UI Polish Pass
v1.0.0Core pack — always active as final step. Visual polish pass for spacing, hierarchy, alignment, and cleanup. Runs after design-review and ux-baseline-check as...
⭐ 0· 91·0 current·0 all-time
byai-ron@aa-on-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's name, description, and SKILL.md all describe a visual polish checklist and the requested capabilities (none) match that purpose. Minor inconsistency: the SKILL.md repeatedly calls this a "Core Pack — Always Active" and says it "Runs after design-review and ux-baseline-check," but the registry metadata sets always: false; this is likely a wording/metadata mismatch rather than a security problem.
Instruction Scope
The instructions are purely procedural design guidance (spacing, typography, alignment, etc.). They do not instruct the agent to read files, environment variables, or send data to external endpoints, nor do they require access to system paths or credentials.
Install Mechanism
There is no install spec and no code files; this is instruction-only. That minimizes disk writes and execution risk.
Credentials
The skill requires no environment variables, credentials, or config paths, which is proportionate for a stylistic checklist.
Persistence & Privilege
The skill is not marked always:true (registry shows always:false) and has default autonomous invocation enabled (disable-model-invocation:false). Autonomous invocation is platform default and not inherently concerning, but if you do not want the agent to call this skill without prompting, consider disabling model invocation in your agent settings.
Assessment
This is a lightweight, instruction-only design checklist with no installs or credential requirements and is coherent with its stated purpose. Before installing, confirm whether you want the agent to be allowed to invoke the skill autonomously (it's allowed by default) and note the minor wording mismatch that calls it "always active" while the registry flag is false. If you rely on linked documents (e.g., alignment.md) or on it running after other skills, ensure those other skills exist in your agent workflow.Like a lobster shell, security has layers — review code before you run it.
latestvk97b59wt5k82rsabe4ywfn35hn838wpw
License
MIT-0
Free to use, modify, and redistribute. No attribution required.