karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes,…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-18 00:15
41,689 results
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes,…
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical…
Use when executing implementation plans with independent tasks in the current session
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via…
Use when you have a spec or requirements for a multi-step task, before touching code
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a…
Implement a piece of work based on a spec or set of tickets.
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a…
Use when you need to resolve an in-progress git merge/rebase conflict.
Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.
Manage an ibl.ai organization's LLM spend caps via the platform API — admin-imposed maximum LLM cost at three scopes (tenant-wide, one agent, or one user on…
Add the agent History tab (conversation history with filters and export) to your Next.js app
Add the agent Prompts tab (system prompts and suggested prompts) to your Next.js app
Connect your app to the iblai backend
Present OpenAPI operations as numbered options, then return the chosen items as a JSON object mapping paths to HTTP methods.
Score all open PRs by risk level and generate a CSV report. Use when asked to rescore, rate, or triage open PRs.
Explain a change until the user could defend it — a PR they are about to review, a diff an agent just wrote, a branch they returned to. Use when the user…
Use when creating or modifying API endpoints (Rails controllers, engine routes, API actions). Requires generating or updating a Postman Collection (JSON v2.1)…
Use when reviewing a Ruby on Rails app for Domain-Driven Design boundaries, bounded contexts, language leakage, cross-context orchestration, or unclear…
Use when the user asks to create tasks, generate a task list, break down a PRD into implementation steps, plan implementation, or create an implementation…
Use when creating, scaffolding, or refactoring a Rails engine. Trigger words: mountable engine, Railtie, engine.rb, isolate_namespace, engine file layout,…
Use when writing or maintaining documentation for Rails engines. Trigger words: engine README, installation guide, configuration docs, mount instructions,…
Use when extracting existing Rails app code into a reusable engine. Trigger words: extract to engine, move feature to engine, host coupling, adapters,…