স্কিল খুঁজুন
আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
command-validator
This skill should be used when the user wants to "validate a command", "review my command", "check command quality", "audit slash command", or needs evaluation of their Claude Code custom command against best practices.
agent-sdk-dev
Agent SDK development utilities for creating, testing, and managing AI agents with comprehensive tooling and debugging capabilities.
synthetic-data
Use this skill when generating synthetic datasets using LLMs. Covers implementation with localrouter, prompting strategies for diversity, model selection, parallelization patterns, and dataset testing workflows. Ideal for creating training data, test datasets, or augmenting existing data.
skill-generator
Generate new Agent Skills following the open standard specification. Use this when asked to create a new skill, teach Copilot a new capability, or capture domain expertise as a reusable skill.
moai-cc-skill-factory
AI-powered enterprise skill creation orchestrator with intelligent discovery, predictive optimization, ML-based content generation, and Context7-enhanced development patterns. Use when creating smart skill systems, implementing AI-driven skill generation, optimizing skill performance with machine learning, or building enterprise-grade skill factories with automated compliance and governance.
qdrant-vectordb
Use when working with Qdrant vector database for semantic search and RAG. Covers collection setup, embedding generation, vector upsert/search, HNSW indexing, filtering, and integration with OpenAI embeddings for textbook content retrieval.
fork-bash-skill
Execute agentic coding tools directly via bash commands with output capture. Use this when the user requests to run AI agents (Gemini, Claude Code, etc.) and get their results directly.
session-closing
End-of-session ritual. Reflect while context is rich, then seal. Triggers on /close, 'wrap up', 'let's finish', or context nearly full. Pairs with /open. (user)
fx-explore
Discover available effects, actions, and placeholders in a Sandestin project. Use when asking what effects exist, searching for functionality, or needing example invocations. Keywords: effects, actions, dispatch, describe, grep, sample.
hitl-design
Design human-in-the-loop workflows including review queues, escalation patterns, feedback loops, and quality assurance for AI systems.
claude-code-knowledge
Access official Claude Code documentation including comprehensive guides on hooks, MCP servers, agent skills, slash commands, settings, CLI reference, security, memory, plugins, and troubleshooting. Use when the user asks about Claude Code features, configuration, capabilities, or best practices. ALWAYS use this skill instead of guessing about Claude Code functionality - it contains the authoritative documentation from docs.anthropic.com with automatic updates. Also includes comprehensive skill creation guide with helper scripts when users want to create new skills.
skill-creator
Create and refine Claude Code skills following best practices. Use when building new skills from scratch, validating existing skills against standards, or improving subpar skills to production quality. For personal, team, or production environments.
multi-ai-debugging
Systematic debugging using Claude, Gemini, and Codex as specialized agents. Multi-agent root cause analysis, log analysis, error classification, and auto-fix generation. Use when debugging production issues, analyzing error logs, performing root cause analysis, troubleshooting complex systems, or implementing self-healing patterns.
langsmith-debugger
Debug and analyze {{PROJECT_NAME}} LangGraph agent traces. Use when investigating agent behavior patterns, finding failures, analyzing latency, or understanding why Orchestrator/Analyst responses went wrong. Covers trace queries by agent tags, pattern analysis across runs, and common debugging scenarios.
gemini-sdk-expert
"Senior SDK Master for @google/genai v1.35.0, expert in Controlled Outputs and Structured Intelligence.
uloop-get-provider-details
Get Unity Search provider details via uloop CLI. Use when you need to: (1) Discover available search providers, (2) Understand search capabilities and filters, (3) Configure searches with specific provider options.
plan
Agent Skill that brainstorm and produce a plan (not implementation). Use when the user asks for planning, a roadmap, an investigation/debug plan, or approach comparisons; gather context, ask clarifying questions, propose 1–3 options with tradeoffs, then produce a step-by-step plan with verification checkpoints.
using-core
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists
