life-gacha
v1.0.0A daily gacha skill — draw a random activity each morning, check in at night, and get a weekly summary. Adds a little surprise to every day.
⭐ 1· 74·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill is a local 'daily gacha' utility and all included scripts implement that functionality (drawing, filling a note, summarizing a week). Minor mismatch: registry metadata lists no required binaries, but SKILL.md and the scripts expect python3 and the draw.py imports PyYAML (yaml); those runtime requirements are not declared in the registry metadata.
Instruction Scope
SKILL.md confines actions to the skill directory: reading/updating config.yaml, writing/reading files under data/, and setting up scheduled tasks. It instructs the agent to run the provided scripts and to edit config.yaml when the user asks — behavior that matches the skill's purpose and the available code.
Install Mechanism
There is no install spec (instruction-only) and no downloads. The code is bundled with the skill and runs locally; this is the lowest-risk install model. Note that the environment must have Python and PyYAML available for the scripts to run.
Credentials
The skill requests no environment variables, no external credentials, and only accesses files within its own directory (config.yaml and data/). The requested access is proportionate to its stated purpose.
Persistence & Privilege
The skill does not request always: true and does not modify other skills or system-wide agent settings. It writes only to its own data files (data/YYYY-MM/week-NN.md) and its own config.yaml as described in SKILL.md.
Assessment
This skill appears to do what it says: local daily draws and local markdown journaling. Before installing, ensure the agent environment has python3 and PyYAML (yaml) so draw.py runs correctly. Be aware the skill will create and modify files under its directory (config.yaml and data/); if you schedule automatic runs, those tasks will cause the agent to run scripts and write local files without further prompts. If you want tighter control, run draws manually or review/approve any config edits before they are written. If you need network isolation, run the skill in an environment without outbound access — the code does not contact external services but being cautious is reasonable.Like a lobster shell, security has layers — review code before you run it.
latestvk973ns0h2xrcbmz92mb6n5pe9x83dvf4
License
MIT-0
Free to use, modify, and redistribute. No attribution required.