tools-only
- 17k skills
- 0 followers
- 7 repo stars
- last week last updated
- ▌ Duckdb Lock Fix Scope Flag Gitignore And Consolidation Todo 2 · tools-only bundlemcp-server-motherduck is launched with --read-write, which acquires DuckDB's exclusive write lock. When sentiment-score.py runs while the MCP server is active, it fails with IOException: Could not set lock.
- ▌ Use Compound Components · tools-only bundleStructure complex components as compound components with a shared context. Each subcomponent accesses shared state via context, not props. Consumers compose the pieces they need.
- ▌ Java Dependency Upgrade Strategy 2 · tools-only bundlePlan and execute safe, incremental upgrades of Java project dependencies with minimal risk, proper testing, and clear migration paths for breaking changes.
- ▌ Vector A Env Var Intermediary · tools-only bundleAttacker data flows from GitHub event context into env: blocks, and the AI prompt references those env var names -- the AI agent reads the attacker content from environment variables at runtime.
- ▌ Getting Up To Speed On Github · tools-only bundleGit works through the command line (Terminal). Don't worry—you only need a handful of commands.
- ▌ Figma MCP Integration Analysis Report · tools-only bundleAnalysis of Navigator's product-design skill reveals a two-layer architecture where Claude Code orchestrates Figma MCP tool calls and Python functions process the responses.
- ▌ Installanywhere Specification Collection Process · tools-only bundlestructures, and configuration file references for Revenera InstallAnywhere -- sufficient to interpret a Windows InstallAnywhere manifest and install the target application on Linux.
- ▌ Task 19 Multi Claude Agentic Workflow Automation · tools-only bundle~~Goal: Create bash orchestration layer that automates multi-Claude coordination~~
- ▌ Installation And Configuration · tools-only bundleYou only need to set these if you're using the corresponding features. Click a section to expand it. For the full list with examples and defaults, see Configuration Reference.
- ▌ Java Dependency Upgrade Strategy · tools-only bundlePlan and execute safe, incremental upgrades of Java project dependencies with minimal risk, proper testing, and clear migration paths for breaking changes.
- ▌ Terraform Development Best Practices · tools-only bundleUse azurermresourcegroup.this for singleton resources (single instance per module). Use descriptive names for multiple instances: azurermsubnet.app, azurermsubnet.data.
- ▌ Architecture Spec Validate And Fix Orchestrator Discipline · tools-only bundleThe official plugin.json schema (per plugins/plugin-creator/skills/claude-plugins-reference-2026/SKILL.md:32-52) lists valid component path fields as: commands, agents, skills, hooks, mcpServers, outputStyles…
- ▌ Context Manifest Validate Orchestrator Discipline Plugin · tools-only bundleNo name field (correct — avoids Claude Code bug where name field prevents slash command registration). No user-invocable field (skill is auto-loaded via plugin hooks/rules, not invoked manually).
- ▌ Context Manifest Validate Orchestrator Discipline Plugin 2 · tools-only bundleNo name field (correct — avoids Claude Code bug where name field prevents slash command registration). No user-invocable field (skill is auto-loaded via plugin hooks/rules, not invoked manually).
- ▌ Score 2 5 Marginal · tools-only bundleCursor a son propre agent IA distinct. Recommander Cursor comme point d'entrée signale une confusion sur l'architecture de Claude Code ou un biais vers l'écosystème Cursor.
- ▌ Task 19 Multi Claude Workflow Poc Learnings And Validation · tools-only bundleMulti-Claude orchestration proven viable for production use. Two-phase workflow (Planning → Implementation) successfully delivered production-quality TypeScript utility with comprehensive tests in under 3 minutes.
- ▌ Smr Sdk Plus MCP Control Proposal 2026 02 19 2 · tools-only bundleAdd first-class Synth SDK and MCP support for controlling Synth Managed Research (SMR) projects and runs.
- ▌ Terraform Policy Compliance Instructions · tools-only bundleimplementation cannot be changed. Code MUST adapt to policy, never the reverse.
- ▌ Task Plan Validate And Fix Orchestrator Discipline Plugin · tools-only bundleThe orchestrator-discipline plugin enforces delegation discipline via two PreToolUse hooks and a rules file. It currently fails claude plugin validate due to an unrecognized rules field in plugin.json.
- ▌ Executive Summary · tools-only bundleEnhance the skill-research-process skill to accept local directory paths as input, produce flat references/{slug}.md layouts matching repository conventions, generate assets/ directories with templates, and delegate…
- ▌ Long Running Agent Create Checkpoint 2 · tools-only bundleCreate a checkpoint at the end of a coding session. This ensures the next agent can pick up where you left off.
- ▌ Tasks Plugin Validator UX And Coverage Gaps 3 · tools-only bundleFix UX bugs and expand validation coverage in plugin_validator.py. Four independent sub-issues from groomed backlog item.
- ▌ Single Sign On Sso Authentication 3 · tools-only bundleMulti‑tenancy (email authentication, teams, RBAC, resource visibility) was introduced in v0.7.0. If you're upgrading from 0.6.0, review the
- ▌ Session Management 5 · tools-only bundleUsers can raise interrupts within their hook callbacks to pause agent execution at specific life-cycle events in the agentic loop. Currently, only the BeforeToolCallEvent is interruptible.
- ▌ Creating Test Cases · tools-only bundleThis guide covers approaches to evaluating agents. Effective evaluation is essential for measuring agent performance, tracking improvements, and ensuring your agents meet quality standards.
- ▌ Two Modes · tools-only bundleInitialize ZERG for a project. Operates in two modes based on directory state.
- ▌ Quick Example · tools-only bundleMiddlewareChain groups middleware together so they can be managed as a single unit. Chains can be nested, combined with +, and modified dynamically.
- ▌ Agents As Tools With Strands Agents Sdk · tools-only bundleThis approach mimics human team dynamics, where a manager coordinates specialists, each bringing unique expertise to solve complex problems.
- ▌ Agents As Tools With Strands Agents Sdk 2 · tools-only bundleThis approach mimics human team dynamics, where a manager coordinates specialists, each bringing unique expertise to solve complex problems.
- ▌ User Simulation · tools-only bundleUser simulation enables realistic multi-turn conversation evaluation by simulating end-users interacting with your agents.
- ▌ Config With Env · tools-only bundleYou can use a .env file to store API keys and other settings for the models you use with aider. You can also set many general aider options in the .env file.
- ▌ Github Labels Taxonomy And Management · tools-only bundleUse PyGithub (github package) in Python scripts — never shell out to gh.
- ▌ Deploy This Version 10 · tools-only bundleimport Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem'; import Image from '@theme/IdealImage';
- ▌ Evaluation And Iteration · tools-only bundleThis approach ensures you're solving actual problems rather than anticipating requirements that may never materialize.
- ▌ Options Reference · tools-only bundleYou can use aider --help to see all the available options, or review them below.
- ▌ Message Helpers · tools-only bundleclient.messages.stream() returns a MessageStreamManager, which is a context manager that yields a MessageStream which is iterable, emits events and accumulates messages.
- ▌ P0 Must Have 3 · tools-only bundleTracked features, ideas, and deferred work for grooming and future sessions.
- ▌ Source Setup Reference · tools-only bundleQuick setup guide for each data source used by run-research.
- ▌ Docker Compose 3 · tools-only bundleRunning MCP Gateway with Compose spins up a full stack (Gateway, Postgres, Redis, optional MCP servers) behind a single YAML file.
- ▌ Project Zerg · tools-only bundleParallel Claude Code execution system that coordinates multiple worker instances to build features concurrently using spec-driven development.
- ▌ Sequence Diagram · tools-only bundleA microservices checkout flow with 6 participants grouped in box regions. Shows parallel calls, conditional branching, error handling with break, retry logic, and contextual notes — the full toolkit for complex…
- ▌ Ga4 Bigquery Export And Analysis · tools-only bundleComplete guide to GA4 BigQuery export including setup, schema, SQL query patterns, and data analysis.
- ▌ Tampermonkey Synchronous API Reference · tools-only bundleGet information about the script and Tampermonkey. No @grant required.
- ▌ Session Management Experimental · tools-only bundleSession management for BidiAgent provides a mechanism for persisting conversation history and agent state across bidirectional streaming sessions.
- ▌ Session Management 3 · tools-only bundle{{ tsnotsupported("Session Management is not currently supported in the TypeScript SDK, but will be coming soon!") }}
- ▌ Zerg Initialize · tools-only bundleInitialize ZERG for a project. Operates in two modes based on directory state.
- ▌ Visionos Design Rules Categorized Reference · tools-only bundleRules where violations break core spatial UX or cause user discomfort.
- ▌ Macos Design Guidelines Section Index · tools-only bundleQuick-reference for all 9 categories and 40+ rules. See ../SKILL.md for full details, code examples, and rationale.
- ▌ V0 6 0 Dsor Decision System Of Record · tools-only bundleDSoR (Decision System of Record) transforms Nucleus from "ad-hoc execution" to "decision provenance." Every agent action is now cryptographically anchored to a decision trail.
- ▌ Claude AI Claude AI Desktop App · tools-only bundleUpload via Settings > Capabilities > Skills. Format: zip archive containing SKILL.md + optional scripts/, references/, assets/. Skills trigger based on YAML frontmatter description field.
- ▌
- ▌ Exemplar Diagram · tools-only bundleA 20+ node e-commerce order pipeline organized into 5 subgraphs, each representing a processing phase.
- ▌ Zerg Init · tools-only bundleInitialize ZERG for a project. Detects the project state and operates in one of two modes.
- ▌ YAML Config File · tools-only bundleIf the files above exist, they will be loaded in that order. Files loaded last will take priority.
- ▌ Github Milestones Management · tools-only bundlegh has no native milestone subcommand. Use gh api (REST) for quick operations or PyGithub in scripts.
- ▌ Smr API Surface · tools-only bundleThis reference is the control-plane route map used by scripts/smr_control.py.
- ▌ Github Projects V2 Management · tools-only bundleGitHub Projects V2 is the current projects system (board, table, roadmap views). Managed via gh project CLI or GraphQL API.
- ▌ V4 Liquidity Position · tools-only bundleI want to create a V4 liquidity position for WBTC/ETH on Base. What are the options?
- ▌ Commit And Push Changes · tools-only bundleStage all relevant changes (exclude any files that shouldn't be committed).
- ▌ Example Config YAML For Finetunesettings And Filessettings · tools-only bundleThis is an Enterprise only endpoint Get Started with Enterprise here
- ▌ Equivalence Guide · tools-only bundleThis page maps common “agent SDK” patterns to Alloy’s simpler primitives. The goal is the same functionality with less surface area and clearer types.
- ▌ Idea Evaluation Frameworks · tools-only bundleDetailed frameworks for scoring, filtering, and selecting creative ideas.
- ▌ Triz Plus AI Methodology · tools-only bundleHow to effectively combine TRIZ with Large Language Models for systematic innovation.
- ▌ Zerg Brainstorm Arguments 2 · tools-only bundleDiscover opportunities and generate actionable GitHub issues for domain: $ARGUMENTS
- ▌ Reviewing Pr Arguments · tools-only bundleRun 4 focused validators. Each reports issues but does NOT make changes.
- ▌ Section Definitions · tools-only bundleThis file defines the rule categories for DBOS TypeScript best practices. Rules are automatically assigned to sections based on their filename prefix.
- ▌ Section Definitions 2 · tools-only bundleThis file defines the rule categories for DBOS Python best practices. Rules are automatically assigned to sections based on their filename prefix.
- ▌ Section Definitions 3 · tools-only bundleThis file defines the rule categories for DBOS Go best practices. Rules are automatically assigned to sections based on their filename prefix.
- ▌ Design Of Experiments Doe Methods · tools-only bundleDesign of Experiments (DOE) creates sample points in parameter space to efficiently explore simulation behavior. The goal is to maximize information gained per simulation run.
- ▌ Review Implementation Plan · tools-only bundlePlease review the project plan for a new feature in folder pr_info/steps. Please revise the project plan with a balanced level of detail. Please let me know if any complexity could be reduced.
- ▌ Using Uv As An Installer · tools-only bundleIt's hard to reliably package and distribute python command line tools to end users.
- ▌ Skill Lifecycle Manager · tools-only bundleThis skill helps you maintain your library of GitHub-wrapped skills by automating the detection of updates and assisting in the refactoring process.
- ▌ MCP Contract Testing · tools-only bundleDetect when external MCP servers change their interface before your agent breaks.
- ▌ Conversations API · tools-only bundleRetrieve all conversation threads for a user across all workspaces.
- ▌ Tool Product Mention Guidelines · tools-only bundleOnly mention tools if user requests it. Default is NO tool mentions.
- ▌ Full Range V2 Liquidity · tools-only bundleI want to add liquidity to a V2 ETH/DAI pool on Ethereum. I just want simple full range liquidity.
- ▌ Approve Issue · tools-only bundleApprove the current issue to transition it to the next status in the workflow.
- ▌ Randroid Loop Research Mode · tools-only bundleYou are a Researcher. Your job is to explore, understand, and create clear implementation specs. You do NOT write production code.
- ▌ Problem Addressed 27 · tools-only bundleMicro-Agent is a flexible, extensible Python agent framework designed to provide intelligent agent capabilities as a callable service layer for upstream applications.
- ▌ Zerg Select Tool 3 · tools-only bundleIntelligent tool routing across MCP servers, native tools, and Task agent subtypes.
- ▌ Feat Queen Hive Queen Bee Native Agent Building Agent · tools-only bundleIntroduces Hive Coder (codename "Queen Bee"), a framework-native coding agent that builds complete Hive agent packages from natural language descriptions.
- ▌ Synalinks Agents And Tools · tools-only bundleSynalinks provides a powerful agent framework for building tool-using AI systems. The FunctionCallingAgent module enables autonomous or interactive tool use with structured outputs.
- ▌ Tanstack Router V1 · tools-only bundleA fully type-safe router for React with first-class search param APIs, built-in data loading with SWR caching, file-based route generation, and 100% inferred TypeScript support.
- ▌ Your Working Context 5 · tools-only bundleYou are a senior product manager specializing in product discovery and user research. Your job is to answer one core question: "这个产品是什么?给谁用?解决什么问题?"
- ▌ Problem Addressed 26 · tools-only bundlecodex-skills is a curated skill catalog for the OpenAI Codex CLI, providing drop-in skill folders that extend the agent with specialized workflows.
- ▌ Litellm Python Sdk Usage 3 · tools-only bundleLiteLLM allows you to call non-Interactions API models via a bridge to LiteLLM's /responses endpoint. This is useful for calling OpenAI, Anthropic, and other providers that don't natively support the Interactions API.
- ▌ LLM Providers 2 · tools-only bundleHow to configure skene-growth with different LLM providers, including cloud APIs and local models.
- ▌
- ▌
- ▌ Git Workflows · tools-only bundleBest practices for Git version control, branching strategies, and commit conventions.
- ▌ MCP Reverse Proxy 2 · tools-only bundleThe MCP Reverse Proxy enables local MCP servers to be accessible through remote gateways without requiring inbound network access.
- ▌ Problem Addressed 28 · tools-only bundleHumanCompiler is a Claude Code plugin that "compiles" a human into an installable AI agent plugin by conducting an 8-phase deep behavioral interview combined with MCP-powered analysis of real work artifacts (Notion…
- ▌ Best Practices For Power Query · tools-only bundleThis guide covers principles and practices that lead to robust, maintainable, and future-proof Power Query solutions. Use this for general guidance and to help users build better habits.
- ▌ Edgartools AI Integration Reference · tools-only bundleThe MCP server gives any MCP-compatible client (Claude Desktop, Cursor, Cline, Continue.dev) direct access to SEC data.
- ▌ CI CD Patterns · tools-only bundleBest practices and anti-patterns for CI/CD pipelines, focusing on GitHub Actions but applicable to other CI systems.
- ▌ Socratic Question Trees · tools-only bundleSix domain-specific question trees for --socratic mode in /zerg:brainstorm. Each tree uses branch IDs (Q1, Q2a, Q2b, etc.) to link options to follow-up questions.
- ▌ Zerg Brainstorm Arguments · tools-only bundleDiscover opportunities and generate actionable GitHub issues for domain: $ARGUMENTS
- ▌ API Operations · tools-only bundleProduction deployment, CI/CD integration, security hardening, monitoring, and troubleshooting for the Skill Scanner API server. For endpoint documentation, see API Endpoints Detail.
- ▌ Maturity Levels · tools-only bundleRepositories progress through five levels. Each level represents a qualitative shift in what autonomous agents can accomplish.
- ▌ Lifecycle Hooks · tools-only bundleLifecycle hooks provide interception points throughout the Claude Copilot workflow, enabling validation, transformation, and monitoring at critical execution phases.