tools-only
- 17k skills
- 0 followers
- 7 repo stars
- last week last updated
- ▌ Bootstrap Script Usage Guide · tools-only bundlesrc/bootstrap.py is a script runner that allows you to run any test script with zero cognitive overhead, automatically handling all environment setup.
- ▌ Build And Publish Litellm Proxy Extras · tools-only bundleThis runbook covers building and publishing a new version of the litellm-proxy-extras PyPI package. For use by litellm engineers only.
- ▌ Device Authorization Flow Template · tools-only bundleOAuth 2.0 Device Authorization Grant for input-constrained devices without browsers.
- ▌ Deployment Targets · tools-only bundleDeploy via Git integration or the LangSmith control plane (UI/API).
- ▌ Openwebui With Ollama Litellm Mcpo And MCP Gateway · tools-only bundleThis guide provides a comprehensive walkthrough for deploying OpenWebUI with local LLM models via Ollama, integrated with MCP (Model Context Protocol) tools through MCPO and MCP Gateway.
- ▌ Stdio Wrapper Mcpgateway Wrapper · tools-only bundlemcpgateway.wrapper ships inside the main PyPI package and re-publishes your Gateway's tools / prompts / resources over stdin ↔ stdout, while connecting securely to the gateway using SSE + JWT.
- ▌ Virtual MCP Server Design Document · tools-only bundleA Virtual MCP Server is a gateway-level construct that aggregates tools, resources, and prompts from multiple backend MCP servers into a single unified endpoint.
- ▌ Extraction Patterns And Question Techniques · tools-only bundleThis reference provides detailed patterns for extracting expertise through strategic questioning and active listening. The goal is to transform implicit knowledge into explicit, documented expertise.
- ▌ Permission Analysis · tools-only bundleFramework for evaluating tool permissions granted to agent skills.
- ▌ Extraction Criteria And Best Practices · tools-only bundleThis document defines when and how to extract components from Claude Code commands and agents into skills.
- ▌ Evidence Discipline · tools-only bundlePrimary-source verification. Training data recall is explicitly rejected as evidence.
- ▌ Plugins Reference · tools-only bundleComplete technical reference for the Claude Code plugin system, including schemas, CLI commands, and component specifications.
- ▌ MCP Gateway Security Features · tools-only bundleFor production deployments, always include JTI in issued tokens to enable proper caching, revocation, and audit capabilities.
- ▌ Neon Platform API 2 · tools-only bundleThe Neon Platform API allows you to manage Neon projects, branches, databases, and resources programmatically. You can use the REST API directly or through official SDKs.
- ▌ Contextforge Security Features · tools-only bundleFor production deployments, always include JTI in issued tokens to enable proper caching, revocation, and audit capabilities.
- ▌ Evermemos Configuration Guide · tools-only bundleThis guide provides a detailed explanation of the configuration options in env.template. Before deploying EverMemOS, please copy env.template to .env and fill in your actual configuration values according to this guide.
- ▌ Allowed Tools Field Guide · tools-only bundleComprehensive guide to using the allowed-tools frontmatter field in Claude Code Skills.
- ▌ Claude Code Subagents Reference · tools-only bundleComplete technical reference for Claude Code subagents architecture, configuration, and usage patterns.
- ▌ Phase 5 5 Customerwebclient Surface Enablement · tools-only bundleThe Agent Runtime API requires OAuth with chatbotapi, sfapapi, and api scopes. See /sf-connected-apps for ECA creation.
- ▌ Anthropic Typescript API Library · tools-only bundleThis library provides convenient access to the Anthropic REST API from server-side TypeScript or JavaScript.
- ▌ Hook Implementation Guide · tools-only bundleProgressive guide from quick code templates to production-ready examples.
- ▌ Message Sanitization For Tool Calling For Anthropic Models · tools-only bundleLiteLLM can automatically sanitize messages to handle common issues that occur during tool calling workflows, especially when using OpenAI-compatible clients with providers that have strict message format requirements…
- ▌ Tmux Plus Claude Code Workflow Reference · tools-only bundleQuick reference for tmux session management with Claude Code.
- ▌ Quick Start Testing Langgraph With Evalview · tools-only bundleThis guide gets you testing your LangGraph agent in 5 minutes.
- ▌ Quick Start Testing Langgraph Agents With Evalview · tools-only bundleRun with --verbose to see the actual API response, then update your test YAML files with the correct tool names.
