Loading...
Loading...
Found 6,268 Skills
Use when the user asks to make something faster, try many variants, run recursive optimization, benchmark latency/throughput/cost, or choose the best implementation by repeated measured tests.
Create or refresh hierarchical AGENTS.md documentation for Claude Code, Codex/OMX, Gemini, and Antigravity/OMA projects, preserving manual notes while excluding runtime state such as root .omc, .omx, .survey, .codex, and generated build folders.
Karpathy's LLM Wiki: build/query interlinked markdown KB.
Document session work with explicit commands. Use /start to begin tracking, /end to finalize session, /clear to reset. Tracks decisions, file changes, and context for continuity.
Kysely type-safe SQL query builder - End-to-end type safety from schema to queries, migrations, transactions, plugins
AI/ML APIs, LLM integration, and intelligent application patterns
Prepare a GitHub PR for merge by rebasing onto main, fixing review findings, running gates, committing fixes, and pushing to the PR head branch. Use after /review-pr. Never merge or push to main.
Automatically analyze performance issues when user mentions slow pages, performance problems, or optimization needs. Performs focused performance checks on specific code, queries, or components. Invoke when user says "this is slow", "performance issue", "optimize", or asks about speed.
MANDATORY when working with time-series data, hypertables, continuous aggregates, or compression - enforces TimescaleDB 2.24.0 best practices including lightning-fast recompression, UUIDv7 continuous aggregates, and Direct Compress
Use when assigning permissions to roles in Bknd. Covers permission syntax (simple strings, extended format), permission effects (allow/deny), policies with conditions, entity-specific permissions, and fine-grained access control patterns.
Unified command interface for the autonomous idea intake workflow system
Analyzes errors, searches past solutions in memory, provides immediate fixes with code examples, and saves solutions for future reference. Use when user says "debug this", "fix this error", "why is this failing", or when error messages appear like TypeError, ECONNREFUSED, CORS, 404, 500, etc.