7 posts
Ad-hoc prompting is fine for one-off questions. Repeatable workflows deserve structure. This post dissects how a production harness defines, discovers, loads, and executes skills — reusable AI workflows that turn tribal knowledge into executable automation.
8 min readYou have been typing instructions into AI assistants one conversation at a time. Skills flip that model — they turn your best prompts into reusable, structured workflows that any team member can run. This post explains the shift from ad-hoc prompting to skill-driven development.
7 min readEvery AI assistant starts each conversation knowing nothing about your project. Context files change that — they encode your stack, conventions, and constraints so the AI works with your codebase instead of against it. This post shows how to build the foundation layer that makes every skill smarter.
9 min readYou have used AI skills. Now you build one. This post walks through the complete process: identifying a repetitive workflow, extracting it into a structured skill, testing it against real work, and iterating until it reliably produces quality results.
9 min readA skill is not a long prompt. It is a structured workflow with a trigger, a prompt body, references, and an output contract. This post breaks down each component, shows how they interact, and explains the design decisions that separate skills that work from skills that frustrate.
11 min readA single skill handles a single workflow. But real development involves chains of workflows — review then fix then test then commit. This post covers composition patterns: how skills delegate to other skills, how hooks automate triggers, and how pipelines chain skills into end-to-end workflows.
9 min readFour complete skill definitions for workflows developers actually do every day — debugging, code review, technical writing, and deployment. Each pattern is tool-agnostic, tested in production, and ready to adapt to your own projects.
13 min read