- ▌ Fix And Debugging 3 · tools-only bundleYou are helping a developer fix a bug or debug an issue. Follow a systematic approach: understand the problem, trace the root cause, design a minimal fix, then implement and verify.
- ▌ Migrating To Claude 4 5 · tools-only bundleBoth migrations involve breaking changes that require updates to your implementation. This guide will walk you through each migration path with step-by-step instructions and clearly marked breaking changes.
- ▌ Worktree Isolation · tools-only bundleWorktree isolation enables tasks to run in dedicated git worktrees, providing complete filesystem isolation for parallel work. This eliminates file conflicts when multiple agents or streams are working simultaneously.
- ▌ Vs Code Extension Release Plan · tools-only bundleRelease all features from mcp-server-full/ as a comprehensive VS Code extension.
- ▌ Socratic Questioning · tools-only bundleStructured question frameworks for exposing assumptions and deepening understanding.
- ▌ Opentelemetry Events Migration Guide · tools-only bundleThis guide documents the migration pattern from span events to OTel log events for LLM instrumentation, following the OpenTelemetry Gen-AI Semantic Conventions.
- ▌ Pii Analysis Workflow Feature · tools-only bundleThe PII Analysis Workflow feature enables users to scan documents for personally identifiable information (PII) and sensitive data patterns using AI-powered analysis.
- ▌ Environment Variable Management · tools-only bundleGuide for managing environment variables and secrets across LangSmith deployment modes.
- ▌ Step 4 Implementation Plan Pci Dss Gw · tools-only bundlePhased Bicep implementation for a PCI-DSS Level 1 compliant payment processing platform on Azure.
- ▌ Step 4 Implementation Plan Pci Dss Gw 2 · tools-only bundlePhased Bicep implementation for a PCI-DSS Level 1 compliant payment processing platform on Azure.
- ▌ Admin UI Customization · tools-only bundleMCP Gateway's Admin UI supports flexible section visibility for embedding in third-party portals, restricting views for specific audiences, and reducing dashboard clutter.
- ▌ Step 4 Implementation Plan Pci Dss Gateway · tools-only bundlePhased Bicep implementation for a PCI-DSS Level 1 compliant payment processing platform on Azure.
- ▌ Agent Lifecycle Audit Research Document · tools-only bundleDeep semantic validation of how agents are configured, what they claim to do, what tools and skills they have access to, and whether their prompts align with the actual capabilities of the components they invoke.
- ▌ Dangerous Code Patterns · tools-only bundlePatterns to check when scanning scripts bundled with agent skills.
- ▌ Linting And Formatting Setup · tools-only bundleHive uses Ruff for all Python linting and formatting. This document explains the tooling, how to set it up locally, and what happens in CI.
- ▌ Kuyuchi Container Audit And Split Proposal · tools-only bundleSome docs describe behavior that differs from code (example: claims about socket handling and privileges).
- ▌ Plugin Validator Implementation Task Decomposition · tools-only bundleImplement core data structures for validation results, issues, and error codes. These models are used by all validators and reporters.
- ▌ Python Project Structure Examples · tools-only bundleRecommended for complex applications with multiple agents or modular architecture.
- ▌ Discovering Available Slash Commands · tools-only bundleSlash commands provide a way to control Claude Code sessions with special commands that start with /.
- ▌ Slash Commands Reference · tools-only bundleControl Claude's behavior during an interactive session with slash commands.
- ▌ Apex Security Guide · tools-only bundleUse for most classes. Enforces record-level security (OWD, sharing rules).
- ▌ Zero Config Installation Guide · tools-only bundleInstalls framework to ~/.claude/copilot for use across all projects.
- ▌ Langgraph JSON Configuration Reference · tools-only bundleThe langgraph.json file specifies dependencies, graphs, environment variables, and other settings required to deploy a LangGraph application. The LangGraph CLI uses this file to build and run your application.
- ▌ Scaling Configuration · tools-only bundleGuide for scaling LangSmith deployments with currently documented controls.
- ▌ Environment Variables Reference Skill Seekers · tools-only bundleVariables are read at runtime and override default settings.
- ▌ Environment Variables Reference 2 · tools-only bundle👉 New to Qdrant? See the Qdrant Setup Guide for step-by-step instructions on creating a collection with the right settings.
- ▌ Environment Variables Reference 3 · tools-only bundle👉 New to Qdrant? See the Qdrant Setup Guide for step-by-step instructions on creating a collection with the right settings.
- ▌ Batch Evaluation Quick Start Guide · tools-only bundleThe batch evaluation infrastructure allows you to evaluate multiple skills at once with automatic test data generation, parallel execution, and comprehensive reporting.
- ▌ Switch Docs Theme To Hextra Implementation Plan · tools-only bundleReplace Docsy module import with Hextra and update params to common Hextra patterns (menu search item, GitHub icon, navbar settings, edit link).
- ▌ Fullstack Development Workflows · tools-only bundleComplete development lifecycle workflows from local setup to production deployment.
- ▌ Governance Constraints Pci Dss Gw · tools-only bundleThis document captures the governance constraints and Azure Policy requirements that must be addressed in the Bicep implementation for the PCI-DSS Level 1 payment gateway.
- ▌ What S Changed · tools-only bundleThe Claude Code SDK has been renamed to the Claude Agent SDK and its documentation has been reorganized. This change reflects the SDK's broader capabilities for building AI agents beyond just coding tasks.
- ▌ Plugin Marketplaces · tools-only bundleCreate and manage plugin marketplaces to distribute Claude Code extensions across teams and communities.
- ▌ Registry Deployment And Registry Mode Configuration · tools-only bundleThis guide explains the DEPLOYMENTMODE and REGISTRYMODE environment variables that control how the MCP Gateway Registry operates.
- ▌ Step 4 Governance Constraints Pci Dss Gateway · tools-only bundleThis document captures the governance constraints and Azure Policy requirements that must be addressed in the Bicep implementation for the PCI-DSS Level 1 payment gateway.
- ▌ Linting Discovery Protocol · tools-only bundleLanguage plugins MUST implement a discovery sequence before executing quality gates. The harness does not assume lint/format/typecheck tools are present or configured.
- ▌ Medical Device Cybersecurity Guidance · tools-only bundleComplete framework for FDA cybersecurity requirements based on FDA guidance documents and recognized consensus standards.
- ▌ Orchestration Workflow · tools-only bundleParallel stream execution using Claude Code's native Task tool. The /orchestrate command is a thin scaffolding layer -- it creates worktrees and validates streams, but does not launch agents.
- ▌ Virtual MCP Server Operations · tools-only bundleThis document describes operations for managing Virtual MCP Servers. Virtual servers aggregate tools from multiple backend MCP servers into a single unified endpoint.
- ▌ Auto Sync Anthropic Beta Headers · tools-only bundleAutomatically keep your Anthropic beta headers configuration up to date without restarting your service. This allows you to support new Anthropic beta features across all providers without restarting your service.
- ▌ Plugin Validator QA Report Task T23 · tools-only bundleThe plugin-validator implementation (T1-T22) is 93% complete. All 23 error codes are implemented, type checking passes, and the validator successfully validates real plugins.
- ▌ Virtual MCP Server How It Works · tools-only bundleThis document explains how Virtual MCP Servers work using diagrams and examples. For detailed implementation specifics, see virtual-mcp-server.md.
- ▌ Troubleshooting Deployment Issues · tools-only bundleIn control-plane deployments, tracing project + tracing env wiring is managed by control plane.
- ▌ Docs Hugo Docsy Migration Implementation Plan · tools-only bundleModify README.md to reference the Hugo docs path (e.g., docs/ or the hosted site URL).
- ▌ Context Manifest · tools-only bundleLines 904-911 in NamespaceReferenceValidator contain unreachable nested skill reference resolution after early return line 903. Verify with coverage before removal.
- ▌ Orchestration Troubleshooting Guide · tools-only bundleThis guide helps diagnose and fix common orchestration issues quickly. Based on real incidents and production debugging sessions.
- ▌ Control Center Application Roles · tools-only bundleAdded two new application roles for finer-grained access control to the Control Center, enabling organizations to delegate administrative functions while maintaining security boundaries.
- ▌ Governance Discovery Instructions 4 · tools-only bundlecannot be retrieved, STOP and inform the user. Do NOT generate governance constraints from assumptions.
- ▌ Backlog Item Groomed Schema 2 · tools-only bundleDo not duplicate name, description, source, added, priority, type, issue in the body — they live in frontmatter.
- ▌ Gsap Motion Graphics Patterns Research · tools-only bundleRemotion renders each frame independently. GSAP timelines must be paused and seeked to the correct time on every frame. The pattern follows the same approach Remotion uses for Anime.js integration.
