Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 80 149 files from 1 774 authors, of which 62 489 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
> General-purpose research orchestrator. Routes ambiguous or multi-step requests to the right skill(s) from the medsci-skills bundle. Use when the user describes a research goal without naming a specific skill, or when a task spans multiple skills.
Academic English consistency linting and non-native (ESL) language polish for medical manuscripts. Deterministically flags abbreviation define-once violations, US/UK spelling drift, hyphen-vs-en-dash numeric ranges, P/p case, hyphenation variants, small-number style, and value/unit spacing, then guides a style-only clarity pass that never alters numbers, citations, or scientific meaning. Distinct from humanize (AI-tell removal) and check-reporting (guideline items).
> Design or audit the data-preparation stage of a medical-imaging model — DICOM/NIfTI intake, resampling and intensity normalisation, and the augmentation plan — so the pipeline is leakage-safe before model-scaffold builds the training repo. Emits a declarative preprocessing manifest and a dataset-level normaliser fit on non-train data, any data-fitted transform run before the split, and the same patient's slices crossing splits. Integrates MONAI / TorchIO transforms; it does not reimplement them, and it never runs preprocessing on real patient data.
> Convert a personal agent skill into a distributable, open-source-ready skill. Runs PII audit, generalization, license compatibility check, cross-platform adapter review, and packaging workflow.
> Academic presentation preparation — paper-driven (journal club, grand rounds, seminar) and lecture/teaching decks (course material, workshop slides, conference talks). Analyzes source material, finds supporting references, drafts audience-adapted speaker scripts, generates or augments PPTX with speaker notes, and prepares Q&A.
> Profile a medical-imaging dataset before any modelling decision is made — the acquisition grid, voxel spacing and orientation spread, the intensity domain, which label values are actually present, how much of the volume the target occupies, and how large the target is in millilitres — then gate that profile against the researcher's declared plan. Catches, at the point where it is carries no ground truth, labels whose grid does not match their image, a stray label index, a target occupying a fraction of a percent while accuracy is planned as a metric, and acquisition heterogeneity nobody declared a resampling decision for. Emits a dataset-profile JSON and a deterministic gate that reads it (stdlib-only, so an audit travels with the JSON). It describes the data and audits the plan against it; it does not preprocess, split, or train.
> Render academic Markdown documents (English or Korean) to publication-quality PDF via pandoc + xelatex. handouts, anchor docs (Q&A grids), and reference tables. Auto-infers pipe-table column widths from content (label column shrinks to fit, data columns share remaining width). CJK-aware font fallback for Korean text (Apple SD Gothic Neo on macOS, Noto Sans CJK KR on Linux). filling (/fill-protocol), figures (/make-figures).
> Produce or audit a radiomics / tabular clinical-ML study — imaging or clinical features → any classical learner (penalised logistic [LASSO / ridge / elastic-net], SVM, k-NN, naive Bayes, LDA/QDA, decision tree, random forest, gradient boosting [XGBoost / LightGBM / CatBoost], shallow cross-validation (tuning never on the reported folds), dimensionality control for the features-far-exceed-events regime, feature selection inside the fold, feature-stability (ICC / test-retest) filtering, calibration, and external/temporal validation. The deterministic gate is learner-agnostic (it audits the pipeline, not the algorithm). Emits a pipeline manifest and the gate. The most common solo-doable clinical-ML workflow — no GPU, no engineer. Integrates scikit-learn / xgboost / lightgbm / catboost / pyradiomics; it does not reimplement them.
Replicate an existing cohort study's methodology on a different database. Extracts study design from a source paper, maps variables to the target DB via harmonization table, generates analysis code, and produces a replication difference report.
> Scaffold and draft medical/AI literature reviews (narrative, scoping PRISMA-ScR, or systematic). Asks for the spine axis, builds a 7-part skeleton with a required Intro scope/non-overlap block, a summary-table stub, an evaluation-metrics critique subsection, and reporting-guideline wiring. Reuses the self-review RV1-RV9 narrative-review probes for QC. Does not invent citations.
Parse peer reviewer comments and generate a structured Response to Reviewers document with tracked manuscript changes. Classifies comments as MAJOR/MINOR/REBUTTAL, coordinates new analyses with /analyze-stats and /make-figures, and produces cover letter for editor.
Diagnostic checklist for the MedSci Skills runtime. Verifies Python, R, Node, Claude Code, Git, Zotero, and configured MCP servers, and prints a pass/fail table with links to the right setup doc for any missing component. Read-only — does not install anything.
Literature search and citation management for medical research. Searches PubMed, Semantic Scholar, and bioRxiv/medRxiv with verified citations. Anti-hallucination — every reference verified via API before inclusion. Generates BibTeX entries.
Pre-submission self-review for the user's own manuscripts, applying a reviewer perspective. Systematic check across 10 categories with research-type branching. Outputs Anticipated Major/Minor Comments with severity framing and optional R0 numbering for /revise pipeline integration.
Audit-only verification of manuscript references against PubMed and CrossRef. Detects fabricated or mismatched citations and writes qc/reference_audit.json. Does not modify references/ or refs.bib.
> Design or audit the uncertainty-quantification, out-of-distribution (OOD) detection, and selective-prediction layer of a medical-imaging model framed for deployment — so a clinical-use claim carries calibrated per-case uncertainty (MC-dropout / deep ensemble / conformal / Bayesian), an OOD guard validated on a held-out OOD set, an abstention rule at a pre-specified operating point, and uncertainty checked under distribution shift. Emits an uncertainty manifest and a deterministic gate that flags a deployment claim built on point predictions, conformal intervals with unmeasured coverage, and an OOD claim with no held-out OOD data. Integrates MAPIE / captum / pretrained OOD scorers; it does not reimplement them and never runs a model on real patient data.
Audit SSOT-to-submission drift and create journal submission manifests from canonical manuscript artifacts.
Dataset version control for research reproducibility. Builds a deterministic content-hash manifest of a dataset (file SHA-256 + tabular schema + per-column value hashes), verifies a later copy against it to detect drift (schema change, row-count change, value changes), and diffs two manifests. Use to prove an analysis ran on the intended data, lock a dataset version, or reproducibility-lock bundled demos.
> IRB/ethics committee research protocol generator. Produces 4 core sections (Background, Study Design, Sample Size, Statistical Plan) with full prose, plus 6 skeleton sections with TODO markers for institution-specific content. Integrates outputs from design-study, calc-sample-size, and search-lit.
Full-pipeline medical/scientific paper writing. 8-phase IMRAD workflow from outline to submission-ready manuscript. Supports original articles, case reports, case series, meta-analyses, AI validation studies, animal studies, and technical notes. Do NOT trigger for self-checking (use self-review instead).
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
Use when work should be delegated to Claude Code CLI, especially headless `claude -p` runs, automation scripts, CI jobs, resumable sessions, or requests to use Claude/Claude Code for a task.
>- 撰写机构级个股投资研究报告（二级市场深度研究）。Use whenever the user wants to research, analyze, or value a specific publicly-traded stock — e.g. "研究/分析一下某只股票（公司名或代码）"、"帮我看看 NVDA 值不值得买"、"给某只股票写一份投研报告/研报"、"is this stock a buy / overvalued / fairly valued"，或针对某个具名上市公司询问 估值/护城河/财报/目标价/多空逻辑/投资建议（valuation, moat, fundamentals, fair value, price target, bull/bear case），以及财报/季报/年报/业绩会/电话会/指引更新/earnings review/results/10-Q/10-K/earnings call/guidance update。只要出现「公司名或股票代码 + 任何投研意图」就应触发，即使用户没有明确说"报告"二字。覆盖美股、港股、A股，含 A/H 双重上市与中概 VIE/ADR 结构分析。技能会跑完整流程：按一手披露优先级探测数据并自动降级标注；以预期差（市场隐含 vs 独立预期）为分析主线，产出结构化九章研报——估值一律由脚本计算，反向 DCF+PVGO、三情景概率加权、EPV、EVA/剩余收益多法交叉验证并可跑蒙特卡洛；财报质量做财报质量核查检查（应计/M-Score）；结论按预注册标定规则映射并经反方论证复核；财报请求自动进入同等深度财报模式——并保存为带来源与时间戳的文件。Do NOT use for 单纯的一句话报价、宏观/大盘评论、组合层面的资产配置、或非股票类工具（债券/期货/外汇本身）。
> Evaluate skill quality, find the weakest dimension, and apply directed improvements. Also tracks usage to spot idle or risky skills. evaluation, inbox, suggestions, or improvement.
> Runs a Greptile CLI review for the current local branch, installing or authenticating the CLI when needed, then summarizes JSON findings for the user. Use when the user wants Greptile feedback before opening a PR, outside a hosted PR review flow, or directly from a local checkout.
将书籍、PDF、PPT/PPTX、Word、网页、Markdown、文本或多份资料转化为可追溯知识库、交互式单文件学习 HTML 和同步 Markdown。用于学习、讲解、总结、复习、深挖材料、生成术语大全、动态测验及错题复习；对书籍执行高密度全量阅读，对所有材料执行出处映射、覆盖审计、安全扫描，并严格区分材料依据、模型补充与外部核验。
Use when verifying SDK event payloads in the Android SDK sandbox, debugging what events are emitted, or validating request bodies via logcat with the sample Kotlin app.
Detects code smells, anti-patterns, and readability issues. Use when implementing features, reviewing code, or refactoring.
Applies React/TypeScript type safety, component design, and state management rules. Use when implementing React components.
Designs frontend tests using the repository's configured React test and browser harnesses, including RTL, MSW, Vitest, and Playwright when present. Use when adding or reviewing component, loading/error-state, integration, or frontend E2E tests.
Defines React environment, component architecture, state/data flow, build verification, and frontend non-functional criteria from repository evidence. Use when configuring or designing a React frontend, its build, or its runtime boundaries.
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream agents can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.
Designs integration and E2E tests with mock boundaries and behavior verification rules. Use when writing E2E or integration tests.
