Research skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

light-research-plan

Light 科研主线第 5 步·研究方案与实验设计：把 idea-critique 放行的 idea 与 data feasibility 拆成**能真执行、能写进论文、 能复现**的 question/estimand、实验矩阵与预注册包。何时用：idea 已通过审查要落地 / 要设计实验·消融·对比·敏感性· 泛化·鲁棒性 / 写研究方案 PROJECT_PLAN / 锁 primary outcome、排除/停止规则或 preregistration / 规划样本量、种子与统计功效 / 算实验算力预算 / 复现已有论文 / 担心 baseline 放水或假设推不翻。触发词：研究方案 / 实验设计 / 实验矩阵 / 假设 / 对照 baseline / 消融 ablation / 公平比较 / 可证伪 / 统计功效 power / 多少种子 / 复现 / reproducibility / research plan / experiment design / 可复现。核心纪律：**对照不公平(baseline 放水)/不可证伪 = critical 一票否决** （spec §4.2，STAGE_GATES[5]=[fair_baseline,falsifiable]）；消融不隔离/欠功效 = warn；功效是计划阶段反推非结果检验； lint 是启发式有边界，公平/可证伪终判仍需人/领域判断，绝不吹"证明了对照绝对公平"。

445 repo starsObserved in 1 repos
Research
GitHub

light-result-analysis

Light 科研主线第 7 步·结果分析：不描述好坏、解释「为什么」，把每条结论**绑死到 claim + 证据强度**，并防 p-hacking。 何时用：实验跑完要解读结果 / 问「这些数说明什么」/ 要做显著性检验 + 效应量 + 置信区间 + 多重比较校正 / 担心 p-hacking (多重比较不校正、选择性报告、HARKing) / 要给每条 claim 定证据强度供写作校准措辞 / 判结果支不支撑假设、可不可复现。 触发词：结果分析 / 解读数据 / 这些结果说明什么 / 显著性 / p 值 / 效应量 effect size / Cohen's d / 置信区间 CI / 多重比较 / BH-FDR / Bonferroni / 校正 / p-hacking / 选择性报告 / garden of forking paths / HARKing / 证据强度 / claim 证据绑定 / SHAP / 消融分析 / 切片分析 / 配对检验 / result analysis。 核心纪律：**统计错误 / p-hacking = critical**（spec §4.2，STAGE_GATES[7]=[stat_validity,evidence_strength]）； 过度解读 / 效应量缺失 = warn；**显著性看 q 不看 p**、不显著只能报「未见显著差异」、措辞强度必须匹配证据强度； 统计检查有边界，绝不吹「证明了方法有效 / 因果成立」。本技能是 **7→5（不支撑假设）/ 7→6（不可复现）回炉发起方**。

445 repo starsObserved in 1 repos
Research
GitHub

light-venue-matching

Build evidence-bound journal or conference shortlists for Light stage 12. Use after typesetting delivers venue-handoff.json/PDF/compliance facts; when an author asks where to submit, journal selection, conference fit, scope or article-type matching, publication strategy, reach/match/safety tiers, transfer order, APC/OA/indexing/deadline constraints, or predatory/hijacked-journal risk. Produces a current-source candidate registry, fit/risk/unknown reports, and an unchosen decision packet; never recompiles the PDF, invents acceptance rates, condemns a venue from soft signals, chooses without a direct user choice or explicit delegation, or submits.

445 repo starsObserved in 1 repos
Research
GitHub

sosumi

Fetches Apple documentation as Markdown via Sosumi. Use for Apple API reference, Human Interface Guidelines, WWDC transcripts, and external Swift-DocC pages.

445 repo starsObserved in 1 repos
Research
GitHub

spec-discovery

Crawl and discover specification documents from a given URL.

445 repo starsObserved in 1 repos
Research
GitHub

双引擎论文搜索

使用 OpenAlex 与 AnySearch 两个真实数据源并行搜索、交叉匹配和输出可追溯论文元数据。

443 repo starsObserved in 1 repos
Research
GitHub

community-research-insight

Extract structured insight briefs from community research transcripts or notes. Produces pain points, stakeholder needs, opportunity maps, risks, and follow-up questions. Requires human review before publication.

442 repo starsObserved in 1 repos
Research
GitHub

daily-news-digest

Produce a daily news brief (AI/security/dev) with links, key takeaways, and action items.

442 repo starsObserved in 1 repos
Research
GitHub

ko-lesson

当用户希望学习某个课程、根据已有材料生成完整课程包、逐课反馈学习、一次性生成全量学习资料，或要求默认模式、一课一知识点模式、故事模式等课程颗粒度时使用。

442 repo starsObserved in 1 repos
Research
GitHub

sentry-docs

Sentry documentation site (docs.sentry.io). Use for contributing to docs or understanding docs architecture. If you need to set up Sentry in a project or debug production issues, see the product skills at https://skills.sentry.dev.

441 repo starsObserved in 1 repos
Research
GitHub