skills/rpgjs-studio/SKILL.md
Use the RPGJS Studio HTTP API to create or manage a 2D RPG game. Trigger this skill when Codex needs to CRUD maps, map events, database records, media assets, or general project settings in RPGJS Studio, especially when the task should be done through `curl` or another HTTP client with an API key and configurable base URL.
npx skillsauth add rsamaium/rpg-js rpgjs-studioInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill to execute content-management tasks against an RPGJS Studio instance.
RPGSTUDIO.md file exists in the current working directory.RPGSTUDIO.md exists, treat it as local project context and read it first.BASE_URLprojectIdRPGSTUDIO.md does not exist, continue normally.BASE_URL from the user if provided.BASE_URL to https://rpgjs.studio when the user did not specify another host.RPGSTUDIO_API_KEY.RPGSTUDIO_API_KEY exists before any API call.RPGSTUDIO_API_KEY, never print its value in the terminal and never echo it back in the response.${BASE_URL}/api-keys, then export RPGSTUDIO_API_KEY.-H "x-api-key:$RPGSTUDIO_API_KEY"
-H "Content-Type: application/json"
curl for HTTP calls. Use another HTTP client only if there is a clear reason.401, or 403, stop the task and tell the user to verify the key or contact support.references/database.mdreferences/maps.mdreferences/events.mdreferences/event-examples.mdreferences/blocks.mdreferences/media.mdreferences/settings.mdUse RPGSTUDIO.md as a lightweight local memory file for the current project.
Typical contents:
BASE_URLprojectIdIf projectId is still unknown after reading RPGSTUDIO.md and the current user request does not provide it:
projectId in RPGSTUDIO.md so it does not need to be requested again later.Never store secrets in this file.
RPGSTUDIO_API_KEY.RPGSTUDIO_API_KEY.Define the base command once and reuse it:
BASE_URL="${BASE_URL:-https://rpgjs.studio}"
curl -sS \
-H "x-api-key:$RPGSTUDIO_API_KEY" \
-H "Content-Type: application/json"
Use project listing when projectId is missing:
curl -sS "$BASE_URL/api/projects" \
-H "x-api-key:$RPGSTUDIO_API_KEY" \
-H "Content-Type: application/json"
For write operations, prefer:
curl -sS -X POST "$BASE_URL/..." \
-H "x-api-key:$RPGSTUDIO_API_KEY" \
-H "Content-Type: application/json" \
-d '{...}'
GET, POST, PUT, DELETE./api/media?query=<search>./api/database/:type?query=<search>._id._id.projectId is missing, list projects, ask the user to choose one, and stop until they answer.GET endpoint first and adapt from that live payload./api/media/generate/... endpoint.POST /api/maps/generate, rely on references/maps.md for the AI map generation workflow and endpoint-specific failure behavior.BASE_URL or projectId, persist that context into RPGSTUDIO.md for future runs.database task: read references/database.mdmap task: read references/maps.mdevent task: read references/events.mdevent example task: read references/event-examples.mdevent workflow block task: read references/blocks.mdmedia task: read references/media.mdsettings task: read references/settings.mdtools
Manage, inspect, install, and implement work in an internal RPGJS v5 game project. Use when Codex needs to work on a codebase that should be an RPGJS v5 project, especially for gameplay features, maps, events, server/client code, `@rpgjs/*` dependencies, Tiled-based content, or `.ce` UI files. Also use when Codex must first verify whether the current project is actually an RPGJS project and, if not, read the RPGJS v5 quick start, install the project scaffold, and continue from that baseline.
tools
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
tools
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
tools
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------