Ads Bid Optimizer
v1.0.0Optimize budget pacing and bid strategy for Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, and DSP/programmatic auctions.
⭐ 0· 318·0 current·0 all-time
bydanyangliu@danyangliu-sandwichlab
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the content of SKILL.md: it describes bid logic, pacing guardrails, allocation optimization across ad platforms and the inputs/outputs and workflow are aligned with that purpose. There are no unexpected requirements (no env vars, no binaries, no platform credentials) that would be incoherent for a planning/advisory skill.
Instruction Scope
SKILL.md contains only guidance for producing strategy output, test matrices, and guardrails. It does not instruct reading system files, environment variables, or contacting external endpoints. One ambiguous phrase — "escalate with a structured handoff payload" — mentions creating a handoff payload but does not specify any endpoint or exfiltration mechanism; this is vague but not demonstrably malicious given the rest of the content.
Install Mechanism
No install spec and no code files — instruction-only skill. This is the lowest-risk install footprint and nothing is written to disk or downloaded.
Credentials
The skill declares no required environment variables, credentials, or config paths. That is proportionate for an advisory/strategy skill which does not connect to ad accounts or execute account-level actions.
Persistence & Privilege
always is false and the skill does not request permanent presence or system modification. Model invocation is allowed (default) which is normal for skills; there are no additional elevated privileges requested.
Assessment
This skill is an offline planning/advice template and appears internally consistent. Before you install or let an agent act on its recommendations: (1) understand this skill does not itself connect to ad accounts — any execution will require separate credentials and integration code, so avoid providing API keys or account credentials to the skill unless you intentionally wire it to a trusted connector; (2) clarify what the vendor/skill does with any "handoff payloads" if you later add an execution layer — require explicit endpoints and consent; (3) if you plan to let the agent run autonomously and execute changes in ad accounts, restrict that to a limited test account and audit all actions; (4) validate suggested strategies against your platform policies and legal/privacy requirements (PII, ad policy, billing); and (5) if you want stronger guarantees, prefer a skill that declares the exact integration method and required environment variables so you can review them before granting access.Like a lobster shell, security has layers — review code before you run it.
latestvk97450xgss715420gzbwachw618273s7
License
MIT-0
Free to use, modify, and redistribute. No attribution required.