Project Development

muratcankoylan/agent-skills-for-context-engineering

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.

skills.sh installs: 189
GitHub stars: 18.3K
last updated: May 26, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Project Development Methodology

This skill covers the principles for identifying tasks suited to LLM processing, designing effective project architectures, and iterating rapidly using agent-assisted development. The methodology applies whether building a batch processing pipeline, a multi-agent research system, or an interactive agent application.

The unit of work for this skill is the whole project or a multi-stage pipeline. Individual tool design (descriptions, schemas, error messages) belongs to tool-design. Per-skill activation routing belongs to the corresponding skill plus the corpus index. This skill owns the project-level questions: should you build this with an LLM at all, what shape should the pipeline take, what does it cost, how should it be iterated.