ClawHub

Ad Budget Rebalancer

v1.0.0

Analyze ecommerce ad spend notes across Meta Ads, Google Ads, TikTok Ads, Amazon Sponsored, and Xiaohongshu promotional feeds, then recommend budget realloca...

⭐ 0· 49·0 current·0 all-time
byhaidong@harrylabsj
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
CryptoCan make purchases
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the implementation: handler.py parses user-provided spend notes, scores channels/campaigns with built-in heuristics, and renders a markdown brief. No unrelated credentials, binaries, or external services are requested.
✓
Instruction Scope
SKILL.md explicitly limits the skill to user-provided data and disclaims live API access. The runtime code follows that constraint (string parsing, heuristic defaults, no network calls or file reads beyond stdin/argv). Instructions do not ask the agent to read unrelated system state or exfiltrate data.
✓
Install Mechanism
No install spec; this is instruction-only with included Python files. No downloads, package installs, or archive extraction are performed.
✓
Credentials
No environment variables, credentials, or config paths are required or accessed. The handler uses only its input argument/stdin and built-in defaults.
✓
Persistence & Privilege
The skill does not request persistent presence (always: false), does not modify system or other skills' configs, and does not perform autonomous privileged actions beyond rendering recommendations.
Assessment
This skill appears internally consistent and safe: it uses only the user's provided notes, applies built-in heuristics, and outputs a markdown brief. Before using recommendations to change live budgets, verify all input numbers (spend, conversions, revenue) and any platform-specific ROAS assumptions—the skill uses default ROAS/CPM values and fallback channel lists when inputs are partial. Treat outputs as advisory (the SKILL.md emphasizes human approval) and avoid automating budget changes directly from this skill. If you need auditability, supply full spend and revenue data rather than short notes so the recommendations are less dependent on defaults.

Like a lobster shell, security has layers — review code before you run it.

latestvk974ny6hcr7fc1422sakh0vmb984ryv6

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments