Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Dfw Content Calendar

v1.0.0

Generate 7- or 30-day social media calendars with hooks, body copy, CTAs, and hashtags tailored by niche, audience, and platform in JSON or CSV formats.

0· 87·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for drivenautoplex1/dfw-content-calendar.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Dfw Content Calendar" (drivenautoplex1/dfw-content-calendar) from ClawHub.
Skill page: https://clawhub.ai/drivenautoplex1/dfw-content-calendar
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install dfw-content-calendar

ClawHub CLI

Package manager switcher

npx clawhub@latest install dfw-content-calendar
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
high confidence
!
Purpose & Capability
The described purpose (social media content calendars) matches the included script and SKILL.md behavior. However, registry metadata says no required env vars/binaries while SKILL.md frontmatter declares ANTHROPIC_API_KEY and python3 as required. Requiring an Anthropic API key is reasonable for LLM-backed generation, but the registry/manifest mismatch is incoherent and should be corrected.
Instruction Scope
SKILL.md and generate_calendar.py stay on-scope: they produce calendar JSON/CSV and include a zero-cost --demo mode that makes no API calls. The script will call external LLM backends (Anthropic or a local proxy) when not in demo mode, meaning user content is sent to third-party services. There are no instructions to read unrelated system files or exfiltrate host data in the visible code.
!
Install Mechanism
The skill is listed as instruction-only in the registry, but SKILL.md includes an install section (kind: uv, package: anthropic). 'uv' is not a standard well-documented installer label here and is ambiguous. The code also uses openai for a local backend path but the install does not declare an openai dependency. The install spec is minimal and not a high-risk remote download, but the mismatch and unclear installer kind are concerning.
!
Credentials
SKILL.md declares ANTHROPIC_API_KEY as primaryEnv (appropriate for API-backed LLM usage). The registry metadata however lists no required env vars — an inconsistency. The code also reads LLM_BACKEND and can import openai/anthropic; those environment expectations (LLM_BACKEND, possible OpenAI/local keys) are not fully documented in the registry. Requesting an Anthropic key is proportionate for LLM use, but the missing/undocumented envs and unclear fallback behavior create risk if users supply credentials without understanding where data will be sent.
Persistence & Privilege
The skill does not request persistent elevated privileges; 'always' is false and there is no evidence it modifies other skills or system-wide agent settings. Autonomy (disable-model-invocation=false) is the platform default — noted but not by itself a red flag.
What to consider before installing
This skill appears to implement the content-calendar functionality and includes a safe zero-cost --demo mode, but there are several inconsistencies you should resolve before installing or supplying credentials: 1) The registry metadata claims no required env vars/binaries, but SKILL.md requires ANTHROPIC_API_KEY and python3 — verify which is correct. 2) The code can call Anthropic (and attempts a local OpenAI proxy path) but the install only lists an ambiguous 'uv' install for 'anthropic' and doesn't declare an openai dependency — ask the author how to install dependencies and whether OpenAI/local backends are supported. 3) If you plan to run non-demo mode, understand that content (and any prompts/data you provide) will be sent to a third-party LLM (Anthropic or a local proxy); do not send sensitive or private data unless you trust the endpoint and have confirmed which API key/backends will be used. 4) Prefer using --demo for evaluation (zero API calls). 5) Ask the publisher to fix the registry metadata to list required env vars and install steps explicitly, and to clarify the 'uv' install kind and any other runtime environment variables (e.g., LLM_BACKEND).

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

latestvk97916mwfbh2635agx5fahrvrn83rq23
87downloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

Content Calendar Skill

Generate a full month of social content in minutes. Paste in your niche and audience — get back a structured, ready-to-schedule calendar with varied hooks, body copy, CTAs, and hashtags.

Free vs Premium

Free tier (no API key needed):

  • --demo — generates a complete 7-day real estate sample calendar, zero API calls
  • --version — print skill version
  • --compliance-only — check any copy for forbidden words before posting

Free tier (API key required):

  • 7-day calendar on any platform/niche
  • Structured JSON + human-readable output
  • Single platform per run

Premium features (same API key, no upgrade needed):

  • --days=30 — full 30-day calendars
  • --platforms=all — LinkedIn + X + Facebook + Instagram in one run
  • --ab-variants — 2 hook variants per post for A/B testing
  • --csv — export to CSV for Buffer, Hootsuite, Notion, or any scheduler
  • --theme — weekly theme override (e.g., "Week 2: objection busting only")

What this skill does

Generates structured content calendars for any niche with:

  • Variety enforcement — topics rotate so nothing repeats within 7 days
  • Platform-aware formatting — character limits, hashtag counts, and tone matched per platform
  • Content mix — market education, social proof, objection busting, community spotlight, CTAs (5-pillar rotation)
  • Hook-first structure — every post opens with a pattern interrupt, not a topic statement
  • JSON + human-readable output — paste JSON into your scheduler; read the human format to review quickly

Supported verticals

NicheExample brand voice
Real estateMarket urgency, local expertise, lifestyle
Mortgage / lendingEducation-first, trust-building, compliance-safe
Crypto / DeFiData-driven, opportunity framing, risk-aware
SaaS / techProblem-solution, feature → benefit, ROI focus
E-commerceProduct-led, social proof heavy, seasonal hooks
Coaching / consultingAuthority positioning, transformation stories
Healthcare / wellnessEmpathy-first, outcome-focused, evidence-backed
Any nichePass --niche="your niche" and --audience="your audience"

Input contract

# Minimum — niche and audience
python3 generate_calendar.py --niche="DFW real estate" --audience="first-time buyers"

# Full options
python3 generate_calendar.py \
  --niche="DFW mortgage broker" \
  --audience="move-up buyers" \
  --platform=linkedin \
  --days=30 \
  --tone=educational \
  --ab-variants \
  --csv \
  --output=my_calendar.json

Options:

FlagDefaultDescription
--nicherequiredYour brand/industry (e.g. "DFW real estate agent")
--audience"general"Target reader (e.g. "first-time homebuyers")
--platformlinkedinlinkedin / x / facebook / instagram / all
--days77 or 30
--toneconversationalconversational / educational / urgent / luxury / bold
--ab-variantsoffGenerate 2 hook options per post
--csvoffExport calendar as CSV
--themeautoWeekly theme override
--demooffRun on built-in sample, zero API calls
--versionoffPrint version
--formathumanhuman / json

Output contract

Human-readable output:

=== 30-Day LinkedIn Calendar: DFW Mortgage Broker → Move-Up Buyers ===

Week 1 Theme: Market Reality

--- Day 1 (Mon) | LinkedIn | Market Education ---
HOOK: Most DFW move-up buyers don't realize they already have the equity to do this.
BODY: If you bought your home 3-5 years ago, you're sitting on an average of $87,000 in
      equity. That's your down payment for the next place — without touching savings.
      The math most people don't run: sell at today's prices, buy at today's prices,
      and the equity gap covers the difference more than you think.
CTA:  Drop your zip code below — I'll run the numbers for your neighborhood.
HASHTAGS: #DFWRealEstate #HomeEquity #MovingUp #DFWHomes
CHARS: 487

JSON output (--format=json):

{
  "metadata": {
    "niche": "DFW Mortgage Broker",
    "audience": "Move-up buyers",
    "platform": "linkedin",
    "days": 30,
    "generated_at": "2026-03-27T17:00:00Z"
  },
  "weeks": [
    {
      "week": 1,
      "theme": "Market Reality",
      "posts": [
        {
          "day": 1,
          "weekday": "Mon",
          "platform": "linkedin",
          "content_type": "market_education",
          "hook": "Most DFW move-up buyers don't realize they already have the equity to do this.",
          "body": "...",
          "cta": "Drop your zip code below — I'll run the numbers for your neighborhood.",
          "hashtags": ["#DFWRealEstate", "#HomeEquity", "#MovingUp", "#DFWHomes"],
          "char_count": 487,
          "hook_b": null
        }
      ]
    }
  ]
}

CSV output (--csv, compatible with Buffer/Hootsuite/Notion):

day,weekday,platform,hook,body,cta,hashtags,char_count
1,Mon,linkedin,"Most DFW move-up buyers...","If you bought your home...","Drop your zip code...","#DFWRealEstate #HomeEquity",487

How the skill works

Uses generate_calendar.py in this directory. Local MLX first (free, unlimited), Haiku fallback.

CONTENT_MIX = {
    "market_education": 0.25,   # Stats, trends, myth-busting
    "social_proof":     0.20,   # Client outcomes, testimonials
    "objection_bust":   0.20,   # Handle common objections
    "community":        0.15,   # Local spotlight, brand building
    "direct_cta":       0.20,   # Urgency-driven asks
}

WEEK_THEMES = [
    "Market Reality",       # Week 1 — establish authority with facts
    "Social Proof",         # Week 2 — build trust with outcomes
    "Education",            # Week 3 — deepen value with expertise
    "Urgency & Action",     # Week 4 — close with timing
]

PLATFORM_LIMITS = {
    "linkedin":  {"chars": 3000, "hashtags": 5,  "tone": "professional"},
    "x":         {"chars": 280,  "hashtags": 2,  "tone": "punchy"},
    "facebook":  {"chars": 500,  "hashtags": 3,  "tone": "community"},
    "instagram": {"chars": 300,  "hashtags": 10, "tone": "visual-first"},
}

Core generation prompt:

CALENDAR_SYSTEM = """You are a social media strategist and direct-response copywriter.
Generate {days} days of {platform} content for: {niche} targeting {audience}.

Rules:
- Hook first: every post opens with a pattern interrupt — a question, stat, or bold claim
- No topic repeats within 7 days
- Match platform tone: {platform_tone}
- Content mix: 25% education, 20% social proof, 20% objection handling, 15% community, 20% CTA
- Week themes: {week_themes}
- Keep under {char_limit} characters per post
- {tone_instruction}
- Never use: [forbidden words for niche]

Output ONLY valid JSON matching the schema provided."""

Usage patterns

Patrick's 2-hour content schedule method:

# Step 1: Generate 30-day calendar
python3 generate_calendar.py --niche="DFW mortgage broker" --audience="move-up buyers" \
  --platform=linkedin --days=30 --csv --output=calendar_march.csv

# Step 2: Review and approve in CSV (Buffer, Hootsuite, Notion)
# Step 3: Schedule — done in 10 minutes

Multi-platform week:

# All 4 platforms, 7 days, A/B hooks
python3 generate_calendar.py --niche="DFW real estate" --audience="first-time buyers" \
  --platform=all --days=7 --ab-variants

Crypto trading content:

python3 generate_calendar.py --niche="crypto trader + DeFi analyst" \
  --audience="retail investors" --platform=x --days=30 --tone=bold

Pipeline (JSON → scheduler automation):

python3 generate_calendar.py --niche="SaaS startup" --audience="SMB owners" \
  --format=json | jq '.weeks[0].posts[] | {day, hook, cta}'

Integration with agent infrastructure

# Via Telegram
@openclaw content-calendar "30-day LinkedIn calendar for DFW mortgage broker targeting move-up buyers"
@openclaw content-calendar "7-day X calendar, crypto niche, bold tone"

# Via Claude Code
openclaw run content-calendar --niche="real estate" --days=30 --platform=linkedin

Content pillar reference

Pillar% of calendarWhat it doesExample hook
Market Education25%Build authority with facts"Most DFW buyers don't know this costs them $340/month"
Social Proof20%Build trust with outcomes"Client bought in Frisco with $0 out of pocket. Here's how."
Objection Busting20%Remove buying resistance"Waiting for rates to drop? Here's what that's actually costing you."
Community15%Brand affinity, local presence"Best kept secret neighborhood in McKinney right now"
Direct CTA20%Drive action"Drop your zip code — I'll pull what's moving in your area today."

Comments

Loading comments...