আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
Guides evaluation-driven development (EDD) process for agent skills. Use when setting up skill testing workflows, creating skill evaluation scenarios, or establishing Claude A/B feedback loops for skill validation. Provides development methodology, not content guidance.
Create MCP (Model Context Protocol) servers using FastMCP Python SDK. Define tools that AI agents can call to perform task operations. Use when building MCP servers for Phase 3 AI chatbot integration.
AUTOMATICALLY run Codex review after writing security-sensitive code (auth, crypto, SQL) - get a second opinion from OpenAI Codex
Continuous learning system that monitors all user requests and interactions to identify learning opportunities. Active during: (1) Every user request and task, (2) All coding sessions and problem-solving activities, (3) When discovering solutions, patterns, or techniques, (4) During /retrospective sessions. Automatically evaluates whether current work contains valuable, reusable knowledge and creates new Claude Code skills when appropriate.
Generate style guides, component mockups, and visual assets using AI (Gemini 3 Pro Image, FLUX.2 Pro). Optional feature - gracefully skips if OPENROUTER_API_KEY unavailable.
Creating high-quality agent skills following Claude's official best practices. Use when designing, implementing, or improving agent skills, including naming conventions, progressive disclosure patterns, description writing, and appropriate freedom levels. Helps ensure skills are concise, well-structured, and optimized for context efficiency.
Use this skill when you need to start or call Chitti's MCP server (chitti.decide/recall/policy/audit) from Codex, keeping tool details out of context until invoked.
Build AI agents with OpenAI's API. Use when creating tool-calling agents, multi-step reasoning systems, function calling implementations, or autonomous AI workflows. Triggers include "OpenAI agent", "function calling", "tool use", "agent loop", "autonomous agent", or "AI assistant with tools".
Expert TypeScript developer specializing in advanced type system features, generic programming, and type-safe application architecture. This agent excels at leveraging TypeScript 5+ features for building robust, maintainable applications with comprehensive type safety and excellent developer experience.
Reinforcement learning training for CTF-AI. Use when training DQN agents, adjusting hyperparameters, debugging training issues, analyzing rewards, or improving AI performance.
Navigating the regulatory landscape and ethical frameworks for responsible AI development and deployment.
Guide for creating Claude Code subagents (custom agents) - specialized AI assistants with isolated context. Use when the user wants to create, add, or configure a subagent/custom agent for Claude Code.
Unified skill management for AI IDEs. Use when users want to: list skills ("what skills do I have", "show installed skills"), search skills ("find skills for X", "search for PDF skill"), install skills ("install a skill", "add skill from GitHub"), create skills ("create a new skill", "make a skill"), sync skills ("sync to all IDEs", "push skills"), remove skills ("remove skill X", "uninstall skill"), validate skills ("validate my skills", "check skill format"), export/import profiles ("export my skills", "import profile", "sync across machines"). Supports 5 IDEs: Claude Code, Cursor, Codex, Gemini CLI, Antigravity. IMPORTANT: When creating or modifying skills, always follow the guidelines in references/skill-creator/SKILL.md.
Self-improving agent architecture using ChromaDB for continuous learning, self-evaluation, and improvement storage. Agents maintain separate memory collections for learned patterns, performance metrics, and self-assessments without modifying their static .md configuration.
Automatically delegates routine coding tasks to free AI models (GLM, GitHub Copilot, and others) via OpenCode MCP, preserving Claude's context window and rate limits for complex reasoning. Use when generating boilerplate, CRUD operations, simple refactoring, test scaffolding, documentation, type definitions, or any well-defined low-judgment task. Triggers automatically when Claude recognizes routine patterns.
This skill should be used when discussing "templates", "apply template", "which template to use", "template selection", "note structure", or when helping users choose appropriate templates for different note types.
An easy way to force agent to think again if it's statement that the "Job is done and production ready" is actually done - usually it's not. This skill ensures that that the AI agent verifies their task and user does not have to check after the agent if they did their job.
Expert guidance for building production-ready tool-calling agents with Databricks Mosaic AI Agent Framework. Use when users need to create agents that orchestrate multiple data sources or APIs, implement LangChain-based agentic workflows, design Foundation Model-powered tool selection, optimize agent prompts and decision-making, or architect multi-tool agent systems. Covers agent architecture patterns, tool design best practices, Foundation Model integration, and common pitfalls.
