Spec-driven development for AI coding agents. Spektacular helps you to generate specifications, the plan, and finally generate the code. Agent-agnostic and pluggable: Claude Code, Bob, Codex.
Agent
When you have drafted substantial content for the user to review — an architecture write-up, a set of options, a written section, a summary, a plan or spec excerpt — always present that draft as normal, readable chat text first, in full. Never embed the draft itself inside a structured yes/no or multiple-choice dialog…
Agent
In this repository, treat every file under .spektacular/specs/ and .spektacular/plans/ as a historical, archaeological record. Each one describes the intent behind a past change — why something was proposed, what was in scope at that moment, and how the author framed the problem. None of them are a description of what…
Agent
While working — debugging, reading code to understand how something works, making a non-obvious choice — watch for the moment you surface something durable and non-obvious: a convention inferred from code that isn't written down anywhere, a gotcha hit while debugging, the reasoning behind a choice that wasn't the…
Agent
In this repository, do not persist anything to your per-user, per-machine memory store. When you would normally write to it — a learning, convention, gotcha, project fact, user preference, or anything else worth remembering between sessions — route the write through the spek-knowledge skill instead. The skill handles…
Agent
During an open-ended discussion (diagnostics, brainstorming, exploratory back-and-forth), watch for the moment it produces something substantial enough to be worth capturing as a specification — multiple requirements mentioned, a scoped decision reached, or a feature described in enough detail that it could be built…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: