PR 审查
Review a PR for correctness, security, code quality, and testing issues.
复习、笔记、作业 · 239 个 Skill
Review a PR for correctness, security, code quality, and testing issues.
| You are an expert fact-checker who evaluates claims systematically using evidence-based analysis.
| You are an expert at creating clear, actionable meeting summaries and notes.
| You are an expert technical writer who creates clear, user-friendly documentation for technical products.
Automated semantic versioning and release workflow for Claude Code plugins.
Prime a codebase by reading every source file in full.
Designer-turned-developer who crafts stunning UI/UX even without design mockups You are a designer who learned to code.
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns.
Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize.
Use this skill when the user asks to save, recall, find, or organize notes.
Manage DeepTutor knowledge bases — list, create, search, add documents, delete.
Automates browser interactions for web testing, form filling, screenshots, and data extraction.
Improve a skill using a test-fix-retest loop.
Personalized 1-on-1 AI tutor.
| This skill is the inverse of gbrain skillpack scaffold.
Expert knowledge for AI deep research — methodology, source evaluation, search optimization, cross-referencing, synthesis, and citation form…
Web search and research specialist for finding and synthesizing information You are a research specialist.
Writing improvement specialist for grammar, style, clarity, and structure You are a writing improvement specialist.
Web search via 9Router /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity.
This skill is split into two layers: Do not try to apply the deck-building logic from memory or from this router.
Build a complete but efficient Nature-style Chinese PPTX presentation from a scientific paper, preprint, PDF, article text, abstract, figure legends, or reading notes.
This skill is split into two layers: Do not try to apply the drafting logic from memory or from this router.
Complete API for Google NotebookLM - full programmatic access including features not in the web UI.
会议纪要整理工作流:汇总指定时间范围内的会议纪要并生成结构化报告。
Statistical methods for combining results across multiple studies.
Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML…
生成深度读书笔记的专用 Skill。
> for evaluating whether the skill fits the user's team and workflow, and whether it duplicates something already installed) This QA check runs automatically as part of /legal-builder-hub:skill-installer.
把一篇文章或口播稿,做成"看起来像视频"的点击驱动 16:9 网页演示,可选合成口播音频。
Autonomous novel writing CLI agent with web workbench (InkOS Studio) - use for creative fiction writing, standalone short-fiction packages, cover generation, novel generation, style imitation, chapter continuation/import, EPUB export, AIGC detection, and fan fiction.
Amazon Ads deep analysis covering Sponsored Products, Sponsored Brands (incl.
LinkedIn Ads deep analysis for B2B advertising.
Use when the user asks for any kind of slide-based output or wants to turn.
Turn raw PM content into a compliant, publish-ready skill.
Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns.
Post-ship doc sync across project markdown.
| What recurring problem does this skill solve?
>- This companion skill is adapted from Yuan1z0825/nature-skills/tree/main/nature-figure.
Create UML diagrams using PlantUML syntax.
花叔Design(Huashu-Design)——用HTML做高保真原型、交互Demo、幻灯片、动画、设计变体探索、设计方向顾问与专家评审。
Guides through the complete Vorta release process - version bump, translations, git tag, GitHub release, PyPi, and macOS builds.
Provides web exploitation techniques for CTF challenges.
Use when writing literature review sections - guides searching, organizing, and synthesizing academic sources 本技能指导文献搜索、整理和综述写作。
>- Generate a CHANGELOG.md entry for a release.
小红书笔记素材创作技能。
Structure compelling design presentations for stakeholders, reviews, and showcases.
Extract methodologies from documents or examples to create executable skills Extract actionable methodologies from learning materials (documents, articles, videos) or quality examples (blog posts, designs, code) to generate reusable Skills.
Prepare a psd-tools release: update changelog, open release PR.
> When this skill triggers, go straight to Step 1.
| Use when the user wants to cherry-pick a PR to a release branch.
Generate structured research questions, testable hypotheses, and candidate empirical strategies from a topic, phenomenon, or dataset description.
Use when a repo skill fails, produces errors, gives wrong instructions, or references stale information.
设计哲学顾问,从20种风格中推荐3个方向并生成视觉Demo和AI提示词。
| 专注 CV/DL 领域,支持 Zotero 集成和 Obsidian 笔记保存。
Write a tight, retention-focused YouTube script from a topic, outline, or research brief.
专业 PPT 演示文稿全流程 AI 生成助手。
Generate CodMate skill drafts from requirements.
> | 全称 | China Health and Retirement Longitudinal Study (中国健康与养老追踪调查) | | 官网 | https://charls.pku.edu.cn/ | | 覆盖 | 全国 150 县级单位、450 社区,45 岁以上…
Analyze gold, gold-linked ETFs, and gold miners through macro drivers, positioning, and event risk Use this skill when the user asks about gold, gold-linked ETFs such as GLD, or gold miners and wants a structured market read rather than a generic headline summary.
Competitive landscape research with positioning maps Thin wrapper that routes competitive analysis research requests to the analyze-agent.
Grant budget spreadsheet generation with forcing questions.
Route design consultations to domain-specific design partner agents Thin wrapper that routes design consultation requests to domain-specific design partner agents.
Generate YC-style investor pitch decks in Typst Thin wrapper that routes pitch deck generation requests to the deck-agent.
Route deck implementation to deck-builder-agent for Slidev pitch deck generation Routes deck-specific implementation requests to the deck-builder-agent, generating Slidev pitch decks from plans created by skill-deck-plan and research from skill-deck-research.
Pitch deck content research through material synthesis Thin wrapper that routes pitch deck research requests to the deck-research-agent.
In-place DOCX editing routing to docx-edit-agent Thin wrapper that routes in-place DOCX editing requests to the docx-edit-agent, which edits documents using SuperDoc MCP with optional Word AppleScript integration for zero-friction workflow.
Implementation skill for R-based epidemiology analysis.
Research skill for epidemiology study design and analysis planning.
Research skill for epidemiology and study design Routes epidemiology research tasks to epidemiology-research-agent.
File format conversion routing with specialized sub-agent dispatch Thin wrapper that routes file format operations to the filetypes-router-agent, which then delegates to specialized sub-agents based on file type.
Spreadsheet to table conversion routing Thin wrapper that routes spreadsheet-to-table operations to the filetypes-spreadsheet-agent.
Financial analysis and verification for founders Thin wrapper that routes financial analysis requests to the finance-agent.
Financial analysis with forcing questions and spreadsheet generation Thin wrapper that routes financial analysis research requests to the financial-analysis-agent.
Scan codebase for FIX:/NOTE:/TODO:/QUESTION: tags and create structured tasks with interactive selection.
Coordinate formal reasoning research across logic, math, and physics domains.
Execute founder plans and generate strategy reports Routes founder-specific implementation requests to the founder-implement-agent, executing plans created by skill-founder-plan and generating detailed strategy reports.
Create founder analysis plans with interactive forcing questions Routes founder-specific planning requests to the founder-plan-agent, enabling interactive forcing questions workflow for market sizing, competitive analysis, and GTM strategy planning.
Cost breakdown spreadsheet generation with forcing questions Thin wrapper that routes cost breakdown spreadsheet requests to the founder-spreadsheet-agent.
Funding landscape analysis with funder portfolio mapping.
Grant proposal research and drafting with funder analysis.
Scan codebase for FIX:/NOTE:/TODO:/QUESTION: tags and create structured tasks with interactive selection.
Contract review and legal analysis for founders Thin wrapper that routes contract review requests to the legal-council-agent.
Research mathematical logic tasks using domain context and codebase exploration.
Market sizing research with TAM/SAM/SOM framework Thin wrapper that routes market sizing research requests to the market-agent.
Research mathematical tasks using domain context and codebase exploration.
Investor meeting note processing and CSV tracking Thin wrapper that routes investor meeting note processing requests to the meeting-agent.
Interactive system builder.
Research physics formalization tasks using domain context and codebase exploration.
Presentation extraction and slide generation routing Thin wrapper that routes presentation operations to the presentation-agent.
Project research with scope analysis and timeline estimation Thin wrapper that routes project research requests to the project-agent.
Thin wrapper that delegates plan revision to reviser-agent subagent.
PDF annotation extraction routing to scrape-agent Thin wrapper that routes PDF annotation extraction to the scrape-agent, which extracts highlights, comments, notes, and other annotations from PDF files.
XLSX creation, editing, and analysis routing to sheet-agent Thin wrapper that routes XLSX creation, editing, and analysis requests to the sheet-agent, which manipulates spreadsheets using openpyxl and pandas via Bash.
Research talk material synthesis, design-aware planning, and presentation assembly.
Spreadsheet to table conversion routing Thin wrapper that routes spreadsheet-to-table operations to the spreadsheet-agent.
Go-to-market strategy research with positioning and channels Thin wrapper that routes GTM strategy research requests to the strategy-agent.
Research timeline planning for medical research projects.
Implement web (Astro/Tailwind/TypeScript) changes following a plan.
Discord messaging via `message_send` (channel=discord).
Generate clinical trial protocols for medical devices or drugs.
智能笔记与流程图绘制工具(优化版-无权限读取)。
Create a pull request following WooCommerce iOS conventions git branch --show-current git log trunk..HEAD --oneline git diff trunk...HEAD --stat
Design the solution and write a technical specification based on requirements analysis.
Use when collaborating with other AI assistants (Codex, Gemini, Aider, Cursor, OpenCode), delegating tasks, or requesting code review.
date: {當前時間,格式: 2022-01-01T00:00:00+08:00} author: davidlei categories: ["{category}"]
Discover available skills and subagents.
Use this skill when the user asks "solana fees", "sol fees", "priority fees", "lamports per signature", or mentions checking transaction fees on Solana.
Run full Contextium session startup sequence with all agents Run the full startup agent pipeline to initialize this session.
Start-of-session sync - pull latest, check handoffs, reviews, and blocked items Run at the start of each session to sync with other agents and see what needs attention.
Launch the Karkinos TUI to monitor worker progress in a new terminal window.
| 每次使用完某个 Skill 后,调用本 Skill 记录一条使用日志。
Pair Codex with Pluto.jl notebooks using MCP tools.
Always and Automatically improve skills after each use by capturing learnings and anti-patterns After ANY skill is used, this meta-skill triggers to: After using a skill, note: Ask these questions: | Category | Where to Add | Example | | ----------------- | -------------------------- | ---------------------------- | makes outbound network calls.
Design and conduct qualitative research using grounded theory and case studies A skill for designing and conducting rigorous qualitative research.
Review skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, required sections, and repo conventions.
Help turn ideas into fully formed plans through collaborative dialogue.
> 为用户提供的研究选题撰写符合顶级期刊标准的文献综述(Literature Review)部分。
| 约束 | 规范 | |---|---| | 字体大小 | 正文字体小四(12pt)= \normalsize (TikZ) = font.size=13 (matplotlib);禁止 \small、\footnotesize | | 留白 | 不过大;
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
Parse requirement and analysis files, then generate high-quality test cases.
Fan-out search across all memory sources when context is unclear or vaguely referenced.
Sync AI coding sessions from 14 tools (Claude Code, Codex, Cursor, Aider, Cline, Gemini CLI, Continue, Copilot, Roo Code, Windsurf, Zed AI, Amp, OpenCode, OpenRouter) to Obsidian vault as markdown notes.
v1.6.0 G-SKLL | Guided Oracle birth and awakening ritual (~15 min).
Record, export, and share your AI coding sessions as replayable buildlogs Record your OpenClaw coding sessions and share them on buildlog.ai.
Etalon memory architecture with Knowledge Graph (PARA), session isolation, memory decay, and QMD hybrid search Three-layer memory architecture for OpenClaw agents: curated long-term memory (MEMORY.md), structured knowledge graph (life/), and session-isolated daily notes (memory/).
Manage GitHub Projects (V2), Issues, and Boards.
Fast local search for markdown files, notes, and docs using qmd CLI.
SNS posting patterns and strategy
Chat with web AI agents (ChatGPT, Gemini, Claude, Grok, Perplexity, NotebookLM) via browser automation.
Prepare a clean handoff for continuing complex work in a fresh Claude Code session.
Improves an existing skill based on real project pain (prior eval corpora under .ai-engineering/evals/, Engram cross-session observations, L…
> This skill provides tools for accessing and analyzing global health data from major open sources: the WHO Global Health Observatory API, IHME Global Burden of Disease study data, and Our World in Data health datasets.
整理 Obsidian 知识库,并通过 CLI 读写、搜索笔记或调试插件与主题。
Conduct comprehensive market research using Y Combinator data, SEC filings, social media insights, and web scraping via anysite MCP server.
Create organized, visual study notes with folder structures, diagrams, and example-based learning from source materials (PDFs, lecture notes, documentation).
中文引导式学习助手。
Lightweight research playbook optimized for the FF-Terminal agent.
Anton ADR lifecycle — author new architectural decision records, list existing ones by status or affects-category, and mark old decisions su…
Organize raw commits, merged changes, and unreleased notes into structured versioned changelog entries.
Transform one source asset into channel-specific content such as LinkedIn posts, X threads, captions, reel scripts, carousel copy, blog outlines, or newsletters while preserving the core message and voice.
Classify support requests, ask the right follow-up questions, choose the correct troubleshooting path, and draft responses in the desired support tone.
Turn implementation details into practical documentation such as README updates, setup guides, architecture notes, runbooks, changelogs, and internal reference docs.
Write reproducible procedures, controls, materials lists, and validation steps for experiments.
Structure post-failure analysis from field symptoms, logs, operator notes, and hardware context.
Draft concise investor, advisor, or team updates from raw notes, metrics, and milestones.
| Unified IMA OpenAPI skill.
Turn raw experiment notes into clean, dated, reproducible lab notebook entries.
Convert raw meeting notes, transcripts, or chat logs into decisions, action items, owners, due dates, risks, and follow-up questions.
Build a full internal or external newsletter from source notes, launches, events, and updates.
Turn alert streams, incident notes, and partial diagnostics into a clean on-call handoff.
Run a lightweight personal operating system by reviewing tasks and notes, clustering priorities, drafting weekly plans, surfacing risks, and turning messy inputs into clear next actions.
Convert transcripts into polished show notes, summaries, timestamps, and links.
Draft polished client or stakeholder responses to proposals, questions, or requests using source notes and requirements.
Build (or refresh) a structured hypothesis on whether a specific company can grow 5x and 10x in valuation over the next 5 years, then track it.
Audit and score an agent-definition markdown such as `AGENTS.md`, `CLAUDE.md`, `SKILL.md`, `SOUL.md`, `.cursorrules`, or a system prompt using a cold-reader rubric for clarity, consistency, context independence, and operating-model fit.
Review Gemini API agent code against mandatory rules in backend/AGENTS.md Use when this capability is needed.
Aider is an open-source AI pair programming tool that runs in your terminal, letting you collaborate with LLMs to edit code across your entire codebase.
Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->
>- Transcribe audio/video to speaker-labeled text.
Use when the user has a crash log (.ips, MetricKit JSON, legacy .crash text, .xccrashpoint bundle, or pasted text) that needs analysis.
Use when the user wants to triage a CORPUS of production crashes/hangs from an aggregator (Sentry, App Store Connect) — grouped, counted iss…
Use when the user mentions Liquid Glass review, iOS 26 UI updates, toolbar improvements, or visual effect migration.
Use this agent for closed-loop test debugging - automatically analyzes test failures, suggests fixes, and re-runs tests until passing.
Use when the user mentions Xcode build failures, build errors, or environment issues.
Use when the user wants to add in-app purchases, implement StoreKit 2, or set up subscriptions.
Use when the user mentions slow builds, build performance, or build time optimization.
Use when the user wants automated performance profiling, headless Instruments analysis, or CLI-based trace collection.
Use when the user mentions SPM resolution failures, "no such module" errors, duplicate symbol linker errors, version conflicts between packages, or Swift 6 package compatibility issues.
Use when the user wants to run XCUITests, parse test results, view test failures, or export test attachments.
Use when the user mentions simulator testing, visual verification, push notification testing, location simulation, screenshot capture, OR live accessibility validation (VoiceOver announcements, Dynamic Type, ADA checks) on the simulator.
Use when the user mentions App Store screenshot validation, screenshot review, checking screenshots before submission, or verifying screenshot dimensions and content.
Converts Markdown files to beautifully styled HTML with inline CSS, optimized for WeChat Official Account and other platforms.
Fetch real, verifiable data for a Bilibili video so you can cite it instead of guessing.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel.
Python or Docker Use the upstream install or setup path that matches your environment: Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Python.
Scaffold/audit GitHub Actions CI/CD — Go/Rust/TS.
Cockpit CMS is a lightweight headless content platform for teams that want flexible models, REST and GraphQL APIs, and self-hosted deployment without a heavy stack.
Build Codex-native workflows for open-source maintenance.
Insert structured START/END code comment blocks around features, sections, logical blocks, TODOs, bugfixes, refactors, or notes.
Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->
| Create high-fidelity research reports with strict format control, evidence mapping, source governance, and multi-pass synthesis.
Use the upstream install or setup path that matches your environment: Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Node.js.
Difftastic is a structural diff tool that compares files based on their syntax rather than line-by-line text.
Use the upstream install or setup path that matches your environment: Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Docker.
Dioxus is a fullstack app framework for Rust that enables building cross-platform applications for web, desktop, and mobile from a single codebase.
Start and verify the local Docker CDC lab (dvdrental), run the PostgreSQL load generators, reset Databricks tables, trigger Databricks notebook jobs through databricks.sdk, and check whether Bronze/Silver notebooks completed successfully.
Dokku is a self-hosted Platform-as-a-Service built on Docker that provides Heroku-like git-push deployment on your own infrastructure.
Modern .NET project structure including .slnx solution format, Directory.Build.props, central package management, SourceLink, version management with RELEASE_NOTES.md, and SDK pinning with global.json.
> Export Douban user collections (books, movies, music, games) to CSV files.
Use when you have a written implementation plan to execute in a separate session with review checkpoints Load plan, review critically, execute all tasks, report when complete.
Use the upstream install or setup path that matches your environment: Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Docker.
Extract a Feishu/Lark source into faithful local Markdown.
Gemini CLI for one-shot Q&A, summaries, and generation.
Use when the user asks to run Gemini CLI, Google Gemini for code tasks, or references Gemini for analysis, code generation, or automated editing | Model | When to Use | |-------|-------------| | gemini-3-flash-preview | DEFAULT - Use for most tasks.
This skill helps you learn Go (Golang) one topic per day.
Full safety mode: destructive command warnings + directory-scoped edits.
Understand implementation details of .NET code by decompiling assemblies.
> One-command installer, troubleshooter, and personalization layer for the official Tencent IMA skill.
Implement a specification in code.
Jujutsu (jj) is a powerful Git-compatible version control system that reimagines VCS workflows with automatic rebasing, first-class conflict tracking, and operation-log undo.
K9s is a terminal-based UI for managing Kubernetes clusters, providing real-time observation of resources, log tailing, pod shell access, and cluster navigation.
Use when: organizing a markdown knowledge repository, importing sources into 原始资料, compiling 来源笔记/概念/主题, maintaining 索引, generating 派生内容, ru…
LangExtract by Google is a Python library for extracting structured information from unstructured text using LLMs with precise source grounding.
Use when the user wants to learn a new programming language, framework, or platform via a hands-on, one-lesson-at-a-time curriculum — phrasi…
帮用户搭一个金融投研专用 LLM Wiki(Karpathy 模式):纯 markdown 文件 + [[wikilink]] 互联 + LLM 维护,知识随用复利。
Patterns pour construire ses propres MCP servers (Model Context Protocol) — outil pour exposer des capabilities custom à Claude Code.
Configures mewt or muton mutation testing campaigns — scopes targets, tunes timeouts, and optimizes long-running runs.
Edit PDFs with natural-language instructions using the nano-pdf CLI.
NocoDB turns any SQL database into a smart spreadsheet with a full REST API.
>- Use when this capability is needed.
Ollama runs large language models locally with a simple CLI and REST API.
Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Docker.
Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Docker.
Propose a code patch for a finding.
>- Two related pipelines, same destination look, different starting point: phone photos of paper documents, or a digital document that needs a synthetic signature before it looks signed.
Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both.
Presentation creation, editing, and analysis.
Runs the full release workflow for the current project.
Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Python >=3.10.
Lightweight research playbook optimized for the FF-Terminal agent.
Lightweight research playbook optimized for the FF-Terminal agent.
Universal release workflow supporting any project type with multi-language changelog.
Keep repository documentation, AGENTS.md, and contributor/test guidance aligned with code, design, and product changes.
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
Use when you need to resolve an in-progress git merge/rebase conflict.
Runs external LLM code reviews (OpenAI Codex or Google Gemini CLI) on uncommitted changes, branch diffs, or specific commits.
Run initial nano-core setup.
Ship current branch — CI, SonarCloud, code review, security review, fix all issues, merge.
Use when a user provides a vague prompt and needs structured clarification to produce a precise master prompt.
Check code against the documentation that specifies it - which requirements hold, which the code contradicts, which are absent, and what the code does that no document mentions.
Use when working with an official MCP server that connects Supabase projects to AI assistants like Claude, Cursor, and Windsurf.
Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->
Basic usage or getting-started notes: Use when this capability is needed.
Use this skill when authoring or running a Terraform plan/apply, refactoring modules, performing state surgery, importing existing cloud res…
Activate when user asks to sync, push, or publish local Tracecat MCP server code or Claude Code skills to their GitHub repositories Use when this capability is needed.
Language-specific verification for Python, TypeScript/JavaScript, and Go.
Extract frames or short clips from videos using ffmpeg.
Uses the W&B Python SDK and Public API to stream live training metrics, system stats, and gradients from active runs.