All authors
Claude Skills by tools-only
github.com/tools-only19,166 skills18 installs6,168 views
- 2515 Toolsets B0785398Toolsets are collections of tools that extend agent capabilities. pydantic-deep includes four built-in toolsets.Votes: 0GitHub stars: 9
- 2515 Webview Patterns 2750a5d4Comprehensive guide for building webview UIs in VS Code extensions.Votes: 0GitHub stars: 9
- 2516 Pl Uodo F405830a**Authority:** Prezes Urzędu Ochrony Danych Osobowych (UODO) — President of the Personal Data Protection Office. **Scope:** 12 categories. Notable for strict cross-referencing of criteria — emphasizes that combined factors amplify risk. **EDPB consistency:** Subject to EDPB Opinion under Art. 64(1)(a). **Character:** Structured, criteria-focused. Strong coverage of employee monitoring, whistleblowing, children's data, and smart metering. ---Votes: 0GitHub stars: 9
- 2516 Rewrite Room Author F18ae79eAuthors and validates user-facing documentation — READMEs, tutorials, API docs, GitLab Wiki pages, and GLFM-formatted content. Also routes summarization requests (files, URLs, images, multi-source). Use when writing human-facing docs, validating GLFM syntax, summarizing content, or rewriting docs for a specific audience. NOT for AI-facing docs — use rewrite-room-optimizer for those.Votes: 0GitHub stars: 9
- 2517 Quick Wins 29f2473aGet immediate value from Skills Directory with these time-boxed quick wins. Start small, prove ROI, then expand. For full multi-step workflows, see the **[Skill Chain Cookbook](SKILL_CHAINS.md)** — 36 ready-to-use recipes. ---Votes: 0GitHub stars: 9
- 2517 Rewrite Room Optimizer 528238bbOptimizes AI-facing prompts, CLAUDE.md configurations, SKILL.md files, and agent definitions using Anthropic prompt engineering best practices. Use when CLAUDE.md feels ineffective, SKILL.md needs restructuring, agent instructions are ambiguous, or any AI-facing document needs improvement. NOT for user-facing docs — use rewrite-room-author for those.Votes: 0GitHub stars: 9
- 2517 Whitelists 70d80678Processing operations that do NOT require a DPIA. These provide safe harbors for low-risk, routine processing. **Critical rules:** - Whitelists are **narrow**. Exemptions apply ONLY if processing matches the description precisely. - Adding profiling, automated decisions, biometrics, or special category data to otherwise exempt processing **removes the exemption**. - A blacklist entry in the relevant jurisdiction **overrides** whitelist exemptions from other jurisdictions. - The EDPB has taken...Votes: 0GitHub stars: 9
- 2518 No Heredocinstructions A1bdea6dPrevents terminal heredoc file corruption in VS Code Copilot by enforcing use of file editing tools instead of shell redirectionsVotes: 0GitHub stars: 9
- 2518 Policy 88f176d7Scan policies control all tuning knobs, detection thresholds, and rule enablement in Skill Scanner. A policy specifies which file types are benign, which rules fire on which files, which installer URLs are trusted, severity overrides, and more. Every setting has a sensible default; custom policies merge on top of defaults so you only specify what you want to change.Votes: 0GitHub stars: 9
- 2518 Skill Chains 312b4d53**Production AI agents from recipes, not from scratch.** This is the primary way to use Skene: pick a recipe, copy-paste the chain, and deploy. **Skill Chains first** — these 36 recipes are the dishes; they’re built from a library of **765 skills** (the ingredients). No ML expertise required.Votes: 0GitHub stars: 9
- 2519 2023 10 22 Repomap 89a9b7a9 GPT-4 is extremely useful for "self-contained" coding tasks, like generating or modifying a simple function that has no dependencies. Tools like GitHub CoPilot serve these simple coding tasks well. But making complex changes in a larger, pre-existing codebase is much more difficult, for both humans and AIs. To do this successfully, you need to: 1. Find the code that needs to be changed. 2. Understand how that code relates to the rest of the codebase. 3...Votes: 0GitHub stars: 9
- 2519 Article Cover Baa31151Generate professional, visually striking article cover images in SVG format for technical blogs, documentation, and articles.Votes: 0GitHub stars: 9
- 2519 Article Cover Eb77cdd3生成专业的文章封面图（SVG 格式）。Votes: 0GitHub stars: 9
- 2519 Binary Handling 5cdbf6ceSkill Scanner treats opaque binaries as reduced-visibility risk, not immediate proof of malware. Binary handling is split across static analysis, analyzability scoring, optional VirusTotal checks, and policy knobs.Votes: 0GitHub stars: 9
- 2519 Skills Catalog B303f24f> **765 AI skills** across **23 domains** for SaaS growth, marketing, compliance, and more. > > **383 executable skills** + **382 context skills** (241 cursor rules + 141 scientific) > > 📊 See [METRICS.md](../METRICS.md) for the canonical source of all counts and methodology. ---Votes: 0GitHub stars: 9
- 2520 2024 05 02 Browser Bd617fca<div class="video-container"> <video controls loop poster="/assets/browser.jpg"> <source src="/assets/aider-browser-social.mp4" type="video/mp4"> <a href="/assets/aider-browser-social.mp4">Aider browser UI demo video</a> </video> </div> <style> .video-container { position: relative; padding-bottom: 101.89%; /* 1080 / 1060 = 1.0189 */ height: 0; overflow: hidden; } .video-container video { position: absolute; top: 0; left: 0; width: 100%; height: 100%; } </style> Use aider's new experimental b...Votes: 0GitHub stars: 9
- 2520 Ai Agent Composability Analysis 8ca26161**Analysis Date:** February 6, 2026 **Source:** [The VC Corner - AI Agent Startup Ideas 2025](https://www.thevccorner.com/p/ai-agent-startup-ideas-2025) **Skills Directory Version:** 0.1.0 (773 skills across 25 domains)Votes: 0GitHub stars: 9
- 2520 Obsidian Bases Ea57819eCreate and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.Votes: 0GitHub stars: 9
- 2520 Scan Policy 4aba8acbEvery organisation has a different security bar. A **scan policy** captures what counts as benign, which rules fire on which file types, which installer URLs are trusted, numeric thresholds, and more — all in a single YAML file. ---Votes: 0GitHub stars: 9
- 2521 01 About Us 2e4e587fOpenViking is an open-source context database initiated and maintained by ByteDance’s Volcano Engine Viking team, dedicated to building robust context engineering infrastructure for the AI Agent ecosystem. As a new-generation context database, OpenViking provides a unified data abstraction layer, an intelligent semantic parsing engine, and a high-performance hybrid retrieval system to deliver reliable backend support for all kinds of AI applications.Votes: 0GitHub stars: 9
- 2521 2024 05 24 Self Assembly 37b50370[](https://aider.chat/assets/self-assembly.jpg) {: .note } This article is quite old and outdated. Aider is currently writing about 70% of the new code in each release. See [aider's release history](/HISTORY.html) for the latest statistics. The [aider git repo](https://github.com/Aider-AI/aider) currently contains about 4K commits and 14K lines of code. Aider made 15% of the commits, inserting 4.8K and deleting 1.5K lines of code. About 7% of the cod...Votes: 0GitHub stars: 9
- 2521 Obsidian Cli C038dad5Control Obsidian from the command line or scripts using the Local REST API plugin. Create notes, append content, list files, and search your vault programmatically.Votes: 0GitHub stars: 9
- 2522 2024 07 01 Sonnet Not Lazy 630e8d66Claude 3.5 Sonnet represents a step change in AI coding. It is incredibly industrious, diligent and hard working. Unexpectedly, this presented a challenge: Sonnet was often writing so much code that it was hitting the 4k output token limit, truncating its coding in mid-stream. Aider now works around this 4k limit and allows Sonnet to produce as much code as it wants. The result is surprisingly powerful. Sonnet's score on [aider's refactoring benchmark](https://aider.chat/docs/leaderboards/#co...Votes: 0GitHub stars: 9
- 2522 Build Program 6794f052- **Inside GEPA (the `gepa` library)**, candidates are plain dicts: - `candidate: dict[str, str]` mapping **component names** → **text blobs**. - For normal predictors: `{"predictor_name": "new instruction text", ...}`. - For tool-optimized ReAct modules: special entries like `{"tool_module:<extract_predictor_name>": "<JSON string with instructions + tools>"}`.Votes: 0GitHub stars: 9
- 2522 Pdf 7df62397This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced features, JavaScript libraries, and detailed examples, see REFERENCE.md. If you need to fill out a PDF form, read FORMS.md and follow its instructions.Votes: 0GitHub stars: 9
