JPeetz/agent-skills / skills/marketing/astra-campaign
astra-campaign
VerifiedUse this skill when the user needs a complete social media advertising campaign — not just ad copy, but full creative strategy with hooks, scripts, image/video prompts, and A/B test plans. Covers X, TikTok, and Instagram. Use when the user says things like "Create a campaign for..." "Launch ads for..." "I need marketing for..." "Promote this product" "Write ad creative for..." even if they don't mention specific platforms or "advertising department." For any product, brand, service, app launch, or crowdfunding campaign.
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 384 B |
| SKILL.md | skill md | 5.8 KB |
| evals/evals.json | config | 4.0 KB |
| references/corrections.md | markdown | 2.3 KB |
| scripts/claims_check.pyexecutable | script | 3.2 KB |
| scripts/validate_skill.pyexecutable | script | 3.0 KB |
scripts/claims_check.py
View on GitHub#!/usr/bin/env python3
# /// script
# dependencies = []
# ///
"""Campaign claims verifier. Flags unsubstantiated claims, regulated terms, policy risks."""
import re, json, sys
# Regulated terms that need special handling
REGULATED_TERMS = [
"guaranteed", "guarantee", "cure", "heal", "treat", "diagnose", "prevent",
"best", "fastest", "easiest", "#1", "number one", "world's best",
"100%", "zero risk", "risk-free", "risk free", "no risk",
"permanent", "instant", "immediate", "guaranteed results",
"FDA approved", "doctor recommended", "clinically proven",
]
# Phrases that indicate a claim needs evidence
CLAIM_PATTERNS = [
r"(\d+)% (of|more|less|faster|better|increase|decrease)",
r"save \$[\d,]+",
r"earn \$[\d,]+",
r"make \$[\d,]+",
r"(\d+)x (faster|better|more)",
r"(\d+),?000\+ (users|customers|downloads)",
r"(over|more than) (\d+),?000",
r"(\d+\.?\d*) star",
]
def check_claims(text: str) -> dict:
"""Check a piece of ad copy for potential issues."""
issues = []
suggestions = []
for term in REGULATED_TERMS:
if term.lower() in text.lower():
issues.append({
"type": "regulated_term",
"term": term,
"severity": "high",
"recommendation": f"Replace or substantiate '{term}' with verifiable source. If unverified, rewrite: e.g., 'trusted by thousands' instead of '#1'."
})
for pattern in CLAIM_PATTERNS:
for match in re.finditer(pattern, text, re.IGNORECASE):
issues.append({
"type": "unverified_claim",
"match": match.group(0),
"severity": "medium",
"recommendation": f"Cite specific source for '{match.group(0)}'. If no source exists, remove or rephrase as projection: 'aims to' or 'targeting'."
})
if "before" in text.lower() and "after" in text.lower():
issues.append({
"type": "before_after",
"severity": "medium",
"recommendation": "Before/after claims require typical results disclosure. Add: 'Individual results vary.' Or replace with testimonial format."
})
if re.search(r"limited time|act now|don't wait|only \d+ left|ending soon", text, re.IGNORECASE):
if not re.search(r"(while supplies last|limited availability|offer valid|expires)", text, re.IGNORECASE):
issues.append({
"type": "false_urgency",
"severity": "low",
"recommendation": "Urgency language detected without substantiation. Add real constraint (e.g., 'offer valid until [date]') or remove."
})
if not issues:
return {"status": "clean", "issues": []}
high = [i for i in issues if i["severity"] == "high"]
med = [i for i in issues if i["severity"] == "medium"]
low = [i for i in issues if i["severity"] == "low"]
return {
"status": "flagged",
"summary": f"{len(issues)} issues: {len(high)} high, {len(med)} medium, {len(low)} low",
"issues": issues,
}
if __name__ == "__main__":
if len(sys.argv) > 1:
text = sys.argv[1]
else:
text = sys.stdin.read()
result = check_claims(text)
print(json.dumps(result, indent=2))
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |