Lucky Skill Creator
v1.0.0Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
⭐ 0· 56·0 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
Name/description ('Create or update AgentSkills') aligns with the included files: templates, init/package/validate scripts, and tests. There are no required environment variables, binaries, or config paths that would be unexpected for a packaging/templating tool.
Instruction Scope
SKILL.md is a guidance/template document describing how to author skills and when to include scripts/references/assets. It explicitly notes that scripts may be executed or read for patching, which is expected for this tool; however that means operators should review bundled scripts before execution. The instructions do not direct the agent to read unrelated system files, access secrets, or transmit data externally.
Install Mechanism
No install spec (instruction-only skill). All code is bundled as plain Python scripts; there are no downloads or third-party package installs referenced. This is the lowest-risk install posture for a skill.
Credentials
The skill declares no required environment variables, credentials, or sensitive config paths. The code does not attempt to read environment variables or external credentials. The scope of access requested is proportional to its purpose.
Persistence & Privilege
Flags show normal defaults (always: false, agent invocation allowed). The skill does not request permanent/always-on presence and does not modify other skills or system-wide agent settings.
Assessment
This package appears to be an honest skill-creation / packaging toolkit: it contains templates, an initializer, a packager, a quick validator, and tests. Before using it, review any bundled scripts (scripts/*.py) you plan to execute — they run locally and could perform filesystem actions. Packaging script includes sane protections (skips symlinks, prevents path escapes) but still writes archives to disk; run it in a directory you control. Because the skill is instruction-only and contains runnable Python, only execute code from sources you trust and consider running it in an isolated environment if you are uncertain.Like a lobster shell, security has layers — review code before you run it.
agentskillvk978z0r3cg577q8sghvx141at183ncyclatestvk978z0r3cg577q8sghvx141at183ncycopenclawvk978z0r3cg577q8sghvx141at183ncycpackagingvk978z0r3cg577q8sghvx141at183ncycskill-creationvk978z0r3cg577q8sghvx141at183ncyc
License
MIT-0
Free to use, modify, and redistribute. No attribution required.