claude-engineering-best-practices
General-purpose guidance for Claude Code (terminal) and Claude Dev (platform). Covers stable principles (progressive disclosure, hooks, security) and volatile details with lookup workflows.
ingesting-git
Transforms repositories into structured plain-text digests optimized for LLM consumption. Use when analyzing GitHub repositories, digesting codebases, or ingesting git repos for AI analysis.
conducting-research
Automatically determines the optimal research tool based on query type and available information. Use when answering technical questions requiring external verification, documentation lookup, or library/repo research. Do not use for statistical calculations, hypothesis testing, or data analysis → see analyzing-data skill.
architecting-slides
Expertise in narrative structure, academic storytelling, and LaTeX Beamer presentations. Use when designing the flow of research talks and building technical slide decks with a focus on scientific rigor and narrative clarity.
analyzing-data
Statistical analysis toolkit for hypothesis testing, regression, correlation, Bayesian statistics, power analysis, and APA reporting. USE when conducting academic research, analyzing experimental data, testing hypotheses with t-tests or ANOVA, performing regression analyses, calculating effect sizes, checking statistical assumptions, or generating publication-ready statistical reports. Do not use for literature reviews, tool selection, or methodology design → see conducting-research skill.
managing-npm
Manages npm, pnpm, and bun dependencies following strict protocols. Use when installing, updating, or auditing packages. Do not use for TypeScript configuration or build tooling.
configuring-typescript
Configures modern TypeScript (4.9+ through 5.x) for maximum type safety with sustainable compile times. Use when designing type-safe configs/maps/APIs, enforcing strictness flags, improving TS build performance (incremental, project references), or setting up separate TS/ESLint configs for tests.
processing-media
Handles video editing, ffmpeg processing, and visual analysis. Use when transforming raw footage into polished output or analyzing visual content.
generating-ui
Creates beautiful visual art in .png and .pdf documents using design philosophy. Use when creating posters, artwork, designs, and static visual pieces with original designs. Never copy existing artists' work to avoid copyright violations.
synchronizing-data
Implements offline-first synchronization with encrypted local storage and intelligent conflict resolution for mobile AI applications. Use when building offline-capable mobile apps, implementing sync with privacy requirements, or managing encrypted local data persistence. Do not use for cloud databases, real-time websocket sync, or server-side data management.
experimenting-edge
Optimizes AI models for edge deployment through quantization, lazy loading, and memory management. Use when deploying models to resource-constrained environments, mobile devices, or edge computing scenarios. Do not use for cloud deployment, model training, or data preprocessing.
repairing-state
Performs forensic investigation and applies permanent fixes. MUST USE when diagnosing component failures, hallucinations, or instruction drift. Do not use for routine tasks, standard debugging, or preventive maintenance.
managing-hooks
Comprehensive guide for creating, configuring, and using Claude Code hooks. MUST Use when creating hooks, implementing PreToolUse/PostToolUse/Stop hooks, or configuring event-driven automation. Do not use for general automation, workflow management, or task execution.
integrating-mcp
Provides comprehensive MCP integration guidance for Claude Code plugins. MUST Use when integrating databases via MCP, setting up MCP servers, or configuring connections. Do not use for API integration, web services, or general database access.
checking-types
Runs configured type checkers (pyrefly, mypy) on files after editing. MUST USE when validating Python type safety (Internal-only passive hook).
auditing-security
Scans for secrets and performs comprehensive security audits. MUST Use when verifying security of code changes or auditing file safety.
auditing-plugins
Comprehensive plugin auditing for compliance with marketplace best practices. MUST Use when validating, refactoring, or improving plugin quality. Do not use for creating new plugins, scaffolding components, or development tasks.
adhering-standards
Provides System Authority on 2026 Universal Agentic Runtime standards for all plugin components. MUST Use when auditing or managing plugin components (Skills, Commands, Agents). Do not use for creating new components, development tasks, or routine maintenance.
operating-claude
Operational manual for driving the Claude runtime. Use when needing to optimize context usage, troubleshoot performance, or understand runtime mechanics. Do not use for architectural definitions or building plugins.
generating-prompts
Creates optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce structured outputs for other prompts to consume, or when running multi-stage workflows. Do not use for simple prompts, single-step tasks, or basic conversational AI.
