স্কিল খুঁজুন
আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
terminal-context
Complete Kitty terminal awareness + control for coding agents: list panes/tabs, read scrollback, map ports→processes, parse per-pane git/last-command metadata (from shell hooks), and send commands/focus panes. Use when user mentions "another terminal", "is the server running", "what failed", or you need to run/inspect commands across panes.
xcode-debugging
Use when encountering BUILD FAILED, test crashes, simulator hangs, stale builds, zombie xcodebuild processes, "Unable to boot simulator", "No such module" after SPM changes, or mysterious test failures despite no code changes - systematic environment-first diagnostics for iOS/macOS projects
networking
Analyzes network traffic and exploits protocols. Use when working with PCAP files, Wireshark captures, packet analysis, protocol exploitation, traffic forensics, or data exfiltration detection.
web-security
Exploits web application vulnerabilities. Use when working with SQL injection, XSS, SSRF, SSTI, command injection, path traversal, authentication bypass, deserialization, or any web-based CTF challenge.
injection-vulnerabilities-ai-generated-code
Understand how AI generates SQL injection, command injection, and XSS vulnerabilities. Use this skill when you need to learn about injection attack patterns in AI code, see real-world examples of injection vulnerabilities, understand why AI generates insecure database queries, or recognize vulnerable code patterns. Triggers include "SQL injection AI", "command injection", "XSS vulnerabilities", "injection attacks", "AI database queries", "shell injection", "cross-site scripting AI code".
cloudflare-browser-rendering
Guide for implementing Cloudflare Browser Rendering - a headless browser automation API for screenshots, PDFs, web scraping, and testing. Use when automating browsers, taking screenshots, generating PDFs, scraping dynamic content, extracting structured data, or testing web applications. Supports REST API, Workers Bindings (Puppeteer/Playwright), MCP servers, and AI-powered automation. (project)
comparing-screenshots
Compares Figma screenshots with HTML screenshots using pixel-level analysis. Use when verifying visual accuracy of Figma-to-HTML conversion.
detecting-double-free
Detects double free vulnerabilities by identifying attempts to free the same memory block twice. Use when analyzing memory management, cleanup paths, or investigating heap corruption issues.
detecting-unchecked-malloc
Detects unchecked return values of memory allocation functions like malloc, calloc, and realloc that can lead to null pointer dereferences. Use when analyzing memory allocation, error handling, or investigating null pointer risks.
claude-chrome-debugging
Diagnoses and fixes Claude in Chrome extension issues including zombie MCP processes, action failures, and extension conflicts
information-leakage-hardcoded-secrets-ai-code
Understand how AI-generated code exposes sensitive information through hardcoded credentials and verbose logging. Use this skill when you need to learn about hardcoded secrets in AI code, understand logging vulnerabilities, recognize exposed API keys, or prevent information disclosure. Triggers include "hardcoded credentials", "hardcoded secrets", "API keys in code", "information leakage", "verbose logging", "exposed secrets", "AWS keys", "logging vulnerabilities", "sensitive data logs".
detecting-buffer-overflows
Detects stack and heap buffer overflow vulnerabilities in binary code by identifying unsafe memory operations. Use when analyzing buffer handling, string manipulation functions, or investigating memory corruption vulnerabilities.
billing-guard
计费审计专家,在规划/开发/运行阶段持续审计与优化成本。评估任务卡预算、模拟调用成本、监控高成本路径,在超出预算或异常时阻断执行并提出替代方案。遵循数据驱动、三板斧优化(缓存/批量/降级)、预警阻断的工程基线。适用于规划预审、PR成本审查、运行时监控时使用。
code-executor-troubleshooting
Troubleshooting guide for Code Executor MCP issues - diagnose hanging, import errors, and connection problems
braintrust-tracing
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
performance-optimization
This skill should be used when the user asks about Rails performance optimization, slow queries, caching strategies, database indexing, N+1 query prevention, memory optimization, asset optimization, profiling, benchmarking, Rack Mini Profiler, Bullet gem, query analysis, Russian doll caching, fragment caching, page speed, or production performance tuning. Also use when discussing YJIT, Puma configuration, or scalability. Examples:
