Atelier
An atelier is the private workshop or studio where a principal master and a number of assistants, students, and apprentices can work together producing fine art or visual art released under the master's name or supervision.
A personal development toolkit for AI agents - spec-driven development, code quality, deep thinking, and ecosystem patterns.
Skills
This repository includes 34 skills that can be installed via skills.sh. Skills are modular, auto-invoked capabilities that enhance AI agents with specialized knowledge and workflows.
Installing Skills
# Install all skills from the repository
npx skills add martinffx/atelier
# Install specific skills
npx skills add martinffx/atelier --skill typescript:drizzle-orm
npx skills add martinffx/atelier --skill python:fastapi
npx skills add martinffx/atelier --skill spec:research
Available Skills
Spec-Driven Development
spec:finish- Post-implementation validationspec:implement- Execute tasks from plan.jsonspec:plan- Implementation plan + tasks → plan.jsonspec:research- Discovery + research + architecture → spec.mdspec:orchestrator- Skill routing and workflow orchestration
Deep Thinking
oracle:architect- DDD patterns, component responsibilitiesoracle:challenge- Critical thinking and challenging approachesoracle:testing- Stub-driven TDD and layer boundary testingoracle:thinkdeep- Extended sequential reasoning for complex problems
TypeScript Patterns
typescript:api-design- REST API resource naming, HTTP methods, error responses, paginationtypescript:drizzle-orm- Type-safe SQL for PostgreSQL/MySQL/SQLite/Cloudflare D1typescript:dynamodb-toolbox- Single-table design, entity definitions, GSI patternstypescript:fastify- Fastify + TypeBox route handlers and validationtypescript:functional-patterns- ADTs, branded types, Option/Result, migration guidetypescript:effect-ts- Functional effects, error handling, resources, schema, servicestypescript:build-tools- Bun, Vitest, Biome, Turborepo configurationstypescript:testing- Mocking, MSW, snapshot testing
Python Patterns
python:architecture- Functional core/imperative shell, DDD patterns, layered architecturepython:fastapi- Pydantic validation, dependency injection, OpenAPIpython:sqlalchemy- ORM patterns, queries, async, upsertspython:temporal- Workflow orchestration, activities, error handlingpython:modern-python- Type hints, generics, async/await, pattern matchingpython:monorepo- uv workspaces, mise task orchestration, apps/packagespython:testing- Stub-Driven TDD, layer boundary testing, pytest patternspython:build-tools- uv, mise, ruff, basedpyright, pytest configurations
Skills are auto-invoked based on their description when you work with relevant technologies. No commands needed - just install and AI agents will use them when appropriate.
How Skills Work
Skills are auto-invoked based on context. When you say "create a spec for user auth", the AI matches this to spec:research and loads it automatically.
Namespace Philosophy
Skills are organized into three namespaces based on their role:
| Namespace | Type | Invocation | Output | Flexibility |
|---|---|---|---|---|
| spec: | Workflow | User/previous skill | Artifact | Follow exactly |
| oracle: | Thinking | Context-driven | Guidance | Adapt to context |
| code: | Utility | User | Result | Use as needed |
- spec: - Sequential workflow steps that produce artifacts
- oracle: - Analytical skills that provide patterns and principles
- code: - Tools and utilities for specific tasks
The Spec Workflow
graph LR
A[spec:research] -->|spec.md| B[spec:plan]
B -->|plan.json| C[spec:implement]
C --> D[spec:finish]
B -.->|design flaw| A
C -.->|missing tasks| B
C -.->|fundamental issue| A
D -.->|bugs found| C
Standard flow:
- Research - Discovery + research + architecture →
spec.md - Plan - Break into tasks →
plan.json - Implement - Execute with TDD
- Finish - Validate and review
Iteration is normal - Backflows (dotted lines) are expected when:
- Planning reveals design flaws → back to research
- Implementation finds missing tasks → update plan
- Validation finds bugs → back to implement