
Available Tactics
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use |
|---|---|
| knowledge-structuring-claim-decomposition | Tactic for decomposing compound claims into atomic propositions — identify logical structure, separate conjunctions, extract implicit assumptions. |
Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| claim-page-creation | SOP for creating a claim page in the vault — atomic proposition with type classification, source attribution, and initial confidence. |
| rebuttal-documentation | SOP for documenting rebuttals and counter-claims — create rebuttal pages with typed contradiction edges and source attribution. |
When not to use it
- →When the source material does not contain claims or arguments to extract
- →When only a summary of the source is needed, not a claim-by-claim breakdown
- →When the task is not related to knowledge structuring or debate mapping
Limitations
- →The skill focuses on extracting and structuring claims.
- →It requires source material to process.
- →The output is structured claim pages and rebuttal documentation.
How it compares
This skill provides a structured method for breaking down arguments into atomic claims and tracking their status in a vault, unlike general information extraction.
Compared to similar skills
claim-extraction side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| claim-extraction (this skill) | 0 | 2mo | No flags | Intermediate |
| literature-review | 559 | 2mo | Review | Advanced |
| openalex-database | 48 | 7mo | Review | Intermediate |
| market-research-reports | 38 | 7mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by yogsoth-ai
View all by yogsoth-ai →You might also like
literature-review
K-Dense-AI
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
openalex-database
davila7
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.
market-research-reports
davila7
Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter's Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix.
scientific-brainstorming
davila7
Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving.
exa-search
benjaminjackson
Search the web for content matching a query with AI-powered semantic search. Use for finding relevant web pages, research papers, news articles, code repositories, or any web content by meaning rather than just keywords.
scientific-critical-thinking
davila7
Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.