Agent skill
railway-projects
List, switch, and configure Railway projects. Use when user wants to list all projects, switch projects, rename a project, enable/disable PR deploys, make a project public/private, or modify project settings.
Install this agent skill to your Project
npx add-skill https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/railway/projects
SKILL.md
Railway Project Management
List, switch, and configure Railway projects.
When to Use
- User asks "show me all my projects" or "what projects do I have"
- User asks about projects across workspaces
- User asks "what workspaces do I have"
- User wants to switch to a different project
- User asks to rename a project
- User wants to enable/disable PR deploys
- User wants to make a project public or private
- User asks about project settings
List Projects
The railway list --json output can be very large. Run in a subagent and return only essential fields:
- Project:
id,name - Workspace:
id,name - Services:
name(optional, if user needs service context)
railway list --json
Extract and return a simplified summary, not the full JSON.
List Workspaces
railway whoami --json
Returns user info including all workspaces the user belongs to.
Switch Project
Link a different project to the current directory:
railway link -p <project-id-or-name>
Or interactively:
railway link
After switching, use railway-status skill to see project details.
Update Project
Modify project settings via GraphQL API.
Get Project ID
railway status --json
Extract project.id from the response.
Update Mutation
bash <<'SCRIPT'
${CLAUDE_PLUGIN_ROOT}/skills/lib/railway-api.sh \
'mutation updateProject($id: String!, $input: ProjectUpdateInput!) {
projectUpdate(id: $id, input: $input) { name prDeploys isPublic botPrEnvironments }
}' \
'{"id": "PROJECT_ID", "input": {"name": "new-name"}}'
SCRIPT
ProjectUpdateInput Fields
| Field | Type | Description |
|---|---|---|
name |
String | Project name |
description |
String | Project description |
isPublic |
Boolean | Make project public/private |
prDeploys |
Boolean | Enable/disable PR deploys |
botPrEnvironments |
Boolean | Enable Dependabot/Renovate PR environments |
Examples
Rename project:
${CLAUDE_PLUGIN_ROOT}/skills/lib/railway-api.sh '<mutation>' '{"id": "uuid", "input": {"name": "new-name"}}'
Enable PR deploys:
${CLAUDE_PLUGIN_ROOT}/skills/lib/railway-api.sh '<mutation>' '{"id": "uuid", "input": {"prDeploys": true}}'
Make project public:
${CLAUDE_PLUGIN_ROOT}/skills/lib/railway-api.sh '<mutation>' '{"id": "uuid", "input": {"isPublic": true}}'
Multiple fields:
${CLAUDE_PLUGIN_ROOT}/skills/lib/railway-api.sh '<mutation>' '{"id": "uuid", "input": {"name": "new-name", "prDeploys": true}}'
Composability
- View project details: Use railway-status skill
- Create new project: Use railway-new skill
- Manage environments: Use railway-environment skill
Error Handling
Not Authenticated
Not authenticated. Run `railway login` first.
No Projects
No projects found. Create one with `railway init`.
Permission Denied
You don't have permission to modify this project. Check your Railway role.
Project Not Found
Project "foo" not found. Run `railway list` to see available projects.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
Didn't find tool you were looking for?