trpc-compat
Check that a tRPC change is safe for released desktop, mobile, CLI, and SDK builds, pick the compatible pattern, and decide when a deprecated procedure can be…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-20 00:12
41,963 results
Check that a tRPC change is safe for released desktop, mobile, CLI, and SDK builds, pick the compatible pattern, and decide when a deprecated procedure can be…
All bugs start here. Disciplined 7-phase diagnosis loop (Phase 0-6) for bugs and performance regressions. Load context → build feedback loop → reproduce →…
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as…
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve…
Configure LSP code intelligence for the current code repository—install LSP language servers, configure Codex LSP MCP, install LSP session hook, write retrieval rules to project CLAUDE.md / AGENTS.md. All configuration is written to the project working directory (.claude/ .codex/), without polluting global settings. Trigger scenarios: lsp-setup, configuration…
Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic…
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality…
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert…
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent,…
Use when you have a spec or requirements for a multi-step task, before touching code
Guides building modular, testable iOS/Swift applications following the Essential Developer methodology -- clean architecture with protocol-oriented design,…
Molten OS Core — fourth step of the Agent Development Loop. Implements an approved plan one thin slice at a time using a lightweight test-driven loop (red,…
Molten OS Core — optional step in the Agent Development Loop, between discovery and spec. Builds a fast, throwaway prototype to answer the riskiest question…
Molten OS Core — sixth and final step of the Agent Development Loop. Reviews the finished change before it merges across five axes — correctness against the…
Spec-driven development workflow for projects that use spec files as both product spec and manual. Use when writing specs, implementing tasks from specs, or…
Fetches verified smart contract source code from Sourcify and Etherscan for any EVM-compatible chain. Use this skill whenever the user wants to download,…
Fetches the full execution trace of an EVM transaction using debug_traceTransaction API. Use this skill whenever the user wants to trace a transaction, inspect…
This skill should be used when the user asks to "update docstrings", "audit docstrings", "fix docstrings", "add docstrings", "check docstrings", "Google-style…
Deep dive into project history, direction, and implementation details
Continue incomplete work - find gaps, finish features, fix what's broken
Deep refactoring - modularity, deduplication, cleanup
Generates complete SDLC Phase 1 (Requirements Analysis) and Phase 2 (System Design) documentation from a single product idea or instruction. Trigger: When user…
Use when developing features with OpenSpec spec-driven workflow, supporting both interactive and Ralph Loop automation modes
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js…