All authors
Claude Skills by tools-only
github.com/tools-only19,166 skills18 installs6,168 views
- 055 Architecture 49f819e9OpenBotX is an AI assistant platform. It provides the infrastructure for running autonomous AI agents that communicate through multiple channels, execute tools, manage tasks, and maintain persistent memory -- all orchestrated through an async message bus. This document describes the system architecture, core components, and data flow. ---Votes: 0GitHub stars: 9
- 055 Architecture 5fc3966b`Lár` is not a heavy, complex framework. It is a tiny, powerful engine with 7 core "primitives." You can combine these "Lego bricks" to build any agent, from a simple chatbot to a complex, multi-agent orchestrator. - The `GraphExecutor` **What it is**: The "Engine" or "Conveyor Belt." **Job**: A simple `generator` that runs one node at a time. It's the "dumb" loop that powers the "smart" nodes. It is also the "flight data recorder" that `yields` the audit log for each step. - The `GraphState`...Votes: 0GitHub stars: 9
- 055 Architecture 6c7a6cdbThis document provides a comprehensive overview of Home Agent's architecture, including component relationships, data flow, and module structure.Votes: 0GitHub stars: 9
- 055 Architecture 78f986f8This document describes the architecture and design principles of OpenAkita.Votes: 0GitHub stars: 9
- 055 Architecture 8ca6b514> This document records the core architecture, design philosophy, and key implementation details of the SkillLite project.Votes: 0GitHub stars: 9
- 055 Architecture 97bc174a> **How Skill Seekers documentation is organized** ---Votes: 0GitHub stars: 9
- 055 Architecture C8b42f42How agents and clients connect through voicemode.dev.Votes: 0GitHub stars: 9
- 055 Architecture Cbe3b86c``` ┌──────────────────────────────────────────────────────────┐ │ vLLM API Layer │ │ (OpenAI-compatible: chat, completions, embeddings, │ │ audio, tools, MCP, reasoning) │ └──────────────────────────────────────────────────────────┘ │ ▼ ┌──────────────────────────────────────────────────────────┐ │ MLXPlatform │ │ (Votes: 0GitHub stars: 9
- 055 Architecture D5fcafaf> **Note**: Parts of this document describe legacy Python structure (core/, sandbox/, SkillManager, SkillRunner removed). For current architecture see [ARCHITECTURE_ANALYSIS_REPORT.md](../../todo/ARCHITECTURE_ANALYSIS_REPORT.md). Current Python SDK is a thin bridge (~200 lines) exporting `scan_code`, `execute_code`, `chat`, `run_skill`, `get_binary`; logic lives in the Rust binary.Votes: 0GitHub stars: 9
- 076 Authentication 9f3ca61aComplete guide to authentication methods for MCP servers in Claude Code plugins.Votes: 0GitHub stars: 9
- 1001 Soql Reference 58d87515```sql SELECT fields FROM object [WHERE conditions] [WITH filter] [GROUP BY fields] [HAVING conditions] [ORDER BY fields [ASC|DESC] [NULLS FIRST|LAST]] [LIMIT number] [OFFSET number] [FOR UPDATE] ```Votes: 0GitHub stars: 9
- 1001 Soql Reference 6c13c987```sql SELECT fields FROM object [WHERE conditions] [WITH filter] [GROUP BY fields] [HAVING conditions] [ORDER BY fields [ASC|DESC] [NULLS FIRST|LAST]] [LIMIT number] [OFFSET number] [FOR UPDATE] ```Votes: 0GitHub stars: 9
- 1001 Soql Reference 85fa3761<!-- Parent: sf-soql/SKILL.md -->Votes: 0GitHub stars: 9
- 1013 Specs 13b3aae8The PDD Prompt Linter analyzes Prompt-Driven Development (PDD) prompt files and produces actionable suggestions to improve prompt quality.Votes: 0GitHub stars: 9
- 102 Best Practices 064cbc39<!-- Parent: sf-apex/SKILL.md -->Votes: 0GitHub stars: 9
- 102 Best Practices 2fb9766d> Source: <https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices> This document covers practical authoring guidance for writing effective skills that agents can discover and use successfully. ---Votes: 0GitHub stars: 9
