Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/plagiarism-detection-guide
Use plagiarism detection tools and ensure manuscript originality
Passed 20 of 24 test cases with the skill, and 20 of 24 without it.
1 fixed19 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
I just ran my manuscript through a scanner and received an overall similarity score of 22%. Here is the source breakdown from the report: Source 1 (12% overlap, type: 'journal_article') and Source 2 (10% overlap, type: 'own_prior_work'). Please interpret these results by assigning an overall risk classification, explaining what this score level implies for manuscript preparation, and outlining the necessary action step for each listed source.
| Checked | Without skill | With skill |
|---|---|---|
| Classifies the 22% similarity score as moderate risk level. | Passed | Passed |
| Specifies that for journal_article sources the required action is to verify proper citation. | Passed | Passed |
| Specifies that for own_prior_work sources the required action is to check if self-plagiarism. | Missed | Passed |
The instructions your model reads when the skill loads.
A skill for using plagiarism detection tools to ensure manuscript originality before submission. Covers major detection platforms, understanding similarity reports, avoiding self-plagiarism, paraphrasing best practices, and institutional policies.
| Tool | Primary Users | Database | Cost |
|---|---|---|---|
| iThenticate | Researchers, publishers | Crossref, web, dissertations | Subscription |
| Turnitin | Universities (student work) | Student papers, web, journals | Institutional |
| Copyscape | Web content | Web pages | Per-search or subscription |
| Quetext | General | Web, academic | Free tier / Premium |
| PlagScan | Academic, corporate | Web, internal database | Per-document |
| Grammarly Premium | Writers | Web, ProQuest | Included in Premium |
Text matching (NOT idea matching):
- Tools compare your text against databases of published content
- They flag verbatim matches and close paraphrases
- They do NOT detect idea plagiarism or conceptual theft
- They do NOT understand context (quoted text may be flagged)
Common databases searched:
- Published journal articles (via Crossref, Scopus partnerships)
- Web pages and online content
- Previously submitted student papers (Turnitin only)
- Books and dissertations (varies by tool)
- Preprint servers (arXiv, SSRN)
def interpret_similarity_score(total_score: float,
test cases passed, vs 20 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.