口播脚本打磨
v0.1.0Polish Chinese spoken scripts for videos and tutorials by improving fluency, shortening breath groups, marking pauses, and preserving original meaning.
⭐ 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, SKILL.md, reference doc, and interface YAML all align: the skill's sole purpose is converting written drafts into smoother spoken Chinese; it does not request unrelated binaries, env vars, or external credentials.
Instruction Scope
Runtime instructions are constrained to checking content clarity and rewriting for oral delivery and rhythm. The 'Content Check' step asks to confirm facts and steps; this is reasonable for the purpose but means the agent may rewrite or flag factual issues—users should provide correct context and verify factual edits.
Install Mechanism
Instruction-only skill with no install spec and no code files to execute; nothing will be downloaded or written to disk by an installer.
Credentials
The skill declares no required environment variables, credentials, or config paths, which is proportionate for a text-transformation/polishing skill.
Persistence & Privilege
Skill is not marked always:true and uses default autonomous invocation settings; this is normal and consistent with its scope. It does not request elevated or persistent access.
Assessment
This skill appears coherent and low-risk: it only contains instructions and small reference docs for polishing spoken Chinese scripts and requests no secrets or installs. Before installing, consider: (1) whether you want the agent to perform fact-checking edits—provide source context or disallow factual changes if undesired; (2) review the referenced GitHub homepage if you want licensing or provenance details; (3) avoid feeding sensitive personal or secret data into the skill, since any model-based rewrite could unintentionally expose or alter such content. Autonomous invocation is normal here, but you can restrict when the agent may call the skill if you prefer tighter control.Like a lobster shell, security has layers — review code before you run it.
latestvk97852z59p66z0qtv61aesjma984mhjq
License
MIT-0
Free to use, modify, and redistribute. No attribution required.