facilitating-reasoning
Clarifies goals and applies structured thinking frameworks (Pareto, Inversion, First-Principles) to complex problems. Use when exploring constraints, analyzing decisions, or applying structured reasoning to uncover hidden assumptions.
applying-reasoning
Applies structured mental models to solve complex problems. Use when solving architectural decisions, root cause analysis, or strategic planning.
architecting-prompts
Applies 2026 Complexity-Based Guidance standards with Attention Management, Sycophancy Prevention, and XML/Markdown decision matrix. Provides theory, patterns, and quality evaluation criteria for AI prompt design. Use when designing, optimizing, or auditing AI prompts, system instructions, or multi-stage chains. Do not use for generating prompt files, basic conversational AI, or single-step interactions.
managing-python
Manages Python environments, dependencies, and tools using uv and ruff. PROACTIVELY Use when setting up Python projects, adding dependencies, managing virtual environments, or enforcing code quality standards. MUST Use `uv` for all operations.
managing-plans
Orchestrates project plan state management and execution. Manages ROADMAP.md state tracking, task dispatch, phase transitions, and handoff protocols. PROACTIVELY Use when managing project plans, executing phases, or coordinating task workflows. MUST Use for all plan-related operations (creation, modification, execution). Do not use for architecture design, system analysis, or creating new projects without a plan → see designing-architecture skill.
generating-tests
Follows project conventions, extracts examples from documentation, converts them to tests, and ensures documentation accuracy through automated testing. PROACTIVELY Use when generating comprehensive Vitest tests for code examples in JavaScript concept documentation pages. Do not use for end-to-end browser automation, user flow testing, or browser-server integration → see testing-e2e skill.
designing-architecture
Applies system architecture and design frameworks for software systems. Provides discovery protocols, system design workflows, architecture decision records (ADRs), and quality evaluation criteria. PROACTIVELY Use when designing new systems, analyzing existing architecture, or making architectural decisions. Do not use for project plan state management, task execution, or phase coordination → see managing-plans skill.
applying-code-standards
Provides Universal Standard for TDD, Security, and Code Quality. PROACTIVELY Use when writing code, debugging errors, or reviewing PRs. Modes: debug, review, refactor, implement.
adhering-execution-standard
Defines behavioral standards for autonomous agents and enforces Uninterrupted Flow, Self-Verification, Auth-Gates, and Handoff protocols. PROACTIVELY Use when defining behavioral standards for autonomous agents or enforcing protocols. Internal-only reference for agent behavior.
testing-e2e
Orchestrates end-to-end testing workflows coordinating browser automation with server verification. Use when validating complete user flows, testing multi-step scenarios, or verifying browser-server integration. Do not use for unit testing, API testing, isolated component testing, or documentation code examples → see generating-tests skill.
crawling-content
High-speed read-only web extraction. Use when fetching documentation, blogs, and static pages. Do not use for apps requiring login or interaction.
browsing-web
Interactive browser automation using agent-browser. Use when navigating dynamic sites, authentication, clicking, typing, and complex state navigation. Do NOT use for simple read-only text extraction.
orchestrating-agents
Implements Orchestrator, Swarm, and Hierarchical patterns for preventing context saturation. Use when designing multi-agent systems for context isolation and parallel execution.
optimizing-context
Provides unified interface for all context engineering patterns. Use when optimizing AI agent context: compression, degradation detection, KV-cache optimization, or session management.
architecting-memory
Implements progression from Vector RAG → GraphRAG → Temporal Knowledge Graphs. Use when designing persistent memory architectures for AI agent systems.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
rails-audit-thoughtbot
Perform comprehensive code audits of Ruby on Rails applications based on thoughtbot best practices. Use this skill when the user requests a code audit, code review, quality assessment, or analysis of a Rails application. The skill analyzes the entire codebase focusing on testing practices (RSpec), security vulnerabilities, code design (skinny controllers, domain models, PORO with ActiveModel), Rails conventions, database optimization, and Ruby best practices. Outputs a detailed markdown audit report grouped by category (Testing, Security, Models, Controllers, Code Design, Views) with severity levels (Critical, High, Medium, Low) within each category.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Page 1656 of 1688 · 84368 results
