All authors
Claude Skills by tools-only
github.com/tools-only19,166 skills18 installs6,168 views
- 2473 Cache 9a3e46f6<Tip> Context caching functionality significantly reduces token consumption and response latency by caching repeated context content. When you repeatedly use the same system prompts or conversation history in dialogues, the caching mechanism automatically identifies and reuses this content, thereby improving performance and reducing costs. </Tip>Votes: 0GitHub stars: 9
- 2473 Cost Estimate Subagentagent Ff75e5d5Azure cost estimation subagent. Queries Azure Pricing MCP tools for real-time SKU pricing, compares regions, and returns structured cost breakdown. Isolates pricing API calls from the parent Architect agent's context window.Votes: 0GitHub stars: 9
- 2474 2026 02 11 00 00 00 Tinyagent Streaming Reimplementation 89582cbe**Date:** 2026-02-11 **Owner:** claude **Phase:** Research **git_commit:** 00f2bd6b653737664499363a01e871a00bf51342 **branch:** master ---Votes: 0GitHub stars: 9
- 2474 Gh Action 277dc840Make ReviewCerberus work as a GitHub Action that runs on PRs, posts a summary comment, and creates review comments on specific lines for each issue.Votes: 0GitHub stars: 9
- 2474 Governance Discovery Subagentagent 0091e699Azure governance discovery subagent. Queries Azure Policy assignments via REST API (including management group-inherited policies), classifies policy effects, and returns structured governance constraints. Isolates heavy REST API work from the parent Bicep Plan agent's context.Votes: 0GitHub stars: 9
- 2474 Governance Discovery Subagentagent 2593e580Azure governance discovery subagent. Queries Azure Policy assignments via REST API (including management group-inherited policies), classifies policy effects, and returns structured governance constraints. Isolates heavy REST API work from the parent Bicep Plan agent's context.Votes: 0GitHub stars: 9
- 2474 Stream Tool Aa22a0f7<Tip> Stream Tool Call is a unique feature of Z.ai's latest model, allowing real-time access to reasoning processes, response content, and tool call information during tool invocation, providing better user experience and real-time feedback. </Tip>Votes: 0GitHub stars: 9
- 2475 Grooming 2026 02 21 F58716b3**Date**: 2026-02-21 **Items groomed**: 39 active (1 DONE skipped) **Arguments**: all **Groomer agents launched**: 10 (2 waves of 5) + 1 single-item **Session branch**: claude/bulk-backlog-grooming-LIQDi ---Votes: 0GitHub stars: 9
- 2475 Infrastructure 7a539a9d**Package:** `src/tunacode/infrastructure/`Votes: 0GitHub stars: 9
- 2475 Locking 1342dd17This document teaches a systematic method for finding race conditions in Linux kernel code by tracing parallel execution timelines on shared data, and provides the locking reference needed to verify correctness.Votes: 0GitHub stars: 9
- 2475 Skill Anatomy 0e01cdaf**Want to understand how skills work under the hood?** This guide breaks down every part of a skill file. ---Votes: 0GitHub stars: 9
- 2475 Thinking Mode 5b81f305> GLM offers multiple thinking modes for different scenarios. The sections below explain how to enable each mode, key considerations, and example usage.Votes: 0GitHub stars: 9
- 2476 2026 02 16 Context Rail Inspector Styling Ec22be1aPolished the context rail inspector with theme-colored border title and reduced the core agents main module to 600 lines.Votes: 0GitHub stars: 9
- 2476 Migrate To Responses 173363a6Migrate to the Responses API ============================ The [Responses API](https://platform.openai.com/docs/api-reference/responses) is our new API primitive, an evolution of [Chat Completions](https://platform.openai.com/docs/api-reference/chat) which brings added simplicity and powerful agentic primitives to your integrations. **While Chat Completions remains supported, Responses is recommended for all new projects.** About the Responses API ----------------------- The Responses API is a...Votes: 0GitHub stars: 9
- 2476 Setup With Gemini 14e7ae1eThis example shows you how to set up **Prompt-Driven Development (PDD)** with a free **Gemini API key** and run the built-in **Hello** example. > **Goal:** By the end, you'll have PDD installed, Gemini configured, and `pdd sync` running on the Hello example. ---Votes: 0GitHub stars: 9
- 2476 Tasks 3 Validator Ci Gate 11d5ba9bThe backlog item (added 2026-02-14) described 19 errors and 63 warnings preventing the validate-plugins CI step from being blocking. As of 2026-02-18, the situation has changed dramatically:Votes: 0GitHub stars: 9
- 2477 2026 02 16 Slopgotchi Pet Widget 36184264Added a decorative ASCII pet widget to the context inspector panel. Clicking the pet shows a red heart and cycles through ASCII art frames with a bounce animation.Votes: 0GitHub stars: 9
- 2477 Adapters 98b83b97> Adapters are the bridge between EvalView and your AI agent. EvalView includes dedicated adapters for LangGraph, CrewAI, OpenAI Assistants, Anthropic Claude, HuggingFace, Ollama, MCP servers, and generic HTTP/streaming APIs. You can also build custom adapters for proprietary frameworks. Adapters connect EvalView to your AI agent's API. EvalView includes adapters for common patterns and makes it easy to build custom ones.Votes: 0GitHub stars: 9
- 2477 Audit E82b525bThis document helps independent auditors verify Hardstop's security claims efficiently. **Target:** "Safe to install" rating **Version:** 1.3.5 **Last Updated:** 2026-01-31 ---Votes: 0GitHub stars: 9
- 2477 Data Model Reference F7c247c5Complete documentation of the Agentforce Session Tracing Data Model stored in Salesforce Data Cloud. > **Source**: [Salesforce Help - Data Model for Agentforce Session Tracing](https://help.salesforce.com/s/articleView?id=ai.generative_ai_session_trace_data_model.htm)Votes: 0GitHub stars: 9
- 2477 Health Check F51b246dYou are a DevOps agent responsible for keeping an OpenClaw AI assistant instance healthy. You run hourly via cron. Be fast, be autonomous, be quiet when things are fine.Votes: 0GitHub stars: 9
- 2477 Mcp Developer Guide Json Rpc Fac51d04This comprehensive guide demonstrates how to interact with MCP (Model Context Protocol) servers using raw JSON-RPC commands via `curl` or through STDIO. This is essential for developers who want to understand the MCP protocol at a low level, integrate MCP into custom applications, or debug MCP implementations.Votes: 0GitHub stars: 9
- 2477 Neon Serverless 3766cb1dPatterns and best practices for connecting to Neon databases in serverless environments using the `@neondatabase/serverless` driver. The driver connects over **HTTP** for fast, single queries or **WebSockets** for `node-postgres` compatibility and interactive transactions. For official documentation: ```bash curl -H "Accept: text/markdown" https://neon.com/docs/serverless/serverless-driver ```Votes: 0GitHub stars: 9
- 2477 Text 6e7a1c9afile = client.files.create( file=open("draconomicon.pdf", "rb"), purpose="user_data", ) response = client.responses.create( model="gpt-5", prompt={ "id": "pmpt_abc123", "variables": { "topic": "Dragons", "reference_pdf": { "type": "input_file", "file_id": file.id, }, }, }, ) print(response.output_text) ``` ``` curl https://api.openai.com/v1/responses -H "Authorization: Bearer $OPENAI_API_KEY" -H "Content-Type: application/json" -d '{ "model": "gpt-5", "prompt": { "id": "pmpt_abc123", "v...Votes: 0GitHub stars: 9
- 2477 Warp D095774eThis file provides guidance to WARP (warp.dev) when working with code in this repository.Votes: 0GitHub stars: 9
- 2478 2026 02 16 Update File Before After Separator Lane 0553d33cImproved readability of `update_file` side-by-side diffs by adding a visible change lane (`-│`, `+│`, ` │`) and explicit `Before`/`After` captions.Votes: 0GitHub stars: 9
- 2478 Backend Requirements 4ae9bbe4> This document outlines what your AI agent backend needs to expose for EvalView testing. EvalView supports three tiers: basic (just text response), metadata (response + cost/tokens), and full streaming (JSONL event stream with tool calls).Votes: 0GitHub stars: 9
- 2478 Copilotkit 9ebf6b0d**Research Date**: 2026-02-23 **Source URL**: <https://copilotkit.ai/> **GitHub Repository**: <https://github.com/CopilotKit/CopilotKit> **npm**: <https://www.npmjs.com/package/@copilotkit/runtime> **Version at Research**: v1.51.4 (released 2026-02-17) **License**: MIT **Docs**: <https://docs.copilotkit.ai> ---Votes: 0GitHub stars: 9
- 2478 Documentation Updates Summary 665ee62f**Date:** 2026-02-22 **Version:** 3.1.0 **Purpose:** Document all documentation updates related to CLI flag synchronization ---Votes: 0GitHub stars: 9
- 2478 Privacy A4277601[Aider AI LLC](/docs/faq.html#what-is-aider-ai-llc) (“Aider,” “we,” “our,” and/or “us”) values the privacy of individuals who use our website, programming tools, and related services (collectively, our “Services”). This privacy policy (the “Privacy Policy”) explains how we collect, use, and disclose information from users of our Services. By using our Services, you agree to the collection, use, disclosure, and procedures this Privacy Policy describes. We may collect a variety of information f...Votes: 0GitHub stars: 9
- 2478 Proposal 8df4efd1添加 Tushare 财务数据完整系列插件：利润表(income)、资产负债表(balancesheet)、现金流量表(cashflow)、业绩预告(forecast)、业绩快报(express)、**财务审计意见(fina_audit)**，以及三大报表的 **VIP 版本(income_vip、balancesheet_vip、cashflow_vip)**，覆盖 Tushare 财务数据模块的全部 9 个接口。Votes: 0GitHub stars: 9
- 2478 Proposal C67b1b6e当前智能对话入口缺少统一的"协调 Agent"进行意图解析与Agent调度，且未在无可用Agent时回退到MCP工具。需要建立可复用的调度模块，先接入chat入口，后续可扩展到其它分析入口。Votes: 0GitHub stars: 9
- 2478 Query Patterns D730b2b3Common query patterns for extracting and analyzing Agentforce session tracing data. > **Official Reference**: [Get Insights from Agent Session Tracing Data](https://help.salesforce.com/s/articleView?id=ai.generative_ai_session_trace_use.htm)Votes: 0GitHub stars: 9
- 2478 Skills Quickstart Eb1dee96> 3 分钟上手 Skills 知识外化系统 ---Votes: 0GitHub stars: 9
- 2479 2026 02 17 Thinking Delta Tui Integration 09df255dImplemented end-to-end thinking stream integration for TunaCode TUI:Votes: 0GitHub stars: 9
- 2479 Custom Lightning Types 5ddaa3dd> Build custom UI components for agent action inputs and outputs using LightningTypeBundleVotes: 0GitHub stars: 9
- 2479 Database Setup B57196ca> EvalView does NOT require a database. This guide is only for teams whose AI agents require a valid user ID in their database. It shows how to set up test users for PostgreSQL, MongoDB, MySQL, Firebase, and Supabase.Votes: 0GitHub stars: 9
- 2479 Google Ai Studio 293ed116**Research Date**: 2026-02-23 **Source URL**: <https://aistudio.google.com/> **Documentation**: <https://ai.google.dev/gemini-api/docs> **GitHub (Cookbook)**: <https://github.com/google-gemini/cookbook> **Version at Research**: Gemini 2.5 Pro / Gemini 3 (preview) **License**: Free tier available; paid usage billed per token via Google account ---Votes: 0GitHub stars: 9
- 2479 Google Ai Studio Fc156345**Research Date**: 2026-02-23 **Source URL**: <https://aistudio.google.com/> **GitHub Repository**: <https://github.com/google-gemini/cookbook> **Version at Research**: Web service - no versioning **License**: Free to use (SaaS); API terms at <https://ai.google.dev/gemini-api/terms> ---Votes: 0GitHub stars: 9
- 2479 Multi Source 9f256d80> **Skill Seekers v3.1.0** > **Combine documentation, code, and PDFs into one skill** ---Votes: 0GitHub stars: 9
- 2479 Streaming Sse Guide 56799ef2**流式输出**是 HelloAgents 框架的实时响应能力，支持 SSE（Server-Sent Events）协议，实现打字机效果和实时进度反馈。Votes: 0GitHub stars: 9
- 2479 Tasks Da032476- [ ] 设计统一策略基类 `BaseStrategy` - [ ] 实现策略注册中心 `StrategyRegistry` - [ ] 创建策略元数据模型 `StrategyMetadata` - [ ] 设计参数配置schema系统 - [ ] 实现策略验证框架Votes: 0GitHub stars: 9
- 2479 Vulnerability Patterns 2d771fb2This reference catalogs common security vulnerability patterns, insecure coding idioms, and historical CVE-style patterns with detection techniques and exploitability assessment.Votes: 0GitHub stars: 9
- 2479 Vulnerability Patterns Fb8a1472**Root Causes:** - Missing bounds check on array/buffer access - Incorrect size calculation (off-by-one) - Assumption that input fits in fixed-size buffer - Unsafe string functions (strcpy, sprintf)Votes: 0GitHub stars: 9
- 2480 2026 02 16 Diff Rendering Pipeline 9cf5a41a**Date:** 2026-02-16 **Phase:** ResearchVotes: 0GitHub stars: 9
- 2480 Design 02377a64本设计文档描述"数据浏览器"功能的技术实现方案，包括后端 API 设计、前端组件结构、SQL 安全校验机制等。Votes: 0GitHub stars: 9
- 2480 Design 497a09d9ETF数据插件采用与现有tushare插件相同的架构模式，继承`BasePlugin`基类，实现ETL流程。Votes: 0GitHub stars: 9
- 2480 Design 6d97a46c智能策略系统整合了传统策略回测和AI策略生成能力，形成一个完整的策略生命周期管理平台。Votes: 0GitHub stars: 9
- 2480 Framework Support 3e670e71> EvalView provides dedicated testing adapters for the most popular AI agent frameworks. Each adapter handles framework-specific API formats, tool call extraction, and response parsing automatically. EvalView supports multiple AI agent frameworks out of the box. Each framework has a dedicated adapter that handles its specific API format.Votes: 0GitHub stars: 9
- 2480 Models Api 85cb0253> Native AI generation in Apex using `aiplatform.ModelsAPI` namespaceVotes: 0GitHub stars: 9