Feelslikeclaude
v1.1.0Make OpenClaw feel more proactive, calm, competent, and execution-focused. Use when the user wants less filler, stronger initiative, clearer progress updates...
⭐ 1· 120·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description match the requested artifacts: the skill is an instruction-only behavior overlay and asks for no binaries, env vars, or installs. Nothing requested is out of proportion with a UI/behavior style overlay.
Instruction Scope
SKILL.md stays within a behavioral/style scope and explicitly forbids network activity and identity/config rewrites. However, it tells the agent to 'start the real work' and to execute step 1 when clear—this encourages autonomous, action-first behavior. If the runtime agent has side-effecting connectors or permissions, that guidance could cause the agent to perform network or destructive actions unless other runtime safeguards are enforced.
Install Mechanism
No install spec and no code files. Lowest-risk distribution method: nothing is downloaded or written to disk by the skill itself.
Credentials
No environment variables, credentials, or config paths are requested. The skill does not require access to secrets or external services.
Persistence & Privilege
always:false and no special privileges requested. The skill does not attempt to persist configuration or modify other skills; autonomous invocation is the platform default and not changed here.
Assessment
This skill is a local behavior overlay and does not request credentials or install anything, so it's coherent with its description. Before enabling it broadly, check how your OpenClaw runtime handles actions: because the skill encourages doing the next step automatically, make sure connectors that can perform network, billing, or destructive operations require explicit confirmation. Consider testing in a low-risk environment, enable logs or an approval step for external actions, and keep the skill disabled for runs that must be strictly read-only or audit-only.Like a lobster shell, security has layers — review code before you run it.
latestvk97dr4zhyfqfw8tc2y5b6yp7kn84dqkb
License
MIT-0
Free to use, modify, and redistribute. No attribution required.