- ▌ Python Development Orchestration Guide · tools-only bundleComprehensive guide for orchestrating Python development tasks using specialized agents and commands.
- ▌ Deploying The MCP Gateway Stack To Ibm Cloud Kubernetes · tools-only bundleThis guide is in preview and will continue to evolve. Content is accurate but may receive refinements as the Helm chart and GitOps flows mature.
- ▌ Issue Description 3 · tools-only bundleThe workflow PDF viewer was not utilizing the full height of the left pane, resulting in a cramped viewing experience with significant unused vertical space.
- ▌ Tasks Plugin Validator UX And Coverage Gaps · tools-only bundleFix UX bugs and expand validation coverage in plugin-validator.py. Four independent sub-issues from groomed backlog item.
- ▌ Tasks Plugin Validator UX And Coverage Gaps 2 · tools-only bundleFix UX bugs and expand validation coverage in plugin_validator.py. Four independent sub-issues from groomed backlog item.
- ▌ Skill Completeness Report Agentskills · tools-only bundleThis is a reference/knowledge skill, not an operational skill, so preparation is less critical than for document-processing skills.
- ▌ Human Out Of Loop Prerequisites · tools-only bundleResearch analysis identifying what must be known, measured, and verified before autonomous refinement loops can operate without human review gates.
- ▌ Task Plan Fix Changelog References To Nonexistent Files · tools-only bundleThe conventional-commits plugin has dead references in CHANGELOG.md (docs/examples.md, placeholder release URL) and in SKILL.md Related Skills (git-commit-helper, semantic-release). All must be removed or fixed.
- ▌ Architecture Spec Fix Changelog References To Nonexistent · tools-only bundleThis is a documentation-only fix. No Python code, CLI commands, or architectural components are being added.
- ▌ Openclaw Integration Design · tools-only bundleIntegrate agent-security-scanner-mcp with OpenClaw (formerly Clawdbot), providing security guardrails for the autonomous AI assistant.
- ▌ State Diagram · tools-only bundleA CI/CD pipeline modeled as a state machine with 3 composite (nested) states, each containing internal substates.
- ▌ Basic Usage 5 · tools-only bundleHooks are a composable extensibility mechanism for extending agent functionality by subscribing to events throughout the agent lifecycle.
- ▌ Basic Usage 6 · tools-only bundleHooks are a composable extensibility mechanism for extending agent functionality by subscribing to events throughout the agent lifecycle.
- ▌ State Management 3 · tools-only bundleUnderstanding how state works in Strands is essential for building agents that can maintain context across multi-turn interactions and workflows.
- ▌ Bidiagent Experimental · tools-only bundleThe BidiAgent is a specialized agent designed for real-time bidirectional streaming conversations.
- ▌ Evermemos Overview · tools-only bundleBuild AI memory that never forgets, making every conversation built on previous understanding.
- ▌ Better Auth Passkey Webauthn Guide · tools-only bundleBetter Auth supports passkey authentication through the @better-auth/passkey plugin. Passkeys provide passwordless authentication using biometrics (fingerprint, face recognition), device PIN, or physical security keys.
- ▌ State API Reference · tools-only bundleAdvanced state management for synchronizing UI elements and introducing controlled cycles.
- ▌ Hooks Experimental · tools-only bundleHooks provide a composable extensibility mechanism for extending BidiAgent functionality by subscribing to events throughout the bidirectional streaming lifecycle.
- ▌ Install The Sdk 3 · tools-only bundleThis quickstart guide shows you how to create your first basic Strands agent, add built-in and custom tools to your agent, use different model providers, emit debug logs, and run the agent locally.
- ▌ Advanced Features 9 · tools-only bundleThe client_args configure the underlying OpenAI client. For a complete list of available arguments, please refer to the OpenAI source.
- ▌ Environment Variables 11 · tools-only bundleOpenAI provides access to GPT models, Whisper speech recognition, text-to-speech, and embeddings through their comprehensive API platform.
- ▌ Uniswap AI · tools-only bundleUniswap-specific AI tools (skills, plugins, agents) for developers and AI agents integrating the trading API.
- ▌ Architecture Overview 12 · tools-only bundleThis document provides a comprehensive overview of Local Deep Research's system architecture.
- ▌ Uniswap AI 2 · tools-only bundleUniswap-specific AI tools (skills, plugins, agents) for developers and AI agents integrating the trading API.