4 views
K-Dense-AI/scientific-agent-skills
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000+ scientists worldwide. 165 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
Python★ 41,713+912 that day#9 on trending
9.25%duplicated code · 15,540 of 168,069 lines
411clones in code
531code files of 3,541 scanned
3.38%duplicated over all files · 1,066 clones
The code number leaves out tests, fixtures, docs, examples, data files, styles, translations and vendored code.
Largest clones in the code
- 949 lines in 4 placespython4,946 tokensskills/latex-posters/scripts/generate_schematic_ai.py:1–949skills/literature-review/scripts/generate_schematic_ai.py:1–949skills/scientific-schematics/scripts/generate_schematic_ai.py:1–949skills/scientific-slides/scripts/generate_schematic_ai.py:1–949
1#!/usr/bin/env python3 2""" 3AI-powered scientific schematic generation using Nano Banana 2. 4 5This script uses a smart iterative refinement approach: 61. Generate initial image with Nano Banana 2 72. AI quality review using Gemini 3.6 Flash for scientific critique 83. Only regenerate if quality is below threshold for document type 94. Repeat until quality meets standards (max iterations) 10First 10 of 949 lines.
- 875 lines in 3 placespython4,068 tokensskills/docx/scripts/office/validators/base.py:1–875skills/pptx/scripts/office/validators/base.py:1–875skills/xlsx/scripts/office/validators/base.py:1–875
1""" 2Base validator with common validation logic for document files. 3""" 4 5import re 6from pathlib import Path 7 8import defusedxml.minidom 9from functools import lru_cache 10First 10 of 875 lines.
- 466 lines in 3 placespython2,005 tokensskills/docx/scripts/office/validators/docx.py:1–466skills/pptx/scripts/office/validators/docx.py:1–466skills/xlsx/scripts/office/validators/docx.py:1–466
1""" 2Validator for Word document XML files against XSD schemas. 3""" 4 5import random 6import re 7import tempfile 8import zipfile 9from pathlib import Path 10First 10 of 466 lines.
7 more
- 441 lines in 3 placespython1,986 tokens
- 232 lines in 3 placespython1,684 tokens
- 197 lines in 4 placespython1,036 tokens
- 299 lines in 3 placespython1,470 tokens
- 170 lines in 3 placespython1,128 tokens
- 173 lines in 3 placespython840 tokens
- 111 lines in 3 placespython663 tokens
Largest clones over all files, tests and data included
- 949 lines in 4 placespython4,946 tokensskills/latex-posters/scripts/generate_schematic_ai.py:1–949skills/literature-review/scripts/generate_schematic_ai.py:1–949skills/scientific-schematics/scripts/generate_schematic_ai.py:1–949skills/scientific-slides/scripts/generate_schematic_ai.py:1–949
1#!/usr/bin/env python3 2""" 3AI-powered scientific schematic generation using Nano Banana 2. 4 5This script uses a smart iterative refinement approach: 61. Generate initial image with Nano Banana 2 72. AI quality review using Gemini 3.6 Flash for scientific critique 83. Only regenerate if quality is below threshold for document type 94. Repeat until quality meets standards (max iterations) 10First 10 of 949 lines.
- 875 lines in 3 placespython4,068 tokensskills/docx/scripts/office/validators/base.py:1–875skills/pptx/scripts/office/validators/base.py:1–875skills/xlsx/scripts/office/validators/base.py:1–875
1""" 2Base validator with common validation logic for document files. 3""" 4 5import re 6from pathlib import Path 7 8import defusedxml.minidom 9from functools import lru_cache 10First 10 of 875 lines.
- 466 lines in 3 placespython2,005 tokensskills/docx/scripts/office/validators/docx.py:1–466skills/pptx/scripts/office/validators/docx.py:1–466skills/xlsx/scripts/office/validators/docx.py:1–466
1""" 2Validator for Word document XML files against XSD schemas. 3""" 4 5import random 6import re 7import tempfile 8import zipfile 9from pathlib import Path 10First 10 of 466 lines.
- 441 lines in 3 placespython1,986 tokens
- 232 lines in 3 placespython1,684 tokens
By format, code only
| Format | Files | Lines | Clones | Duplicated lines | Duplication |
|---|---|---|---|---|---|
| python | 519 | 166,947 | 411 | 15,540 | 9.31% |
| bash | 11 | 948 | 0 | 0 | 0% |
| perl | 1 | 174 | 0 | 0 | 0% |
By format, all files
| Format | Files | Lines | Clones | Duplicated lines | Duplication |
|---|---|---|---|---|---|
| python | 1,278 | 293,202 | 589 | 17,326 | 5.91% |
| json | 177 | 86,384 | 188 | 4,408 | 5.1% |
| markdown | 1,248 | 352,174 | 113 | 1,060 | 0.3% |
| markup | 12 | 6,256 | 79 | 2,150 | 34.37% |
| text | 228 | 11,017 | 39 | 179 | 1.62% |
| latex | 30 | 7,328 | 31 | 749 | 10.22% |
| bash | 279 | 7,871 | 21 | 169 | 2.15% |
| yaml | 181 | 3,426 | 3 | 38 | 1.11% |
| txt | 4 | 120 | 3 | 90 | 75% |
| mermaid | 38 | 1,800 | 0 | 0 | 0% |
Trending appearances
| Day | Rank | Stars | Files | Lines | Clones | All files | Code | Health | Commit |
|---|---|---|---|---|---|---|---|---|---|
| Sep 2, 2026 | #9 | 41,713 (+912) | 3,541 | 773,237 | 1,066 | 3.38% | 9.25% | — | 1dd0fcc |
| Sep 1, 2026 | #10 | 41,242 (+1,980) | 3,541 | 773,237 | 1,066 | 3.38% | 9.25% | — | 1dd0fcc |
Want this for your own project? Install jscpd and run jscpd ., or measure it the way the baselines were measured.