- 2523 2024 11 21 Quantization 7b1bdc60{: .no_toc } <canvas id="quantChart" width="800" height="600" style="margin: 20px 0"></canvas> Open source models like Qwen 2.5 32B Instruct are performing very well on aider's code editing benchmark, rivaling closed source frontier models. But pay attention to how your model is being served and quantized, as it can impact code editing skill. Open source models are often available at a variety of quantizations, and can be served with different token limits. These details matter when working w...Votes: 0GitHub stars: 9
- 2523 Project Claude Librarian 50d18515Use when completing development phases and project context files may need updating - analyzes what changed since phase start, identifies affected CLAUDE.md or AGENTS.md files, and coordinates updates to maintain accurate project documentationVotes: 0GitHub stars: 9
- 2523 Tech Blog Cd8538c4Write technical blog posts that explain system internals, architecture, and implementation details.Votes: 0GitHub stars: 9
- 2524 2024 12 03 Qwq 223f2745{: .no_toc } <canvas id="qwqChart" width="800" height="500" style="margin: 20px 0"></canvas> QwQ 32B Preview is a "reasoning" model, which spends a lot of tokens thinking before rendering a final response. This is similar to OpenAI's o1 models, which are most effective with aider [when paired as an architect with a traditional LLM as an editor](https://aider.chat/2024/09/26/architect.html). In this mode, the reasoning model acts as an "architect" to propose a solution to the coding problem wi...Votes: 0GitHub stars: 9
- 2524 Context Utilization Abd87a1d**Opus**: Attends well to information regardless of position in long context. Can synthesize across distant sections. **Haiku**: Strong primacy and recency bias. Information in the middle of long contexts may be underweighted. **Mitigation**: Position-aware prompt design. - Place critical instructions at the START and END of the prompt - Keep context passages short and clearly labeled - Repeat key constraints AFTER the context block - For long documents, extract relevant snippets rather than ...Votes: 0GitHub stars: 9
- 2524 Synthesis Arl Applicable A7305dc8This document maps each ARL requirement (R1–R10) to what the logical process should do, when it activates, why it's needed, what success/failure looks like, and which framework patterns inform it. **Scope boundary:** This document describes what and why. It does not describe how to build it. No schemas, pseudocode, thresholds, file paths, or algorithm specifications. **Source:** All claims trace to Phase 1 Q&A exchanges and Phase 2 R-requirement mapping in the Q&A file (qa-expert-panel.md). ---Votes: 0GitHub stars: 9
- 2524 Tech Design Doc 72b9eae5- Designing a new feature or system - Documenting architecture decisions (ADR/RFC) - Planning refactoring or optimization workVotes: 0GitHub stars: 9
- 2525 2025 01 28 Deepseek Down B46d65b3{: .no_toc } <canvas id="editChart" width="800" height="450" style="margin-top: 20px"></canvas> DeepSeek's API has been experiencing significant reliability issues for the past 24-48+ hours, with many users reporting downtime and overload problems. Their [status page](https://status.deepseek.com) notes an ongoing incident. If you're affected by these issues, several alternative providers offer access to DeepSeek V3. This article compares their performance on aider's polyglot benchmark to help...Votes: 0GitHub stars: 9
- 2525 Summarization Fidelity 8ab789c0**Opus**: Produces summaries that accurately reflect source material. Naturally distinguishes between main claims and supporting detail. Maintains appropriate level of abstraction. **Haiku**: Summaries may: - Overweight content from the beginning/end of the source (position bias) - Lose nuance (turn hedged claims into definitive statements) - Miss the central thesis while including peripheral details - Add interpretive framing not present in the source **Mitigation**: Constrain the summarizat...Votes: 0GitHub stars: 9
- 2525 Xlsx 5d4e24fe- Use a consistent, professional font (e.g., Arial, Times New Roman) for all deliverables unless otherwise instructed by the userVotes: 0GitHub stars: 9
- 2526 2025 05 08 Qwen3 B8c3e75cAs [previously discussed when Qwen2.5 was released](/2024/11/21/quantization.html), details matter when working with open source models for AI coding. Proprietary models are served by their creators or trusted providers with stable inference settings. Open source models are wonderful because anyone can serve them, but API providers can use very different inference settings, quantizations, etc. Below are collection of aider polyglot benchmark results for the new Qwen3 models. Results are prese...Votes: 0GitHub stars: 9
- 2526 Yt Dlp C3a23a3e强大的视频下载工具，支持 1000+ 网站，包括 YouTube、Bilibili、Twitter、Instagram、TikTok 等。Votes: 0GitHub stars: 9
- 2526 Yt Dlp Ce34f4cb基于 yt-dlp 的专业视频下载工具，支持 YouTube、Bilibili、Twitter、Instagram 等 1000+ 网站。Votes: 0GitHub stars: 9
- 2527 Benchmarks 0125 C20592e5[](https://aider.chat/assets/benchmarks-0125.svg) [OpenAI just released a new version of GPT-4 Turbo](https://openai.com/blog/new-embedding-models-and-api-updates). This new model is intended to reduce the "laziness" that has been widely observed with the previous `gpt-4-1106-preview` model: > Today, we are releasing an updated GPT-4 Turbo preview model, gpt-4-0125-preview. This model completes tasks like code generation more thoroughly than th...Votes: 0GitHub stars: 9
- 2527 Cli Discuss Agent 3010b402Multi-CLI collaborative discussion agent with cross-verification and solution synthesis. Orchestrates 5-phase workflow: Context Prep → CLI Execution → Cross-Verify → Synthesize → OutputVotes: 0GitHub stars: 9
- 2528 Ctags 9dd05206Votes: 0GitHub stars: 9
- 2528 Ui Design Agent D94c4da6Specialized agent for UI design token management and prototype generation with W3C Design Tokens Format compliance. Core capabilities: - W3C Design Tokens Format implementation with $type metadata and structured values - State-based component definitions (default, hover, focus, active, disabled) - Complete component library coverage (12+ interactive components) - Animation-component state integration with keyframe mapping - Optimized layout templates (single source of truth, zero redundancy)...Votes: 0GitHub stars: 9
- 2528 Wagmi React E854d7d4Reference for React/wagmi hooks for building frontend blockchain applications.Votes: 0GitHub stars: 9
- 2528 Weekly Trade Blog Writer 5fab873aUse this agent when you need to create a comprehensive weekly trading strategy blog post for part-time traders and investors. Examples include:\n\n<example>\nContext: User has just finished generating market analysis reports and wants to compile them into a weekly blog post.\nuser: "今週のマーケット分析レポートができたので、ブログ記事を書いてください"\nassistant: "週間トレード戦略ブログ記事を作成します。まず、weekly-trade-blog-writerエージェントを起動して、既存のレポートを確認し、ブログ記事を生成します。"\n<commentary>\nThe user is requesting a weekly blog post creation. Use the Task...Votes: 0GitHub stars: 9
- 2529 Spec Reviewer 6692bfed高级代码评审员，专注于代码质量、最佳实践和安全性。评审代码的可维护性、性能优化和潜在漏洞。提供可操作的反馈，并能直接重构代码。与所有专业代理协作，确保一致的质量。Votes: 0GitHub stars: 9
- 2529 Unified Diffs 16b627c7 Aider now asks GPT-4 Turbo to use [unified diffs](#choose-a-familiar-editing-format) to edit your code. This dramatically improves GPT-4 Turbo's performance on a challenging new benchmark and significantly reduces its bad habit of "lazy" coding, where it writes code with comments like "...add logic here...". Aider's new "laziness" benchmark suite is designed to both provoke and quantify lazy coding. It consists of 89 python refactoring tasks wh...Votes: 0GitHub stars: 9
- 2530 Browser 27e56b0fAider can run in your browser, not just on the command line.Votes: 0GitHub stars: 9
- 2530 Latex Paper En 080fab3e英文学术论文 LaTeX 助手，支持格式检查、编译、语法分析和表达优化。Votes: 0GitHub stars: 9
- 2530 Validation Gates A1b8f9f3Testing and validation specialist. Proactively runs tests, validates code changes, ensures quality gates are met, and iterates on fixes until all tests pass. Call this agent after you implement features and need to validate that they were implemented correctly. Be very specific with the features that were implemented and a general idea of what needs to be tested.Votes: 0GitHub stars: 9
- 2531 Mastra 6f48164fUsing planning-with-files with [Mastra Code](https://code.mastra.ai/). ---Votes: 0GitHub stars: 9