task-breakdown
Break down implementation plans into organized task lists using Epic → Story → Task hierarchy with Enabler support, P1/P2/P3 prioritization, and TaskCreate integration
tech-stack
Specifies the technologies to be used for backend development, including Node.js, Express.js, MongoDB, and Mongoose.
technical-accuracy-and-usability-rules
Ensures the documentation is technically accurate and highly usable for the target audience.
telegram-bot-api-rules
Rules for files related to the Telegram Bot API integration, emphasizing API-specific best practices.
terminal-commands-rule
Specifies expertise in suggesting wrangler commands within the terminal environment.
thoughtful-and-accurate-responses
Instructs the AI to provide accurate, factual, and thoughtful answers, emphasizing reasoning and accuracy in all contexts.
todo-app-general-rules
General rules for the entire Todo web application project. Encompasses specifications and guidelines applicable across all files.
toon-format
TOON Format Rules for Claude Code
trpc-api-rule
Enforces conventions and practices for tRPC API endpoints and procedures.
truthfulness-and-clarity-for-ai
Specifies guidelines for the AI assistant to provide accurate, thoughtful answers, admit when it doesn't know something, and be concise while ensuring clarity. This rule promotes trustworthy and helpf
type-hinting-rule
Mandates strict type hinting using the typing module for all Python functions, methods, and class members.
unit-testing-requirement
Enforces the implementation of unit tests to guarantee code reliability and maintainability, especially within the 'tests' directory.
use-case-example
Use Case Example for Cypress Defect Tracking Prompt
using-git-worktrees
Create isolated development workspaces with safety verification. Use when needing parallel development branches.
vercel-ai-sdk-best-practices
Best practices for using the Vercel AI SDK in Next.js 15 applications with React Server Components and streaming capabilities.
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
vercel-kv-database-rules
Defines how to interact with Vercel's KV database for storing and retrieving session and application data.
verify-information-rule
This rule ensures that the AI always verifies information before presenting it, avoiding assumptions and speculation.
version-control-rule
Applies to git related files, specifies to always use git for version control.
virtual-environment-usage
Mandates the use of virtual environments for isolating project dependencies and ensuring reproducibility.
vue-expert
Vue.js ecosystem expert including Vue 3, Composition API, Nuxt, and Pinia
vueuse-library-rule
Encourages leveraging VueUse functions throughout the project to enhance reactivity and performance.
windows-compatibility
Guidelines for working on Windows with Git Bash. Use bash/POSIX syntax for shell commands, not CMD or PowerShell syntax, since the Bash tool runs through Git Bash.
writing-plans
Create bite-sized task lists with complete code. Use when planning multi-step implementations.
integration
Integration skills
testing-expert
Deprecated alias for tdd skill
writing
Deprecated alias for writing-skills skill
accessibility
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
advanced-elicitation
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
adversarial-debate
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
adversarial-review
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
agent-creator
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
agent-evaluation
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
agent-tool-design
The Agent Tool Contract — 5 principles for designing tools agents call reliably: predictable signature, rich errors, token-efficient output, idempotency, graceful degradation. Includes anti-pattern table with 8 common mistakes.
agent-updater
Research-backed workflow to refresh existing agent prompts/frontmatter with diff-based risk scoring, TDD gates, and ecosystem validation.
ai-ml-expert
AI and ML expert covering PyTorch, TensorFlow, Hugging Face, scikit-learn, LLM integration, RAG pipelines, MLOps, and production ML systems
android-expert
Comprehensive Android development expert covering Jetpack Compose, Kotlin coroutines/Flow, Architecture Components, Hilt DI, Navigation, testing, performance, Material Design 3, and modern Android patterns (MVI, Clean Architecture).
api-development-expert
API development expert including REST design, OpenAPI, and documentation
api-testing
API security testing and validation for REST/GraphQL/gRPC endpoints, contract testing, load testing, fuzzing, and Postman/Bruno/Hurl workflows
architecture-review
Architecture review and design validation. Evaluates system designs against best practices, identifies anti-patterns, and ensures architectural decisions align with non-functional requirements.
artifact-integrator
Deep integration analysis for newly created artifacts
arxiv-mcp
Search and retrieve academic papers from arXiv.org using WebFetch and Exa. No MCP server required - uses existing tools to access arXiv API directly.
arxiv-monitor
Scheduled ArXiv paper monitor. Uses CronCreate to search configured keywords every 6 hours, deduplicates via MemoryRecord, and stores summaries in named memory for morning briefing integration.
ask-questions-if-underspecified
Ask the minimum clarifying questions before implementation when requirements are ambiguous or missing crucial details
assimilate
Benchmark external agent frameworks and convert findings into a concrete TDD upgrade backlog for agent-studio evolution.
async-operations
Specifies the preferred syntax for asynchronous operations using async/await and onMount for component initialization. This results in cleaner and more readable asynchronous code.
atlassian-integration
Atlassian ecosystem integration covering Jira project management, Confluence documentation, Bitbucket source control, and cross-product automation workflows
audit-context-building
Ultra-granular code analysis for deep architectural context building. Line-by-line and block-by-block analysis using First Principles, 5 Whys, 5 Hows methodology at micro scale. Builds mental models, tracks invariants and assumptions, and maps cross-function call flows for security audit preparation.
auth-security-expert
OAuth 2.1, JWT (RFC 8725), encryption, and authentication security expert. Enforces 2026 security standards.
auto-recall
Use when you need semantic retrieval from perpetual memory at query time. Parses query intent, searches vector store, ranks by relevance and recency, and injects context. Complements memory-search.cjs with the perpetual_memory LanceDB table.
Page 666 of 1530 · 76465 results