{"full_name":"Imbad0202/academic-research-skills","owner":"Imbad0202","name":"academic-research-skills","url":"https://github.com/Imbad0202/academic-research-skills","description":"Academic Research Skills for Claude Code: research → write → review → revise → finalize","homepage":"https://buymeacoffee.com/crucify020v","topics":[],"language":"Python","license":"NOASSERTION","avatar":"https://avatars.githubusercontent.com/u/132531341?u=20ded149dee4052c0de48cadcd5c9a2eda961c22&v=4","created_at":"2026-02-26T06:31:01Z","pushed_at":"2026-11-10T04:34:01Z","metrics":{"stars":56281,"forks":4283,"watchers":146,"issues":433,"prs":588,"releases":51,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":23},"growth":{"day":{"stars":227,"forks":14,"base_day":"2026-11-09"},"week":{"stars":1257,"forks":91,"base_day":"2026-11-03"}},"history":{"dates":["2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-09","2026-11-10"],"stars":[52847,52968,53166,53347,53481,53596,53729,54011,54166,54330,54530,54670,55024,55209,56054,56281],"forks":[4052,4060,4076,4091,4102,4114,4120,4132,4141,4151,4167,4174,4192,4210,4269,4283],"watchers":[141,143,144,146,143,143,141,142,143,143,143,143,144,145,146,146],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null]},"boards":{"daily":155,"weekly":102,"monthly":155,"weekly_rate":148},"same_owner":[],"issues":[{"number":684,"title":"Bind field/venue criteria across three consumers and measure constructive-review value","comments":8,"created_at":"2026-08-08T05:08:42Z"},{"number":1025,"title":"Windows: prefer a Python outside WindowsApps so the guard launcher does not start the Install Manager alias at all (follow-up to #1015)","comments":7,"created_at":"2026-10-26T01:26:53Z"},{"number":879,"title":"Gemini/Antigravity support?","comments":6,"created_at":"2026-09-17T10:55:26Z"},{"number":996,"title":"Support Perplexity AI","comments":3,"created_at":"2026-10-21T19:53:34Z"},{"number":828,"title":"Reviewer calibration corpus: OpenReview camera-ready replacement leaks the accept label (blocks #653 first scored run)","comments":3,"created_at":"2026-09-06T00:43:50Z"},{"number":575,"title":"[META] User-confirmed review target and source-backed field/venue criteria","comments":3,"created_at":"2026-07-24T00:16:19Z"},{"number":1001,"title":"Reviewer-recommended references: verify through the existing resolver clients before they reach the decision letter (paper-derived: King & Worthington 2026)","comments":2,"created_at":"2026-10-23T06:52:22Z"},{"number":871,"title":"Reviewer Round-1 paired controls: presentation-only rewrite invariance, soundness-counterfactual sensitivity, bounded-feedback rounds (paper-derived: arXiv:2609.07713)","comments":2,"created_at":"2026-09-15T05:59:45Z"}],"discussions":[{"number":1047,"title":"分享一个面向机器学习实证的实验—主张交接 skill，想请教复审与来源记录设计","comments":1,"category":"Show and tell","created_at":"2026-11-04T05:04:25Z"},{"number":1046,"title":"Newbie questions","comments":1,"category":"Q&A","created_at":"2026-11-04T04:43:32Z"},{"number":848,"title":"Review of acronyms and their appearance in text","comments":2,"category":"Ideas","created_at":"2026-09-09T09:48:20Z"},{"number":818,"title":"ARS token fee claim","comments":2,"category":"General","created_at":"2026-09-04T11:38:42Z"},{"number":780,"title":"Clarification on bibliographic API usage in ARS-Codex","comments":1,"category":"Q&A","created_at":"2026-08-18T06:23:38Z"},{"number":767,"title":"Feature Proposal: Integration of Institutional Subscription Databases (Scopus, WoS, ScienceDirect)","comments":2,"category":"Ideas","created_at":"2026-08-17T10:41:40Z"},{"number":765,"title":"Will it 100% work  with  the Codex  app  for Windows OS and PoweShell , without Linux?","comments":1,"category":"Q&A","created_at":"2026-08-17T07:56:22Z"},{"number":721,"title":"会不会做成deepseek