unspa-worldplay
unspa-worldplay is an Entertainment & games skill for AI agents, published by lyriks-io in the unspaghettit repository on GitHub. Skillspace rates unspa-worldplay D (66/100) and it passed the safety scan; the rating is based on static analysis only.
Use to actually walk a player through a world built with Unspaghettit — chat-explorable text-adventure style. Keeps the runtime state in a save file at `.unspa-world/<featureId>.save.json` so the model never relies on its own eroding context for the player's purse, inventory, time of day, or location. Each turn re-reads the save, maps the user's intent to a modeled Action, asks the MCP's simulator to resolve it, applies the resulting diff back to the file, and narrates. Triggers on "walk in", "enter the world", "let me play", "drop me into", "begin the adventure", "start the world", "let's chat-explore", "run the world", "play <world name>".
- Grade
- D
- Quality
- 66 / 100
- Safety
- Passed
- GitHub stars
- 25
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 96 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- AGPL-3.0
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.