overclaiming-check
Skill0 starsChanged 3 months agoMITView on GitHub
Detect conclusions or language that are stronger, broader, more certain, or more causal than the available evidence justifies.
In this repository101 other files it gives its agents.
- AGENTS.mdAGENTS.md
- abstract-reviewSkill
- literature-gapSkill
- methodology-reviewSkill
- paper-structureSkill
- results-discussion-alignmentSkill
- reviewer-responseSkill
- book-outlineSkill
- chapter-purposeSkill
- character-consistencySkill
- narrative-arcSkill
- pacing-checkSkill
- timeline-consistencySkill
- citation-accuracySkill
- citation-checkSkill
- citation-completenessSkill
- citation-generationSkill
- citation-relevanceSkill
- citation-styleSkill
- duplicate-reference-checkSkill
- reference-list-checkSkill
- source-claim-mappingSkill
- source-to-claim-mapSkill
- active-voiceSkill
- ambiguity-checkSkill
- clarity-checkSkill
- coherence-checkSkill
- concision-checkSkill
- grammar-checkSkill
- jargon-checkSkill
- parallelism-checkSkill
- passive-voiceSkill
- proofreadingSkill
- punctuation-checkSkill
- readability-checkSkill
- redundancy-checkSkill
- repetition-checkSkill
- spelling-checkSkill
- terminology-consistencySkill
- tone-checkSkill
- attribution-auditSkill
- claim-auditSkill
- final-document-auditSkill
- plagiarism-risk-reviewSkill
- quotation-integritySkill
- self-plagiarism-riskSkill
- source-provenanceSkill
- chapter-structureSkill
- manuscript-consistencySkill
- manuscript-readinessSkill
- manuscript-structureSkill
- title-page-checkSkill
- cover-letterSkill
- ethics-disclosure-checkSkill
- journal-fitSkill
- peer-review-readinessSkill
- submission-requirementsSkill
- coherence-checkSkill
- completeness-checkSkill
- consistency-checkSkill
- The first 60 shown.
The file
Files
Overclaiming Check
Compare claim strength with evidence strength. Inspect certainty markers, causal language, generalization scope, temporal claims, population claims, and implied mechanisms.
Flag only defensible mismatches and explain how to calibrate language without weakening a legitimately supported conclusion.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.