harness插件","comments":1,"category":"General","created_at":"2026-08-13T15:57:22Z"}],"latest_release":{"name":"v3.24.2 — An honest null for experiment locks, repro_lock alignment, and a corrected sr-screener methods sentence","tag":"v3.24.2","published_at":"2026-11-06T04:38:21Z","body":"\n> **Repairs and docs; no new skill or mode, and the prompt-level changes are unmeasured:** An `experiment_provenance[]` entry can now say it has no honest lock values, with `repro_lock: null` and a `repro_lock_reason` (#1049). A survey or an analysis with no LLM could pass before only with placeholder values. Earlier ARS releases reject this form, so a passport that uses it needs this release. `check_repro_lock.py` now fails a required value that breaks its field's type or value rule, such as a null model id; `cross_model.secondary_model_id` may still be null. `planned_vs_executed[].value` accepts only a number or a string, so some passports that passed before now fail (#1050). The `sr-screener` methods text no longer says the reviewers could read only the record file: the tool list removes web and write access, and reading only the given file is an instruction (#1039). SETUP records two checks in which an uploaded skill dispatched a built-in sub-agent in a conversation after a retry; multi-agent stages stay untested (#1040).\n\n### Fixed\n\n- **An experiment with no honest lock values can say so (#1049, PR #1051).** Every `experiment_provenance[]` entry had to fill every `repro_lock` field, and those fields describe LLM and ARS run settings. A survey, an analysis with no LLM, or a trained model with no ARS prompts could pass only with placeholder values. The key stays required. Its value may now be `null`, and `repro_lock_reason` is then required; a reason beside a populated lock is rejected. The reason is free text: it discloses the gap, does not prove the lock does not apply, and no script checks the details it names. The passport-level validator and the required-field set do not change. **Compatibility:** earlier ARS releases reject `repro_lock: null` in an entry, so a passport that uses it needs this release.\n- **`repro_lock` docs, example, gate, and validators agree (#1050, PR #1052).** `check_repro_lock.py` now checks each required value against its field's type or value rule, matching the nested entry schema. `cross_model.secondary_model_id` may be null or any string, and the other string fields must be non-empty. A drift test compares the two on required keys, supported values, and a fixed set of wrong and edge-case values, not on every possible value, and extra keys stay the one known difference. The example passport gains a passport-level lock, and its two trained-model experiments use `repro_lock: null` with a reason. The D7 text in the integrity gate names 3.12.0 as the boundary and adds a fifth FAIL condition, a post-#260 passport with status `legacy_unknown`. The pattern doc no longer says a version change alters the prompt hashes, because they hash only the prompt files. **Compatibility:** a populated lock with a required value that breaks these rules now fails when `check_repro_lock.py` is run on it, and `planned_vs_executed[].value` accepts only a number or a string. Some passports that passed before now fail. The gate text is prompt-level and its effect is unmeasured.\n- **The `sr-screener` methods text states what the tool list enforces (#1039, PR #1043).** `tools: Read, Grep` removes web and write access but does not confine Read and Grep to one file. The title/abstract and full-text methods text now say: \"The reviewer agents had read-only file tools and no web access; each was instructed to read only the file it was given.\" Methods text generated by an earlier release keeps the old sentence, so an author who used it should correct it by hand.\n\n### Docs\n\n- **SETUP records what an uploaded skill did on Claude Desktop (#1040, PR #1045).** Claude Desktop refused an upload named `deep-research` because Anthropic already provides a skill with that name, so Method 3 (en/zh-TW) now zips a copy named `ars-deep-research`, with the skill folder at the top of the zip. In two checks on 2026-11-02, the uploaded skill dispatched a built-in `Explore` sub-agent in a conversation; each time the first dispatch did not run and a"},"readme":true,"readme_zh":true,"news":[{"title":"Academic Research Skills for Claude Code","url":"https://github.com/Imbad0202/academic-research-skills","hn":"https://news.ycombinator.com/item?id=48083919","source":"Hacker News","lang":"en","date":"2026-05-10","points":82,"comments":25},{"title":"Academic Research Skills 如何 2 条命令装好：完整安装与快速上手指南","url":"https://blog.csdn.net/gitblog_01178/article/details/155124725?index=related&type=card","source":"blog.csdn","lang":"zh","date":"2026-10-07"},{"title":"Githubトレンド on X: \"9/2 21:47 JST｜GitHub Trendingから academic-research-skills をピックアップ。中身はスレッドへ。\"","url":"https://x.com/github_trendjp/status/2095131761500094481","source":"x","lang":"zh","date":"2026-09-02"},{"title":"★31,400のClaude Code論文スキルを、note記事・Gumroad商品づくりに転用する全手順","url":"https://note.com/samurai_ai/n/na038ce8b6269","source":"note","lang":"zh","date":"2026-06-15"},{"title":"Academic Research Skills 全解析 — Claude Code 学术研究技能套件（25k+ Stars）","url":"https://www.bilibili.com/zh-Hans/video/BV1xEVB6QE13/","source":"bilibili","lang":"zh","date":"2026-06-02"},{"title":"Academic Research Skillsとは？Claude Codeで論文作成・文献レビュー・引用チェックを半自動化する使い方","url":"https://note.com/tomo4006685/n/n8cdb5f4c119a","source":"note","lang":"zh","date":"2026-05-26"},{"title":"想用Codex做科研，可以先从这9个Skills开始","url":"https://news.google.com/rss/articles/CBMiV0FVX3lxTE5HNGRJZnhoYjFrOUhQRk01V2t2RnhoQzlEZ3d6R2ZiWHFwUVg1SDl0ZWtibk0yb3RmemJxSXQ5Sms2dGQzRzU0MnhoVFhyVE9EQzdsdjNEVQ?oc=5","source":"view.inews.qq.com","lang":"zh","date":"2026-07-21"},{"title":"GitHub Trending Top 10: Agents, Memory and On-Device Dominate the Week","url":"https://news.google.com/rss/articles/CBMif0FVX3lxTE5zTVdkMlJuOVpkME91V0YzU3oyckJWNTZvWTFXTXN3cVNwemZlNFBXSlhBZWFCSUNPM2I4dE1BcFBXZmZBcU1YR0xaUlZsM3Q2TjlEQWxTLVZNbjNMYUVDYmxBYlptbTZDRV9sQW5GM2xFNzVJZlAzUVFFQlpGdFk?oc=5","source":"Pasquale Pillitteri","lang":"en","date":"2026-05-24"},{"title":"GitHub Trending Top 10: 智能体、内存与端侧运行主导本周","url":"https://news.google.com/rss/articles/CBMiggFBVV95cUxNM1ZBcTJfZHVXUFVRWFoyMmhnamh1OFNfbUVOQkRQTjR0ZHJjd3lMNElHdXJqal83RlZHemJXLVNTUkNkdmlWbFM1Ml9YN0tKOXVKNDBZSWZSWnhaZV9OWFZudXowYTREVE5Fc0J0MmtjOGN3bHVFZjZvdTh4QUd3V3p3?oc=5","source":"Pasquale Pillitteri","lang":"zh","date":"2026-05-21"},{"title":"6.4k Stars！用Claude Code写论文的全套流水线，有人打包开源了","url":"https://news.google.com/rss/articles/CBMiSEFVX3lxTE9PWTg3ZWdZUWhESE94Nk45X3FtRzU0SGw5MkIxOFJ5MTNHMnllMnBvQ1ZieUpYS3hvWlBtNVUxVHE1YkI2M3NZRA?oc=5","source":"智源社区","lang":"zh","date":"2026-05-19"},{"title":"Chinese Developers Bypass VPN to Use Claude Code: One-Line Command Connects DeepSeek, Academic Writing Toolkit Arrives","url":"https://news.google.com/rss/articles/CBMiYEFVX3lxTFBmcW5WeTFjZFRmVmZXV1o2eDlXU0h2aDZyUDg5cnFCUGU4WTBQZFhLYzhRSlhnNi1YcXRLN09vOEIyaF8tbmJRVXZHNkhmaGxqS0JWWHRINGJKT2lkWTRJNg?oc=5","source":"finance.biggo.com","lang":"en","date":"2026-05-17"},{"title":"Claude Code学术研究流水线开源！4个skill跑通科研全流程，多机制防AI出错","url":"https://news.google.com/rss/articles/CBMia0FVX3lxTE5XTTR2S2lITUk1aGlPcGNlVzdYbVpRQ2xGaHYybUFLUmZtUXJQQldDb29Zb19VUkxncWtFUVhycmNrcmoyZFQ0S0wxQ0RtTmVXRnE0ZUVxcjAwQmdWRkVfSWdQNUxKbkVraEc0?oc=5","source":"CSDN博客","lang":"zh","date":"2026-05-17"}],"stale":false,"snapshot_at":"2026-11-10T09:35:25Z","history_start":"2026-09-06"}