Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
Don't assume. Don't hide confusion. Surface tradeoffs.
Before implementing:
Minimum code that solves the problem. Nothing speculative.
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
Touch only what you must. Clean up only your own mess.
When editing existing code:
When your changes create orphans:
The test: Every changed line should trace directly to the user's request.
Define success criteria. Loop until verified.
Transform tasks into verifiable goals:
For multi-step tasks, state a brief plan:
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]
Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
The English summary is being prepared. Showing the original description.
Use test-driven development for behavior-changing feature or fix work, and whenever the user mentions TDD, test-first, red-green-refactor, tracer bullets, integration tests, or public-interface behavior tests. Skip for docs-only, path-only rename, formatting-only, or purely mechanical chores unless explicitly requested.
The English summary is being prepared. Showing the original description.
Plan how to build with You.com. Use when adding web search, content extraction, or research to an app or agent: finds the right You.com API, MCP server, SDK, or docs path (for example Vercel AI SDK, LangChain, Python SDK, or REST) through the `you-discover` tool and Docs MCP.
The English summary is being prepared. Showing the original description.
Answer finance and market-data questions with the You.com `you-finance` MCP tool: stock prices, tickers, earnings, company financials, and market trends, with payment-aware fallbacks for keyless hosts.
The English summary is being prepared. Showing the original description.
Multi-source research with citations using You.com. Use for questions that need several sources compared and synthesized, such as library or framework comparisons, tool and vendor evaluations, market research, or deep-dive reports. Routes between a cost-conscious agentic search loop and the one-shot `you-research` MCP tool.
The English summary is being prepared. Showing the original description.
Search the live web and read full pages with You.com. Use whenever a task needs information newer than training data or from outside the codebase: current library docs and API references, changelogs and release notes, breaking changes, error messages, package versions, pricing, news, or any claim to verify with cited sources. Works keyless through the free MCP profile when no You.com credentials are configured.
The English summary is being prepared. Showing the original description.