Menu
Apply planned changes
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | editing |
| description | Apply planned changes |
| whenToUse | When the plan exists and you're applying step-by-step edits |
| allowedTools | ["edit_file","run_tests","read_file"] |
Apply the plan one step at a time. Run tests after each change.
Helps developers integrate @context-chef/ai-sdk-middleware into their Vercel AI SDK (v7+) projects. Use this skill when the user wants to add transparent context management to an AI SDK app, wrap a model with automatic history compression, truncate large tool results, manage token budgets, or inject dynamic state into AI SDK prompts. Also trigger when the user mentions 'context-chef middleware', 'AI SDK middleware', 'ai-sdk context', or asks about compressing history / truncating tool results / managing tokens in a Vercel AI SDK project.
Helps developers integrate the context-chef library into their TypeScript/JavaScript AI agent projects. Use this skill when the user wants to add context-chef to their project, set up context management for LLM calls, integrate history compression or tool management into an agent loop, or asks about wiring context-chef with OpenAI/Anthropic/Gemini. Also trigger when the user mentions 'context-chef', 'context compiler', 'context engineering', or asks how to manage LLM context, compress conversation history, prune tools, or add memory to their AI agent.
Helps developers integrate @context-chef/core into their TypeScript/JavaScript AI agent projects. Use this skill when the user wants to add context-chef to their project, set up context management for LLM calls, integrate history compression or tool management into an agent loop, or asks about wiring context-chef with OpenAI/Anthropic/Gemini. Also trigger when the user mentions 'context-chef', 'context compiler', 'context engineering', or asks how to manage LLM context, compress conversation history, prune tools, or add memory to their AI agent.
Folded multi-line description that the v1 parser would have rejected because of the indentation.
Diagnose database query and connection issues
Plan changes before editing