- 102 Best Practices E1c528d6> Source: <https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices> This document covers practical authoring guidance for writing effective skills that agents can discover and use successfully. ---Votes: 0GitHub stars: 9
- 1033 Structure 95818f9cComplete guide to Claude skill directory organization and file requirements.Votes: 0GitHub stars: 9
- 104 Bigquery Guide Eb84e01f**Tested with:** IDC data version v23 For most queries and downloads, use `idc-index` (see main SKILL.md). This guide covers BigQuery for advanced use cases requiring full DICOM metadata or complex joins.Votes: 0GitHub stars: 9
- 1043 Sync Skills Readme 154b4277Sync root README.md with current skills inventory from skills/ directoryVotes: 0GitHub stars: 9
- 1050 System Prompt 0ec11ccb始终仔细思考。保持耐心和彻底。不要过早放弃。 始终，保持极其简单。不要过度复杂化事情。 从零开始完成任务时，你应该： - 理解用户的需求 - 制定实现计划 - 逐一利用已有工具和能力完成任务 在处理现有代码库时，你应该： - 理解代码库和用户的需求。确定最终目标以及实现该目标的最重要标准。 - 对于错误修复，通常需要检查错误日志或失败的测试，扫描代码库以找到根本原因，并找出修复方法。如果用户提到任何失败的测试，你应该确保更改后这些测试能够通过。 - 对于功能开发，通常需要设计架构，并以模块化和可维护的方式编写代码，同时最小化对现有代码的侵入。如果项目已有测试，请添加新测试。 - 对于代码重构，如果接口发生更改，通常需要更新所有调用你正在重构的代码的地方。不要更改任何现有逻辑（尤其是在测试中），只专注于修复由接口更改引起的任何错误。 - 为实现目标进行最少的更改。这对你的性能非常重要。 - 遵循项目中现有代码的编码风格。 你的回答应该简洁明了，直奔主题。 除非用户要求详细解释，否则你必须用不超过 4 行的文字（不包括工具使用或代码生成）简洁地回答问题。 重要提示：在保证答案的实用性...Votes: 0GitHub stars: 9
- 1058 Target Annotations 21f1e0b9Open Targets defines a target as "any naturally-occurring molecule that can be targeted by a medicinal product." Targets are primarily protein-coding genes identified by Ensembl gene IDs, but also include RNAs and pseudogenes from canonical chromosomes.Votes: 0GitHub stars: 9
- 1082 Todo 9674497f- [x] **Fix YAML frontmatter parsing** — Removed HTML comments before `---` in 8 files (from @kylewhirl fork) - [x] **SSRF prevention in Python scripts** — Private IP blocking in fetch_page.py and analyze_visual.py (from @artyomsv #7) - [x] **Install hardening** — venv-based pip, no `--break-system-packages` (from @JawandS #2) - [x] **Windows install fixes** — `python -m pip`, `py -3` fallback, requirements.txt persistence (from @kfrancis #5, PR #6) - [x] **requirements.txt persistence** — CopieVotes: 0GitHub stars: 9
- 1087 Tools 118d5c25Command-line tools, Neovim utilities, and AI-assisted workflow patterns for this configuration.Votes: 0GitHub stars: 9
- 1087 Tools 70e8d015M4 exposes these tools to AI clients via the Model Context Protocol. Tools are filtered based on the active dataset's modality.Votes: 0GitHub stars: 9
- 1087 Tools 84fc5444OpenBotX is an AI assistant platform. Tools are Python functions the AI agent can call during conversations. This document provides a complete reference for all built-in tools, their parameters, and access rules.Votes: 0GitHub stars: 9
- 1087 Tools B91e0aa6**Package:** `src/tunacode/tools/`Votes: 0GitHub stars: 9
- 1087 Tools E7eb6c66**Package:** `src/tunacode/tools/`Votes: 0GitHub stars: 9
- 1087 Tools F9f2a2ed> Expose functions as executable capabilities for your MCP client. Tools are the core building blocks that allow your LLM to interact with external systems, execute code, and access data that isn't in its training data. In FastMCP, tools are Python functions exposed to LLMs through the MCP protocol. Tools in FastMCP transform regular Python functions into capabilities that LLMs can invoke during conversations. When an LLM decides to use a tool: 1. It sends a request with parameters based on t...Votes: 0GitHub stars: 9
- 1097 Troubleshooting 0f249dcdCommon issues and solutions for the MCP Context Provider.Votes: 0GitHub stars: 9
- 1097 Troubleshooting 161806951. **Test MCP server independently:** ```bash npx chrome-devtools-mcp@latest --help ```Votes: 0GitHub stars: 9
- 1097 Troubleshooting 271bcac1This guide covers common issues when using EvalView and how to resolve them.Votes: 0GitHub stars: 9
- 1097 Troubleshooting 4a1973c9Comprehensive troubleshooting guide for Azure AD OAuth2/OIDC integration issues.Votes: 0GitHub stars: 9
