claude-code-atelier
Spec-driven planning, code review, and disciplined debugging workflows
All Skills in This Repository (24)
Pure Emerald Level Indicatorsatelier-typescript-dynamodb-toolbox
Model DynamoDB single-table designs with type-safe PK/SK patterns in TypeScript.
atelier-typescript-api-design
Design REST APIs with consistent error handling and pagination.
atelier-typescript-testing
Generate Vitest and MSW testing patterns for TypeScript unit and integration tests.
atelier-typescript-build-tools
Configure TypeScript build tooling with Bun, tsgo, Vitest, Biome, and Turborepo.
atelier-typescript-fastify
Build typed REST APIs with Fastify and TypeBox schema validation.
atelier-typescript-functional-patterns
Model TypeScript domain logic with ADTs, Option/Result, and branded types.
atelier-typescript-drizzle-orm
Define Drizzle ORM schemas and generate type-safe TypeScript queries.
atelier-typescript-effect-ts
Model TypeScript computations as typed effects with Effect-TS.
atelier-spec-beads
Manage dependency-aware tasks for spec-driven workflows with Git-backed persistence.
atelier-spec-testing
Guide stub-driven TDD and layer-boundary testing for software teams.
atelier-spec-architect
Translate feature ideas into domain-driven hexagonal architecture plans.
atelier-spec-methodology
Coordinate spec-driven development with AgentOS context layers and OpenSpec living specifications.
Frequently Asked Questions
FAQPage SchemaHow to install Atelier?โผ
Run `npx skills add martinffx/claude-code-atelier --all -g -y` in your terminal to install all skills globally.
What does Atelier do for coding workflows?โผ
It enforces a disciplined loop of brainstorming, planning, implementation, review, and pull request creation so code is approved and verified before it ships.
Does Atelier work with Claude Code, Codex, and Cursor?โผ
Yes. The skills follow the standard SKILL.md format and the CLI configures specialist agents for Claude Code, OpenCode, Codex, and Cursor.
How does Atelier handle debugging?โผ
The oracle-debug skill enforces root-cause investigation first, then hypothesis testing and a verified fix, preventing random quick patches.
Do I stay in control of the code changes?โผ
Yes. Every plan, commit, and pull request requires your explicit approval before the agent writes or merges anything.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core