Ai Automation Workflows

Build automated AI workflows combining multiple models and services. Patterns: batch processing, scheduled tasks, event-driven pipelines, agent loops. Tools:...

Security Scan

The skill's instructions mostly match its stated purpose (automating model pipelines) but contain a risky install pattern (curl | sh from a third‑party domain), a small mismatch between declared requirements and runtime actions (it tells users to log in but declares no credentials), and persistent/privileged operations (cron, writing to /var/log) that deserve scrutiny.

Purpose & Capability

The skill claims to build AI automation pipelines and the SKILL.md shows concrete Bash patterns using the inference.sh (infsh) CLI — this is coherent. Minor inconsistency: the header mentions 'Python SDK' and 'webhook integration' but the documented examples are only Bash/infsh; that's plausible but worth noting as a documentation mismatch.

Instruction Scope

The runtime instructions tell users to run 'curl -fsSL https://cli.inference.sh | sh' (execute a remote install script) and to run 'infsh login'. Executing a remote install script without manual verification is a high-risk instruction even though the doc points to a checksums page; the Quick Start uses the piped installer by default. The instructions also show creating cron jobs and writing logs to /var/log and an /output directory, which require appropriate filesystem permissions. The SKILL.md does not instruct the agent to read unrelated system files or secret env vars, but it does rely on interactive login to an external service that will generate local credentials.

Install Mechanism

There is no registry install spec, but the SKILL.md instructs installing a CLI via a remote script from cli.inference.sh which downloads binaries from dist.inference.sh. While the doc references SHA-256 checksums, the provided quick-start uses a direct 'curl | sh' pipeline (runs code from the network immediately). This pattern is higher risk than a package manager or verified release install because it executes remote code by default; the domains are service-specific (not a well-known central repo) which increases the need for manual verification.

Credentials

The registry metadata lists no required env vars or primary credential, but the instructions require running 'infsh login' (i.e., authenticating to the inference.sh service) and call models across different providers via the infsh CLI. The absence of declared credential variables in the metadata is a mild inconsistency: the skill relies on external service auth but does not declare what secrets will be used or where they will be stored.

Persistence & Privilege

The skill is not marked 'always' and is user-invocable (normal). The examples guide users to create cron entries and write to /var/log and /output, which are persistence actions that require filesystem permissions; the skill itself does not request elevated privileges in metadata, but following the examples could require sudo or privileged access depending on paths chosen. No instructions suggest modifying other skills or system configs beyond user cron/log files.

What to consider before installing

This skill appears to do what it says (build automation using the inference.sh CLI) but take precautions before installing or running examples: 1) Avoid blindly running 'curl | sh' — fetch the installer, verify the SHA-256 checksums against the listed checksums, and review the install script before executing. 2) Confirm where 'infsh login' stores credentials and whether those credentials grant access to other services; prefer using service-scoped API keys rather than broad accounts. 3) When creating cron jobs or logs, use directories you control (avoid writing to /var/log unless you understand permissions and implications). 4) Because the registry metadata doesn't declare required credentials, ask the publisher (or inspect the service docs) about what auth/account is required and what data is sent to inference.sh. 5) If you need stronger assurance, request the skill's source/homepage or prefer installing the CLI from a package manager or a verified release tarball you inspect first.

Build automated AI workflows via inference.sh CLI.

Quick Start

curl -fsSL https://cli.inference.sh | sh && infsh login

# Simple automation: Generate daily image
infsh app run falai/flux-dev --input '{
  "prompt": "Inspirational quote background, minimalist design, date: '"$(date +%Y-%m-%d)"'"
}'

Install note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.

Automation Patterns

Pattern 1: Batch Processing

Process multiple items with the same workflow.

#!/bin/bash
# batch_images.sh - Generate images for multiple prompts

PROMPTS=(
  "Mountain landscape at sunrise"
  "Ocean waves at sunset"
  "Forest path in autumn"
  "Desert dunes at night"
)

for prompt in "${PROMPTS[@]}"; do
  echo "Generating: $prompt"
  infsh app run falai/flux-dev --input "{
    \"prompt\": \"$prompt, professional photography, 4K\"
  }" > "output_${prompt// /_}.json"
  sleep 2  # Rate limiting
done

Pattern 2: Sequential Pipeline

Chain multiple AI operations.

#!/bin/bash
# content_pipeline.sh - Full content creation pipeline

TOPIC="AI in healthcare"

# Step 1: Research
echo "Researching..."
RESEARCH=$(infsh app run tavily/search-assistant --input "{
  \"query\": \"$TOPIC latest developments\"
}")

# Step 2: Write article
echo "Writing article..."
ARTICLE=$(infsh app run openrouter/claude-sonnet-45 --input "{
  \"prompt\": \"Write a 500-word blog post about $TOPIC based on: $RESEARCH\"
}")

# Step 3: Generate image
echo "Generating image..."
IMAGE=$(infsh app run falai/flux-dev --input "{
  \"prompt\": \"Blog header image for article about $TOPIC, modern, professional\"
}")

# Step 4: Generate social post
echo "Creating social post..."
SOCIAL=$(infsh app run openrouter/claude-haiku-45 --input "{
  \"prompt\": \"Write a Twitter thread (5 tweets) summarizing: $ARTICLE\"
}")

echo "Pipeline complete!"

Pattern 3: Parallel Processing

Run multiple operations simultaneously.

#!/bin/bash
# parallel_generation.sh - Generate multiple assets in parallel

# Start all jobs in background
infsh app run falai/flux-dev --input '{"prompt": "Hero image..."}' > hero.json &
PID1=$!

infsh app run falai/flux-dev --input '{"prompt": "Feature image 1..."}' > feature1.json &
PID2=$!

infsh app run falai/flux-dev --input '{"prompt": "Feature image 2..."}' > feature2.json &
PID3=$!

# Wait for all to complete
wait $PID1 $PID2 $PID3
echo "All images generated!"

Pattern 4: Conditional Workflow

Branch based on results.

#!/bin/bash
# conditional_workflow.sh - Process based on content analysis

INPUT_TEXT="$1"

# Analyze content
ANALYSIS=$(infsh app run openrouter/claude-haiku-45 --input "{
  \"prompt\": \"Classify this text as: positive, negative, or neutral. Return only the classification.\n\n$INPUT_TEXT\"
}")

# Branch based on result
case "$ANALYSIS" in
  *positive*)
    echo "Generating celebration image..."
    infsh app run falai/flux-dev --input '{"prompt": "Celebration, success, happy"}'
    ;;
  *negative*)
    echo "Generating supportive message..."
    infsh app run openrouter/claude-sonnet-45 --input "{
      \"prompt\": \"Write a supportive, encouraging response to: $INPUT_TEXT\"
    }"
    ;;
  *)
    echo "Generating neutral acknowledgment..."
    ;;
esac

Pattern 5: Retry with Fallback

Handle failures gracefully.

#!/bin/bash
# retry_workflow.sh - Retry failed operations

generate_with_retry() {
  local prompt="$1"
  local max_attempts=3
  local attempt=1

  while [ $attempt -le $max_attempts ]; do
    echo "Attempt $attempt..."

    result=$(infsh app run falai/flux-dev --input "{\"prompt\": \"$prompt\"}" 2>&1)

    if [ $? -eq 0 ]; then
      echo "$result"
      return 0
    fi

    echo "Failed, retrying..."
    ((attempt++))
    sleep $((attempt * 2))  # Exponential backoff
  done

  # Fallback to different model
  echo "Falling back to alternative model..."
  infsh app run google/imagen-3 --input "{\"prompt\": \"$prompt\"}"
}

generate_with_retry "A beautiful sunset over mountains"

Scheduled Automation

Cron Job Setup

# Edit crontab
crontab -e

# Daily content generation at 9 AM
0 9 * * * /path/to/daily_content.sh >> /var/log/ai-automation.log 2>&1

# Weekly report every Monday at 8 AM
0 8 * * 1 /path/to/weekly_report.sh >> /var/log/ai-automation.log 2>&1

# Every 6 hours: social media content
0 */6 * * * /path/to/social_content.sh >> /var/log/ai-automation.log 2>&1

Daily Content Script

#!/bin/bash
# daily_content.sh - Run daily at 9 AM

DATE=$(date +%Y-%m-%d)
OUTPUT_DIR="/output/$DATE"
mkdir -p "$OUTPUT_DIR"

# Generate daily quote image
infsh app run falai/flux-dev --input '{
  "prompt": "Motivational quote background, minimalist, morning vibes"
}' > "$OUTPUT_DIR/quote_image.json"

# Generate daily tip
infsh app run openrouter/claude-haiku-45 --input '{
  "prompt": "Give me one actionable productivity tip for today. Be concise."
}' > "$OUTPUT_DIR/daily_tip.json"

# Post to social (optional)
# infsh app run twitter/post-tweet --input "{...}"

echo "Daily content generated: $DATE"

Monitoring and Logging

Logging Wrapper

#!/bin/bash
# logged_workflow.sh - With comprehensive logging

LOG_FILE="/var/log/ai-workflow-$(date +%Y%m%d).log"

log() {
  echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1" | tee -a "$LOG_FILE"
}

log "Starting workflow"

# Track execution time
START_TIME=$(date +%s)

# Run workflow
log "Generating image..."
RESULT=$(infsh app run falai/flux-dev --input '{"prompt": "test"}' 2>&1)
STATUS=$?

if [ $STATUS -eq 0 ]; then
  log "Success: Image generated"
else
  log "Error: $RESULT"
fi

END_TIME=$(date +%s)
DURATION=$((END_TIME - START_TIME))
log "Completed in ${DURATION}s"

Error Alerting

#!/bin/bash
# monitored_workflow.sh - With error alerts

run_with_alert() {
  local result
  result=$("$@" 2>&1)
  local status=$?

  if [ $status -ne 0 ]; then
    # Send alert (webhook, email, etc.)
    curl -X POST "https://your-webhook.com/alert" \
      -H "Content-Type: application/json" \
      -d "{\"error\": \"$result\", \"command\": \"$*\"}"
  fi

  echo "$result"
  return $status
}

run_with_alert infsh app run falai/flux-dev --input '{"prompt": "test"}'

Python SDK Automation

#!/usr/bin/env python3
# automation.py - Python-based workflow

import subprocess
import json
from datetime import datetime
from pathlib import Path

def run_infsh(app_id: str, input_data: dict) -> dict:
    """Run inference.sh app and return result."""
    result = subprocess.run(
        ["infsh", "app", "run", app_id, "--input", json.dumps(input_data)],
        capture_output=True,
        text=True
    )
    return json.loads(result.stdout) if result.returncode == 0 else None

def daily_content_pipeline():
    """Generate daily content."""
    date_str = datetime.now().strftime("%Y-%m-%d")
    output_dir = Path(f"output/{date_str}")
    output_dir.mkdir(parents=True, exist_ok=True)

    # Generate image
    image = run_infsh("falai/flux-dev", {
        "prompt": f"Daily inspiration for {date_str}, beautiful, uplifting"
    })
    (output_dir / "image.json").write_text(json.dumps(image))

    # Generate caption
    caption = run_infsh("openrouter/claude-haiku-45", {
        "prompt": "Write an inspiring caption for a daily motivation post. 2-3 sentences."
    })
    (output_dir / "caption.json").write_text(json.dumps(caption))

    print(f"Generated content for {date_str}")

if __name__ == "__main__":
    daily_content_pipeline()

Workflow Templates

Content Calendar Automation

#!/bin/bash
# content_calendar.sh - Generate week of content

TOPICS=("productivity" "wellness" "technology" "creativity" "leadership")
DAYS=("Monday" "Tuesday" "Wednesday" "Thursday" "Friday")

for i in "${!DAYS[@]}"; do
  DAY=${DAYS[$i]}
  TOPIC=${TOPICS[$i]}

  echo "Generating $DAY content about $TOPIC..."

  # Image
  infsh app run falai/flux-dev --input "{
    \"prompt\": \"$TOPIC theme, $DAY motivation, social media style\"
  }" > "content/${DAY}_image.json"

  # Caption
  infsh app run openrouter/claude-haiku-45 --input "{
    \"prompt\": \"Write a $DAY motivation post about $TOPIC. Include hashtags.\"
  }" > "content/${DAY}_caption.json"
done

Data Processing Pipeline

#!/bin/bash
# data_processing.sh - Process and analyze data files

INPUT_DIR="./data/raw"
OUTPUT_DIR="./data/processed"

for file in "$INPUT_DIR"/*.txt; do
  filename=$(basename "$file" .txt)

  # Analyze content
  infsh app run openrouter/claude-haiku-45 --input "{
    \"prompt\": \"Analyze this data and provide key insights in JSON format: $(cat $file)\"
  }" > "$OUTPUT_DIR/${filename}_analysis.json"

done

Best Practices

1. Rate limiting - Add delays between API calls
2. Error handling - Always check return codes
3. Logging - Track all operations
4. Idempotency - Design for safe re-runs
5. Monitoring - Alert on failures
6. Backups - Save intermediate results
7. Timeouts - Set reasonable limits

Related Skills

# Content pipelines
npx skills add inference-sh/skills@ai-content-pipeline

# RAG pipelines
npx skills add inference-sh/skills@ai-rag-pipeline

# Social media automation
npx skills add inference-sh/skills@ai-social-media-content

# Full platform skill
npx skills add inference-sh/skills@inference-sh

Browse all apps: infsh app list