Deepchat Sdd

This enforces a spec-driven development workflow for the DeepChat project before you touch any code. It makes you classify whether you're building a feature, fixing an issue, or refactoring architecture, then generates three markdown files in the right docs folder: spec.md for requirements, plan.md for approach, and tasks.md for execution. Every NEEDS CLARIFICATION marker must be resolved before implementation starts. The workflow is opinionated about DeepChat's patterns like Presenter boundaries and typed contracts, and it includes hygiene rules for archiving stale specs. If you're working on DeepChat or want to enforce similar discipline on your own Electron project, this keeps design decisions visible and prevents diving straight into code when you should be writing things down first.

GitHub stars: 6K
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add thinkinaixyz/deepchat --skill deepchat-sdd --agent claude-code

Installs into .claude/skills of the current project.

Files

DeepChat SDD

When To Use

Use this skill before substantial DeepChat source code, configuration, tests, docs, build scripts, release workflows, or project structure changes that need shared context or a durable decision record.

Skip SDD for trivial or tightly localized work unless the developer explicitly asks for it:

visual/style fixes, copy changes, and small UI layout adjustments
simple localized logic changes with a clear owner module
routine docs edits that do not change project direction
release metadata already covered by the release flow

If the scope is unclear, inspect first and then ask whether SDD is wanted instead of creating artifacts by default.

Classify The Goal

Create one kebab-case folder per goal:

New capability, user-visible behavior, integration, or tool large enough to need a shared plan: docs/features/<goal>/
Complex bug, regression, failing test, CI failure, reliability problem, or prompt/runtime issue: docs/issues/<goal>/
Refactor, migration, dependency boundary, shared contract, runtime architecture, or cross-module design: docs/architecture/<goal>/

SKILL.md on GitHub