Project Development

Before you write a single line of code for an LLM project, this walks you through whether an LLM is even the right choice for your task. It covers the full project lifecycle: evaluating task-model fit with those handy proceed-or-stop tables, running manual prototypes to validate quality, designing multi-stage pipelines with the acquire-prepare-process-parse-render pattern, and using the file system as your state machine for natural caching and idempotency. The structured output design section is especially practical, focusing on section markers and parser resilience. Use this when you're architecting a whole pipeline or making project-level decisions about single versus multi-agent systems. Route individual tool schemas to tool-design and per-trajectory optimization to context-optimization.

Install to Claude Code

npx -y skills add muratcankoylan/agent-skills-for-context-engineering --skill project-development --agent claude-code