- 1097 Troubleshooting 50903b7f> This guide covers common issues when using EvalView for AI agent testing, including type errors, connection problems, framework-specific issues, and evaluation debugging.Votes: 0GitHub stars: 9
- 1097 Troubleshooting 7cf3f258**Symptoms**: CUDA out of memory during generation phaseVotes: 0GitHub stars: 9
- 1097 Troubleshooting A83f9df4**Error**: `make: *** No targets specified and no makefile found`Votes: 0GitHub stars: 9
- 1097 Troubleshooting Ad1270b4This document provides diagnostic procedures and resolution strategies for common issues encountered during Promptheus operation.Votes: 0GitHub stars: 9
- 1097 Troubleshooting F3910689Common issues and solutions when using Skill Seeker. ---Votes: 0GitHub stars: 9
- 1100 Tutorials Df587d76**Pages:** 59 ---Votes: 0GitHub stars: 9
- 1121 Validator 10fea6deQuality assurance agent. Runs tests, linters, type checks. Reports pass/fail with specific errors. Does not fix issues.Votes: 0GitHub stars: 9
- 1121 Validator D32a836aQuality assurance agent. Runs tests, linters, type checks. Reports pass/fail with specific errors. Does not fix issues.Votes: 0GitHub stars: 9
- 1128 Versioning Cd81ae77This document describes the versioning policy for this repository. We follow [Semantic Versioning](https://semver.org/). We will start our versioning at `v0.x.x`. Major version zero (0.y.z) is for initial development. Anything may change at any time. The public API should not be considered stable. SDK versions will follow this structure `<major>.<minor>.<patch>`: - `major` is incremented for any backwards-incompatible updates made to our [Cloud service / backend](https://cloud.jamaibase.com/)...Votes: 0GitHub stars: 9
- 1152 Worker 8c5ccf48Task implementation worker. Spawned by flow-next-work to implement a single task with fresh context. Do not invoke directly - use /flow-next:work instead.Votes: 0GitHub stars: 9
- 1153 Workflow 058cd28eFollow these steps in order. This workflow is **idempotent** - safe to re-run.Votes: 0GitHub stars: 9
- 1153 Workflow 30cfd097Follow these steps in order. This workflow is **idempotent** - safe to re-run.Votes: 0GitHub stars: 9
- 1153 Workflow B234b1d1The reviewer model only sees selected files—it's blind to the rest of the codebase. RepoPrompt's Context Builder (hereafter "Builder") is AI-powered—its strength is **discovering related context** the reviewer needs: - Existing patterns the changes should follow - Similar implementations for consistency - Architectural context (how things connect) - Dependencies and side effectsVotes: 0GitHub stars: 9
- 1156 Workflows 46d35683from Middleware.workflows.handlers.base.base_workflow_node_handler import BaseHandler from Middleware.workflows.models.execution_context import ExecutionContext class DatabaseQueryHandler(BaseHandler): def handle(self, context: ExecutionContext) -> str: query_template = context.config.get("query") resolved_query = context.workflow_variable_service.apply_variables( query_template, context ) connection_string = context.config.get("connectionString") result = f"Executed: {resolved_query}" return...Votes: 0GitHub stars: 9
- 1156 Workflows 479d3243This guide provides the complete, validated rules, structure, and component details for generating valid and effective workflows for the WilmerAI system. It has been verified against the system's source code (`workflow_manager.py`, `workflow_variable_manager.py`, and `workflow_processor.py`) to ensure total accuracy.Votes: 0GitHub stars: 9
- 1169 Main Eb458d72**WCAG 2.2 Compliance** für barrierefreie Web-Apps (fokussiert auf DresdenAIInsights)Votes: 0GitHub stars: 9
- 1178 Name Skill 00ca3e9cUse when interacting with Jira issues - searching, creating, updating, transitioning, commenting, logging work, downloading attachments, managing sprints, boards, issue links, fields, or users. Auto-triggers on Jira URLs and issue keys (PROJ-123).Votes: 0GitHub stars: 9