Xiang miles | Space2.world

v1.0.0

Interactive CLI tool to create custom AI agent personalities using 16 RPG-style classes, behavioral directives, and a mathematical DNA engine, fully local an...

0· 92·0 current·0 all-time
byMilesXiang@spacesq
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description, SKILL.md, manifest, and the Python entrypoint all align: the tool assembles 5D personality vectors, generates an S2-DNA signature, and prints a Markdown template. No unrelated credentials or binaries are requested.
Instruction Scope
Runtime instructions and code limit actions to interactive terminal prompts, local computation, and printing the generated Markdown. The SKILL.md explicitly promises 0 network calls and the code contains no networking, file writes, or attempts to read other system state beyond user input.
Install Mechanism
No install spec is provided and this is effectively an instruction-only skill with a small Python script. No downloads, package installs, or archive extraction are present.
Credentials
The skill declares and requires no environment variables, no credentials, and accesses no config paths. The code uses only user inputs and local computation, so requested environment access is proportionate.
Persistence & Privilege
always is false and the skill does not persist settings, modify other skills, or change system-wide configuration. It only prints output to stdout and instructs the user to copy the result manually.
Assessment
This skill appears safe and local: it only prompts you, computes a 5D vector, and prints a Markdown template. Before running, you may optionally inspect the script (skill.py) yourself — it is short and readable. Note that while the script does not perform networking, the generated output includes a link to space2.world and the SKILL.md suggests you may visit that site to 'claim' the DNA; do not paste any sensitive or private information to external sites. If you have low trust in third-party code, run the script in an isolated environment (e.g., temporary VM or container) or manually review the file contents first.

Like a lobster shell, security has layers — review code before you run it.

latestvk973xe46wahyqhvetkcbkqxgv1836p1d

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments