tools-only
- 17k skills
- 0 followers
- 7 repo stars
- last week last updated
- ▌ Arl Expert Panel · tools-only bundleYou are the orchestrator for the Autonomous Refinement Loop (ARL) expert panel process.
- ▌ Security Policy 2 · tools-only bundleThe Skills Directory takes security seriously. Every skill is analyzed for potential risks, and high-risk skills require additional safeguards. This document explains our security framework and policies.
- ▌ Quickstart To Building An Intelligent Textbook · tools-only bundleCopy these lines into Claude one at a time and verify they work.
- ▌ Welcome Screen Implementation · tools-only bundleThe Skene Skills Directory now features a beautiful, branded welcome screen using Charm-inspired libraries for professional terminal UI rendering.
- ▌ Analyze Command · tools-only bundleThe analyze command scans a codebase to detect its technology stack, identify existing growth features, surface growth opportunities, and flag revenue leakage -- all powered by an LLM of your choice.
- ▌ Analyze Command 2 · tools-only bundleThe analyze command scans a codebase to detect its technology stack, identify existing growth features, surface growth opportunities, and flag revenue leakage -- all powered by an LLM of your choice.
- ▌ Mermaid Diagram Generator 4 · tools-only bundleGenerate simple minimalist but colorful interactive workflow diagrams using Mermaid.js for intelligent textbooks.
- ▌ Mermaid Diagram Generator 5 · tools-only bundleGenerate simple minimalist but colorful interactive workflow diagrams using Mermaid.js for intelligent textbooks.
- ▌ Publication Figure Design Theory Derived From Repository · tools-only bundleThis theory is inferred from 22 Python plotting scripts in this repository.
- ▌ Openviking Team And Organization · tools-only bundleOpenViking 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.
- ▌ Hook Events Reference · tools-only bundleComplete reference for all Claude Code hook event types, their behaviors, and use cases.
- ▌ Conversation Metadata Control Guide · tools-only bundleThis guide explains when and how to control metadata for optimal results.
- ▌ Batch Operations Guide · tools-only bundleThis guide explains how to efficiently process multiple messages using EverMemOS's batch operations.
- ▌ Storage Backends · tools-only bundleFastMCP uses pluggable storage backends for caching responses and managing OAuth state. By default, all storage is in-memory, which is perfect for development but doesn't persist across restarts.
- ▌ Web Dashboard · tools-only bundleThe default interface for PocketPaw — a browser-based control panel for chatting, managing channels, and monitoring agent activity.
- ▌ Quick Wins Value In Your First Day · tools-only bundleGet immediate value from Skills Directory with these time-boxed quick wins. Start small, prove ROI, then expand.
- ▌ Inspiration And References · tools-only bundleThanks to the following projects, communities, and individuals for their inspiration and support.
- ▌ Manifest Schema Reference · tools-only bundleComplete JSON schema reference for growth manifests produced by skene-growth analysis.
- ▌ Skills Directory Complete Project Summary · tools-only bundleBuilt a complete, production-ready AI Skills Directory with enterprise-grade architecture, comprehensive security, automated remediation, and developer-friendly tooling.
- ▌ Mission Control · tools-only bundleMulti-agent orchestration system for PocketPaw. Coordinate multiple AI agents working together like a team.
- ▌ Guided Refactoring · tools-only bundlePerform safe, incremental refactoring with test verification at every step.
- ▌ Security Auditor 3 · tools-only bundleDeep security analysis AFTER code is written. Complements code-reviewer (which catches surface-level security at Critical severity) with deeper OWASP-focused analysis.
- ▌ Security Auditor 4 · tools-only bundleDeep security analysis AFTER code is written. Complements code-reviewer (which catches surface-level security at Critical severity) with deeper OWASP-focused analysis.
- ▌ Background Tasks · tools-only bundleFastMCP implements the MCP background task protocol (SEP-1686), giving your servers a production-ready distributed task scheduler with a single decorator change.
- ▌ Choosing Between Query And Claudesdkclient · tools-only bundleCreates a new session for each interaction with Claude Code. Returns an async iterator that yields messages as they arrive. Each call to query() starts fresh with no memory of previous interactions.
- ▌ Openai Python Sdk · tools-only bundleIn some scenarios, there are still differences between Z.AI and OpenAI interfaces, but this does not affect overall compatibility.
- ▌ Openai Python API Library · tools-only bundleThe OpenAI Python library provides convenient access to the OpenAI REST API from any Python 3.9+ application.
