Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Academic Research Skills for Claude Code: research → write → review → revise → finalize
| Date | Stars |
|---|---|
| 2026-07-31 | 40223 |
| 2026-08-09 | 41455 |
| 2026-08-18 | 42902 |
| 2026-08-19 | 43005 |
| 2026-08-20 | 43129 |
| 2026-08-21 | 43210 |
| 2026-08-22 | 43303 |
| 2026-08-23 | 43395 |
| 2026-08-24 | 43533 |
| 2026-08-25 | 43640 |
| 2026-08-26 | 43791 |
| 2026-08-27 | 43909 |
| 2026-08-28 | 44039 |
| 2026-08-29 | 44140 |
| 2026-08-30 | 44226 |
| 2026-08-31 | 44374 |
| 2026-09-01 | 44565 |
| 2026-09-02 | 45351 |
| 2026-09-03 | 45842 |
| 2026-09-04 | 46217 |
| 2026-09-05 | 46375 |
| 2026-09-06 | 46495 |
| 2026-09-07 | 46719 |
| 2026-09-08 | 46958 |
| 2026-09-09 | 47196 |
| 2026-09-10 | 47452 |
| 2026-09-11 | 47620 |
| 2026-09-12 | 47735 |
| 2026-09-13 | 47826 |
| 2026-09-14 | 47995 |
| 2026-09-15 | 48138 |
| 2026-09-16 | 48307 |
| 2026-09-17 | 48457 |
| 2026-09-18 | 48608 |
| 2026-09-19 | 48706 |
| 2026-09-20 | 48823 |
| 2026-09-21 | 48968 |
| 2026-09-22 | 49110 |
| 2026-09-23 | 49257 |
| 2026-09-24 | 49365 |
| 2026-09-25 | 49436 |
| 2026-09-26 | 49517 |
| 2026-09-27 | 49608 |
| 2026-09-28 | 49733 |
| 2026-09-29 | 49862 |
| 2026-09-30 | 49959 |
| 2026-10-01 | 50057 |
| 2026-10-02 | 50139 |
| 2026-10-03 | 50243 |
| 2026-10-04 | 50346 |
| 2026-10-05 | 50460 |
| 2026-10-06 | 50628 |
| 2026-10-07 | 50744 |
| 2026-10-08 | 50878 |
| 2026-10-09 | 51036 |
| 2026-10-10 | 51160 |
| 2026-10-11 | 51286 |
| 2026-10-12 | 51493 |
| 2026-10-13 | 51718 |
| 2026-10-14 | 51922 |
| 2026-10-15 | 52128 |
| 2026-10-16 | 52368 |
| 2026-10-17 | 52494 |
| 2026-10-18 | 52648 |
| 2026-10-19 | 52912 |
| 2026-10-20 | 53105 |
| 2026-10-21 | 53288 |
| 2026-10-22 | 53436 |
| 2026-10-23 | 53552 |
| 2026-10-24 | 53687 |
| 2026-10-25 | 53807 |
| 2026-10-26 | 53969 |
| 2026-10-27 | 54127 |
| 2026-10-28 | 54285 |
| 2026-10-29 | 54483 |
| 2026-10-30 | 54629 |
| 2026-10-31 | 54720 |
| 2026-11-01 | 54827 |
| 2026-11-02 | 54983 |
| 2026-11-03 | 55146 |
| 2026-11-04 | 55306 |
Today
+160 stars today
This week
+1.0k stars this week
This month
+4.8k stars this month
Momentum
1696.0
growth rate 1.88%/day
# Academic Research Skills for Claude Code [](https://github.com/Imbad0202/academic-research-skills/releases/tag/v3.24.0) [](https://doi.org/10.5281/zenodo.20696614) [](https://creativecommons.org/licenses/by-nc/4.0/) [](https://buymeacoffee.com/crucify020v) [简体中文版](README.zh-CN.md) | [繁體中文版](README.zh-TW.md) | [日本語版](README.ja-JP.md) | [한국어](README.ko-KR.md) | [Español](README.es-ES.md) A comprehensive suite of Claude Code skills for academic research, covering the full pipeline from research to publication. **Install in 30 seconds** (Claude Code CLI / VS Code / JetBrains, v3.7.0+): ```text /plugin marketplace add Imbad0202/academic-research-skills /plugin install academic-research-skills ``` Then try `/ars-plan` to walk through your paper structure via Socratic dialogue, or jump to [Quick install](#quick-install) for prerequisites and the traditional symlink flow. > **AI is your copilot, not the pilot.** It can draft text, including a whole paper in full mode, but the decisions stay yours, and the pipeline stops for your confirmation at every stage. It handles the grunt work (hunting down references, formatting citations, verifying data, checking logical consistency) so you can focus on the parts that actually require your brain: defining the question, choosing the method, interpreting what the data means, and deciding what comes after "I argue that." You remain the author, and you answer for every claim you submit. > > Unlike a humanizer, this tool doesn't help you hide the fact that you used AI. It helps you write better. Style Calibration learns your voice from past work. Writing Quality Check catches the patterns that make prose feel machine-generated. The goal is quality, not cheating. ### Why human-in-the-loop, not full automation? Lu et al. (2026, *Nature* 651:914-919) built **The AI Scientist** — the first fully autonomous AI research system to publish a paper through blind peer review at a top-tier ML venue (ICLR 2025 workshop, score 6.33/10 vs workshop average 4.87). Their Limitations section enumerates the failure modes that any fully-autonomous AI research pipeline inherits: implementation bugs, hallucinated results, shortcut reliance, bug-as-insight reframing, methodology fabrication, frame-lock, citation hallucinations. ARS is built on the premise that **a human researcher augmented by AI avoids these failure modes better than either alone**. Stage 2.5 and Stage 4.5 integrity gates run a 7-mode blocking checklist (see [`academic-pipeline/references/ai_research_failure_modes.md`](academic-pipeline/references/ai_research_failure_modes.md)); the reviewer offers an opt-in calibration mode that measures its own FNR/FPR against a user-supplied gold set. [**Zhao et al.**](https://arxiv.org/abs/2605.07723) (2026-05) audited 111M references across 2.5M papers on arXiv, bioRxiv, SSRN, and PMC. Their conservative estimate is 146,932 hallucinated citations for 2025 alone, with an observed mid-2024 inflection; for the bioRxiv-to-PMC pairing they report 85.3% preprint-to-published persistence. The paper describes "real citations deployed to support claims the cited references do not actually make" as an open challenge. ARS v3.7.1 added trust-chain frontmatter for source provenance; v3.7.3 added locator infrastructure (three-layer citation anchors) for future claim-level audits and surfaces advisory risk signals at cite time (ARS labels the claim-faithfulness gap internally as "L3"; this is ARS terminology, not the paper's). v3.7.x is motivated by Zhao et al.'s corpus-scale findings; corpus-scale evaluation of ARS itself remains future work. v3.8 closes the second half of the L3 gap. v3.7.3 made ever
Excerpt of 46,610 characters
Read on GitHub
Edward Cheng-I Wu
614
Lixin2026
8
Madhav Jha
3
Leo-Ricardo
1
Puneet Dixit · India
1
jo0on · South Korea
1
1
xpfo
1
Ikko Eltociear Ashimine · Japan
1
Jiaxing Yu
1
Infinity_Block · 株式会社RaJA
1
JinHyuk Sung
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:69773f3712a45c10, topic:prompt-engineering