Loading...
Loading...
Found 2,158 Skills
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use this skill when the user needs to build Move code, or when when the user asks about sui move build.
Debug Compact contracts and manage toolchain versions. Covers static vs dynamic errors, reading compiler messages, the --skip-zk dev loop, version synchronization, and common traps.
Avoid common mistakes and debug issues in PydanticAI agents. Use when encountering errors, unexpected behavior, or when reviewing agent implementations.
Use when app feels slow, memory grows, battery drains, or diagnosing ANY performance issue. Covers memory leaks, profiling, Instruments workflows, retain cycles, performance optimization.
See exactly what your AI did on a specific request. Use when you need to debug a wrong answer, trace a specific AI request, profile slow AI pipelines, find which step failed, inspect LM calls, view token usage per request, build audit trails, or understand why a customer got a bad response. Covers DSPy inspection, per-step tracing, OpenTelemetry instrumentation, and trace viewer setup.
Debug regex patterns with visual breakdowns, plain English explanations, test case generation, and flavor conversion. Use when user needs help with regular expressions or pattern matching.
Use when building UIKit interfaces without storyboards, setting up Auto Layout constraints with anchors, creating reusable UI components, or encountering layout constraint errors and ambiguous layout warnings
Creates a pull request from current changes, monitors GitHub CI, and debugs any failures until CI passes. Use this when the user says "create pr", "make a pr", "open pull request", "submit pr", or "pr for these changes". Does NOT merge - stops when CI passes and provides the PR link.
Fetch and analyze Sentry issues, events, transactions, and logs. Helps agents debug errors, find root causes, and understand what happened at specific times.
strace and ltrace skill for system call and library call tracing. Use when a binary behaves incorrectly without crashing, diagnosing file-not-found errors, permission failures, network issues, or unexpected library calls by tracing syscalls and library function calls. Activates on queries about strace, ltrace, syscall tracing, library interception, ENOENT, EPERM, strace -e, or diagnosing binary behaviour without a debugger.
Analyzes an MLflow session — a sequence of traces from a multi-turn chat conversation or interaction. Use when the user asks to debug a chat conversation, review session or chat history, find where a multi-turn chat went wrong, or analyze patterns across turns. Triggers on "analyze this session", "what happened in this conversation", "debug session", "review chat history", "where did this chat go wrong", "session traces", "analyze chat", "debug this chat".