- ▌ How Effort Works · tools-only bundleControl how many tokens Claude uses when responding with the effort parameter, trading off between response thoroughness and token efficiency.
- ▌ Evidence Audit · tools-only bundleFalsificationism and evidence quality assessment for auditing whether claims are actually supported by evidence.
- ▌ Skill Chain Cookbook · tools-only bundleThese recipes expand into new domains with 95%+ skill coverage validated against the library.
- ▌ Visual Elements Library · tools-only bundleIcon and symbol vocabulary organized by topic. Use these as building blocks for cover compositions.
- ▌ Orchestrator Worker Pattern · tools-only bundleThe orchestrator-worker pattern distributes independent tasks across multiple worker agents that execute in parallel, then aggregates their results. Best for parallelizable workloads.
- ▌ Full OAUTH Server · tools-only bundleThe Full OAuth Server pattern exists to support the MCP protocol specification's requirements.
- ▌ Smart Memory System Development Guide · tools-only bundleThis document provides detailed guidance for developers on interface definitions, Mock implementations, and decoupled development.
- ▌ Entity Action API 2 · tools-only bundleAirbyte Agent Connectors use a unified entity-action model for interacting with third-party APIs. This document explains the core concepts, available actions, and how to work with results.
- ▌ Building With Extended Thinking · tools-only bundleExtended thinking gives Claude enhanced reasoning capabilities for complex tasks, while providing varying levels of transparency into its step-by-step thought process before it delivers its final answer.
- ▌ Tool Use With Claude · tools-only bundleClaude is capable of interacting with tools and functions, allowing you to extend Claude's capabilities to perform a wider variety of tasks.
- ▌ Thinking Reasoning Content · tools-only bundleLiteLLM will standardize the reasoningcontent in the response and thinkingblocks in the assistant message.
- ▌ Run Memorize Py Usage Documentation · tools-only bundlerun_memorize.py is a group chat memory storage script that reads JSON files conforming to the GroupChatFormat format and stores them item by item into the memory system via HTTP API.
- ▌ Fn 15 96t 6 Update Docs Readme Flowctl Md Changelog · tools-only bundleAdded plan-sync documentation to README (Features section), flowctl.md (config table), and CHANGELOG (0.11.4 entry).
- ▌ Fn 17 Wti 1 Add Review Backend To Flowctl Default Config · tools-only bundleAdd review.backend to the default config structure in flowctl.py.
- ▌ Group Chat Conversations Guide · tools-only bundleThis guide covers how to leverage group-based memory management for various use cases.
- ▌ Headless Obsidian CLI Setup · tools-only bundleSnap confinement creates separate filesystem namespaces. The CLI process and the running Obsidian instance end up with different SingletonLock/SingletonSocket paths, so CLI can't connect via IPC.
- ▌ Validation Rules · tools-only bundleChecks performed by ./scripts/validate-research.py and severity mapping for the /research-curator --validate mode.
- ▌ Validation Rules 2 · tools-only bundleChecks performed by ./scripts/validate_research.py and severity mapping for the /research-curator --validate mode.
- ▌ Token Verification · tools-only bundleToken verification enables your FastMCP server to validate bearer tokens issued by external systems without participating in user authentication flows.
- ▌ Programmatic Connector Setup 2 · tools-only bundleSet up connectors entirely from the terminal or via HTTP APIs—no UI required.
- ▌ Sdk Options · tools-only bundleThe Claude Code SDK has been renamed to the Claude Agent SDK. If you're migrating from the old SDK, see the Migration Guide.
- ▌ Mode Selection Guide · tools-only bundleHow to recommend the right reasoning mode when the user selects "You choose" or when auto-recommending.
- ▌ Monitoring And Alerts · tools-only bundleCurrent guidance for monitoring LangSmith projects and configuring alerts.
- ▌ Auto Selection Rules · tools-only bundleWhen a dimension is omitted, select based on content signals.
- ▌ Arl Agent Instructions · tools-only bundleThe expert panel process is structured around these research questions. All discussion, mapping, and synthesis should advance answers to them.
- ▌ Analysis Patterns For Langsmith Traces · tools-only bundleProven patterns for analyzing traces at scale, finding insights, and debugging issues.
- ▌ Phase 8r Detailed Risk Analysis Reports Optional · tools-only bundleWithin the same priority level, order by CVSS score (highest first).
- ▌ Dialectic Synthesis · tools-only bundleHegelian dialectic with steel manning for constructing the strongest possible counter-argument and driving toward synthesis.
- ▌ API Key 2 · tools-only bundlerootapikey 是静态配置(部署时手动写入 ov.conf),但 account key 和 user key 是运行时通过 Admin API 动态增删的,不能放 ov.conf。动态存储有两个选择:
- ▌ Benefits Of Using Subagents · tools-only bundleSubagents in the Claude Agent SDK are specialized AIs that are orchestrated by the main agent. Use subagents for context management and parallelization.
- ▌ State Debugging Techniques · tools-only bundleDebugging state management issues in LangGraph applications requires understanding how state flows through the graph, how reducers merge updates, and how to inspect state at each step.
- ▌ Benchmark Analysis Guide · tools-only bundleGuide for analyzing agent benchmark runs (like Terminal Bench/Harbor) using LangSmith traces.
- ▌ Skills Remediation Complete · tools-only bundle✅ Zero Critical Risk Skills - All 470 eliminated ✅ 470 Human Approval Bottlenecks Removed - No more per-skill approvals ✅ 100% Automated Execution Ready - All 808 skills can run automatically ✅ 521 Skills Enhanced…
- ▌ False Positive Prevention Guide · tools-only bundleIt is critical this prompt is fully processed in a careful, systematic way. It is used during the false positive section of the review, where avoiding false positives is of utmost importance.
- ▌ False Positive Prevention Guide 2 · tools-only bundleIt is critical this prompt is fully processed in a careful, systematic way. It is used during the false positive section of the review, where avoiding false positives is of utmost importance.
- ▌ Openai Typescript And Javascript API Library · tools-only bundleThis library provides convenient access to the OpenAI REST API from TypeScript or JavaScript.
- ▌ Skene Rebranding Skills Directory CLI · tools-only bundleRebranded Skills Directory CLI from "SKILL-LOOM" to full Skene branding, using design tokens and visual identity from the Skene ASCII Design System.
- ▌ Development Standards · tools-only bundleThis document introduces various standards and best practices in the project development process to help the team maintain code quality and collaboration efficiency.
- ▌ Sdk Permissions · tools-only bundleThe Claude Agent SDK provides powerful permission controls that allow you to manage how Claude uses tools in your application.
- ▌ Database Migration Runbook · tools-only bundleThis is a runbook for creating and running database migrations for the LiteLLM proxy. For use for litellm engineers only.
- ▌ Group Chat Format Specification · tools-only bundleThis is an open-source group chat data format specification for standardizing the storage and exchange of group chat conversation data.
- ▌ Password Management And Recovery · tools-only bundleThis guide covers all supported password reset and account recovery paths for MCP Gateway administrators.
- ▌ Human Escalation With Interrupts · tools-only bundleHuman-in-the-loop (HITL) error escalation allows LangGraph agents to pause execution and request human intervention when they encounter situations they cannot handle autonomously.
- ▌ Gemini API Coding Guidelines Python · tools-only bundleYou are a Gemini API coding expert. Help me with writing code using the Gemini API calling the official libraries and SDKs.
- ▌ LLM Provider Configuration · tools-only bundleGuide to configuring API keys and credentials for various LLM providers.
- ▌ Build Your First Skill · tools-only bundleThis tutorial walks you through creating a simple skill from scratch. We'll build a competitormentiontracker skill that monitors mentions of competitors in customer conversations.
- ▌ Creating Custom Tools · tools-only bundleCustom tools allow you to extend Claude Code's capabilities with your own functionality through in-process MCP servers, enabling Claude to interact with external services, APIs, or perform specialized operations.
- ▌ Save Session Learnings · tools-only bundleCapture and persist significant discoveries from this session into project documentation so knowledge survives across sessions and agents.
- ▌ Multi Agent Pattern Comparison · tools-only bundleQuick reference for choosing the right pattern for your use case.
- ▌ Agentic Retrieval Guide · tools-only bundleAgentic retrieval is an LLM-guided multi-round retrieval method that significantly improves retrieval quality for complex queries through intelligent judgment and query optimization.
- ▌ Sdk Cost Tracking · tools-only bundleThe Claude Agent SDK provides detailed token usage information for each interaction with Claude.
- ▌ Supervisor Subagent Pattern · tools-only bundleThe supervisor-subagent pattern uses a central coordinator (supervisor) to analyze tasks and delegate work to specialized subagents. This is a common multi-agent pattern for complex workflows.
- ▌ Sla Management Guide · tools-only bundleAn SLI is the quantitative measurement of a specific aspect of service quality. SLIs are the raw data that feed everything above them. They must be precisely defined, automatically collected, and unambiguous.
- ▌ Openakita Desktop Terminal User Guide And Feature Overview · tools-only bundleThe Chat page is the core feature of the desktop terminal, providing a full AI conversation experience using the same Agent pipeline (Persona, memory, tools, skills, context compression) as IM/CLI channels.
- ▌ Message Types · tools-only bundleThe primary function for interacting with Claude Code. Creates an async generator that streams messages as they arrive.
- ▌ Gemini API Coding Guidelines Javascript Typescript · tools-only bundleYou are a Gemini API coding expert. Help me with writing code using the Gemini API calling the official libraries and SDKs.
- ▌ Ascii Design System Python Port Complete · tools-only bundleSuccessfully ported the Skene ASCII Design System from TypeScript/Node.js to Python/Rich for use in skill-loom-cli.py. The CLI now uses consistent Skene branding with design tokens, symbols, and adaptive rendering.
- ▌ Claude Code Managing Anthropic Beta Headers · tools-only bundleWhen using Claude Code with LiteLLM and non-Anthropic providers (Bedrock, Azure AI, Vertex AI), you need to ensure that only supported beta headers are sent to each provider.
- ▌ Diagnose Azure Resources · tools-only bundleRun the 6-phase diagnostic workflow to assess resource health, identify issues, and generate a remediation report with actionable recommendations.
- ▌ Prompt Injection Patterns · tools-only bundlePatterns to detect when scanning agent skills for prompt injection attacks.
- ▌ Incident Response Framework Reference · tools-only bundleProduction-grade incident management knowledge base synthesizing PagerDuty, Google SRE, and Atlassian methodologies into a unified, opinionated framework.
- ▌ Developer Success · tools-only bundleOur value and principle is developer success. We truly care about helping developers achieve their goals — not just shipping features, but ensuring every developer who uses Hive can build, debug, deploy, and iterate on…
- ▌ Gsap Animation Skill Architecture Design · tools-only bundleThe gsap-animation skill provides a curated catalog of GSAP-powered motion graphics patterns, integrated with Remotion for deterministic video rendering.
- ▌ Deduplication And Intelligent Chaining Complete Guide · tools-only bundleBuilt a comprehensive system for semantic deduplication, intelligent skill chaining, and workflow synthesis. The system uses machine learning for similarity detection and graph analysis for workflow generation.
- ▌ Adr 0040 Flexible Admin UI Section Visibility · tools-only bundleMCP Gateway's Admin UI is a full-featured dashboard with many sections (overview, servers, gateways, tools, prompts, resources, roots, mcp-registry, metrics, plugins, export-import, logs, version-info, maintenance…
- ▌ State Management Patterns For Multi Agent Systems · tools-only bundleState schemas must support the coordination requirements of each multi-agent pattern. This reference covers state design for supervisor, router, orchestrator-worker, and handoff patterns.
- ▌ Gsap Plus Remotion Integration Research · tools-only bundleGSAP integrates with Remotion through a seek-based synchronization pattern: GSAP timelines are created in paused state, then on every frame Remotion's useCurrentFrame() value is converted to seconds and used to seek()…
- ▌ Streaming Input Mode Recommended · tools-only bundleThis guide explains the differences, benefits, and use cases for each mode to help you choose the right approach for your application.
- ▌ Understanding System Prompts · tools-only bundleSystem prompts define Claude's behavior, capabilities, and response style. The Claude Agent SDK provides three ways to customize system prompts: using output styles (persistent, file-based configurations), appending to…
- ▌ Shared Theme Variable Contract For Tunacode And Nextstep · tools-only bundleEstablished a single variable schema for both Textual themes so base TCSS can stay theme-agnostic and avoid missing-variable runtime paths.
- ▌ Statusbar Content Row Regression Fix · tools-only bundleThe status bar gained a top bevel border during the UI revamp, but its height remained 1. In Textual, border rows consume layout space, so a one-row widget with a top border leaves zero content rows.
- ▌ Security Auditor 5 · tools-only bundleDeep security analysis AFTER code is written. Complements code-reviewer (which catches surface-level security at Critical severity) with deeper OWASP-focused analysis.
- ▌ Diagnose Azure Resources 2 · tools-only bundleRun the 6-phase diagnostic workflow to assess resource health, identify issues, and generate a remediation report with actionable recommendations.