Selects implementation strategy (vertical slice, horizontal, or hybrid) with risk assessment. Use when planning feature implementation.
Guides PRD, ADR, Design Doc, UI Spec, and Work Plan creation. Use when creating or reviewing technical documents, or when "UI spec/screen design/component decomposition" is mentioned.
Separates the outcome a change must produce from the requirements proposed to reach it, records what the user excluded, and bands cost from structure. Use when a requirement enters a workflow, before design begins, or when "how far do we go/what's out of scope/is this worth it" is mentioned.
Marks project context as unconfigured until project-inject materializes domain constraints, phase, conventions, and external-resource access in this file. Use when checking project context before the initial project-inject run.
Classifies task intent, change risk, and execution scale, then selects skills from the project skills index. Use when starting work, routing a task, estimating scope, or selecting skills.
Evaluates and optimizes skill file quality using 8 content patterns and 9 editing principles. Use when creating skills, refining skill content, or auditing skill quality.
Applies type safety and error handling rules. Enforces no-any policy and type guards. Use when implementing TypeScript or reviewing types.
Defines environment variables, architecture design, and build/test commands. Use when configuring environment or designing architecture.
Coordinates subagents through scale-based planning, approval, implementation, verification, and escalation flows. Use when routing work to subagents, executing an approved work plan, or resuming autonomous execution.
Applies Vitest test design and quality standards. Provides coverage requirements and mock usage guides. Use when writing unit tests.
リポジトリの根拠に基づき、Reactの環境、コンポーネントアーキテクチャ、状態・データフロー、ビルド検証、フロントエンドの非機能基準を定義。Reactフロントエンド、そのビルド、ランタイム境界の設定・設計時に使用。
React/TypeScriptの型安全性、コンポーネント設計、状態管理ルールを適用。Reactコンポーネント実装時に使用。
コードの品質問題、アンチパターン、可読性を検査。機能実装、コードレビュー、リファクタリング時に使用。
PRD、ADR、Design Doc、UI Spec、作業計画書の作成を支援。技術ドキュメントの作成・レビュー時、または「UI Spec/画面設計/コンポーネント分解」が言及された時に使用。
統合テストとE2Eテストを設計。モック境界と振る舞い検証ルールを適用。E2Eテスト、統合テスト作成時に使用。
実装戦略（垂直スライス、水平、ハイブリッド）をリスク評価で選択。機能の実装計画時に使用。
リポジトリで設定済みのReactテスト・ブラウザハーネスを使用してフロントエンドテストを設計。RTL、MSW、Vitest、Playwrightが存在する場合に適用。コンポーネント、loading/error state、統合、フロントエンドE2Eテストの追加・レビュー時に使用。
入力・出力・成功基準・決定事項・未解決条件を明確化し、下流エージェントが推測せず実行できるようにする。LLM向けのプロンプト・ハンドオフ・計画成果物・レビュー・レポート・生成指示を記述または改訂する時に使用。
project-injectによってドメイン制約、フェーズ、規約、外部リソースへのアクセス方法がこのファイルに反映されるまで、プロジェクトコンテキストを未設定として示す。初回project-inject実行前にプロジェクトコンテキストを確認する場合に使用。
スキルファイルの品質を8つのコンテンツパターンと9つの編集原則で評価・最適化。スキル作成、内容改善、品質監査時に使用。
変更が生むべき成果と、そこへ至るために提案された要件を切り分け、ユーザーが除外したものを記録し、コストを構造からバンドで見積もる。要件がワークフローに入った時点、設計を始める前、または「どこまでやるか/スコープ外は何か/やる価値があるか」が言及された時に使用。
タスクの意図、変更リスク、実行規模を分類し、プロジェクトのスキルインデックスからスキルを選択。作業開始、タスクの振り分け、スコープ見積もり、スキル選択時に使用。
環境変数、アーキテクチャ設計、ビルド・テストコマンドを定義。環境設定、アーキテクチャ設計時に使用。
規模に応じた計画、承認、実装、検証、エスカレーションのフローでサブエージェントを調整。サブエージェントへの作業振り分け、承認済み作業計画の実行、自律実行の再開時に使用。
型安全性とエラーハンドリングルールを適用。any禁止、型ガード必須。TypeScript実装、型定義レビュー時に使用。
Vitestテスト設計と品質基準を適用。カバレッジ要件とモック使用ガイドを提供。ユニットテスト作成時に使用。
Use when designing or tuning exit logic for a Freqtrade strategy on Superior Trade — anything described as ratcheting trailing stop, two-phase exit, ALO-aware exit, dynamic stoploss DSL, ROI ladder, take-profit ladder, exit engine. Specifies a three-phase exit (Phase 0 ROI ladder, Phase 1 hard stop, Phase 2 ratcheting trail) that strategies compose. The Phase 2 ratchet was the most consistently profitable primitive across 21 validation backtests; the Phase 0 ladder is what makes mean-reversion strategies actually book wins.
Claude Skills — questions
Answers built from the skills we actually parsed.