Tiktok Claim Rewriter
v1.0.0Rewrite risky TikTok product claims into safer and clearer language without losing persuasion. Use when scripts may trigger policy risk or overpromise concerns.
⭐ 0· 201·1 current·1 all-time
byLeroyCreates@leooooooow
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (rewrite risky TikTok claims) matches the SKILL.md workflow and expected inputs; nothing requested (env vars, binaries, or installs) is unrelated to the stated task. Note: source/homepage are unknown and the skill carries a CC BY-NC-SA license — commercial use requires a separate license from Razestar.
Instruction Scope
SKILL.md only instructs the agent to detect risky lines, explain risk, produce safer rewrites and alternatives. It does not direct reading of unrelated files, access to system env vars, or transmission to external endpoints. Instructions are reasonably scoped to the stated purpose.
Install Mechanism
No install spec and no code files — instruction-only skill. There is nothing written to disk or downloaded at install time.
Credentials
The skill requires no environment variables, credentials, or config paths. Declared inputs (script, factual boundaries, forbidden phrases, audience) are appropriate for the task.
Persistence & Privilege
always is false and the skill does not request persistent system presence or modify other skills/config. The default ability for the agent to call the skill autonomously is normal and not by itself a concern here.
Assessment
This skill appears coherent and low-risk because it is instruction-only and requests no credentials or installs. Before installing, consider: (1) provenance — source and homepage are unknown, so verify trustworthiness if you require provenance assurances; (2) license — CC BY-NC-SA disallows commercial use without a separate paid license from Razestar; (3) privacy — do not feed the skill PII or sensitive commercial secrets unless you are prepared to accept that the agent will process them; (4) review outputs — have a human compliance/legal reviewer approve rewritten claims (the model can still hallucinate or soften required factual claims despite instructions not to fabricate); (5) if you enable autonomous invocation, monitor usage and audit logs so the skill isn't used on sensitive content without oversight.Like a lobster shell, security has layers — review code before you run it.
latestvk97fet9fadw80mwrdvg1qrx7b182tx9a
License
MIT-0
Free to use, modify, and redistribute. No attribution required.