Data Processing

#!/usr/bin/env -S ai --haiku
Analyze the JSON data provided on stdin.
Summarize key metrics and flag any anomalies.

cat metrics.json | ./analyze.md

{
  "date": "2026-03-03",
  "users": 1500,
  "revenue": 45000,
  "signups": 120,
  "churn": 8,
  "response_times_ms": [120, 150, 890, 130, 125]
}

Metrics Summary for 2026-03-03:
- Active users: 1,500
- Revenue: $45,000 ($30/user)
- Growth: 120 signups, 8 churn (93.3% retention)

Anomaly Detected:
- Response time spike: 890ms (7x normal)
- Other requests: 120-150ms (healthy)
- Action: Investigate slow query/endpoint

#!/usr/bin/env -S ai --haiku
Convert the JSON data on stdin to CSV format.
Include all fields as columns.

cat data.json | ./json-to-csv.md > data.csv

#!/usr/bin/env -S ai --haiku
The stdin contains JSON with an array of transactions.
Filter for transactions > $1000.
Output: total count and sum.

cat transactions.json | ./filter-sum.md
# Output: 47 transactions totaling $87,340

# Extract → Analyze → Format pipeline
./extract-data.md | ./analyze.md | ./format-report.md > report.txt

#!/usr/bin/env -S ai --haiku --skip
Read metrics.json and output only:
- users
- revenue  
- signups
- churn

Format as CSV (no headers).

#!/usr/bin/env -S ai --haiku
The stdin contains CSV: users,revenue,signups,churn

Calculate:
- Revenue per user
- Retention rate
- Growth rate

Output: One line summary.

#!/usr/bin/env -S ai --haiku
Format the analysis from stdin as a professional email to executives.
Keep it under 3 paragraphs.

#!/bin/bash
# process-all.sh

for file in data/*.json; do
    cat "$file" | ./analyze.md > "results/$(basename "$file" .json).txt" &
done

wait
echo "Processed $(ls results/ | wc -l) files"

#!/usr/bin/env -S ai --haiku
Analyze the API response on stdin (JSON format):

1. Response structure validity
2. Expected fields present?
3. Data types correct?
4. Any error indicators?
5. Performance metrics (if present)

Output: VALID or INVALID with explanation.

# Test API endpoint
curl -s https://api.example.com/v1/users | ./validate-response.md

#!/usr/bin/env -S ai --sonnet
Analyze the nginx access logs on stdin:

1. Request volume and patterns
2. Top 10 endpoints by traffic
3. Error rate (4xx, 5xx)
4. Response time distribution
5. Unusual patterns or potential attacks

Focus on actionable insights.

tail -1000 /var/log/nginx/access.log | ./analyze-logs.md

#!/usr/bin/env -S ai --haiku
Analyze the database query results on stdin (CSV format).

Identify:
- Trends in the data
- Outliers
- Missing or null values
- Data quality issues

Suggest next steps for data cleanup.

psql -d mydb -c "SELECT * FROM metrics WHERE date > NOW() - INTERVAL '7 days'" \
  --csv | ./analyze-db-results.md

#!/usr/bin/env -S ai --haiku
Analyze the git commit history on stdin:

1. Most active areas of the codebase
2. Commit message quality
3. Commit frequency patterns
4. Authors and contribution patterns
5. Any concerning trends?

git log --oneline --numstat -100 | ./analyze-commits.md

#!/usr/bin/env -S ai --haiku
Convert the JSON array on stdin to a Markdown table.
Auto-detect columns from the first object.
Format numbers with proper separators.

cat users.json | ./json-to-table.md > users-table.md

[
  {"name": "Alice", "sales": 45000, "region": "West"},
  {"name": "Bob", "sales": 38000, "region": "East"}
]

| Name  | Sales   | Region |
|-------|---------|--------|
| Alice | 45,000  | West   |
| Bob   | 38,000  | East   |

#!/usr/bin/env -S ai --haiku
Clean the CSV data on stdin:

1. Remove duplicate rows
2. Fix inconsistent formatting
3. Handle missing values (use "N/A")
4. Standardize date formats to YYYY-MM-DD
5. Trim whitespace

Output: Cleaned CSV.

cat messy-data.csv | ./clean-csv.md > clean-data.csv

#!/usr/bin/env -S ai --sonnet
Enrich the user data on stdin (CSV).

For each row:
1. Read: user_id, email, signup_date
2. Infer: likely timezone from email domain
3. Calculate: days since signup
4. Determine: user lifecycle stage (new/active/at-risk)

Output: Enriched CSV with new columns.

cat users.csv | ./enrich-users.md > users-enriched.csv

#!/usr/bin/env -S ai --sonnet
Detect anomalies in the time-series data on stdin (CSV).

Columns: timestamp, value

Use statistical methods:
- 3-sigma rule for outliers
- Moving average for trend
- Sudden spikes or drops

Output: CSV with only anomalous rows + explanation column.

cat timeseries.csv | ./detect-anomalies.md > anomalies.csv

#!/bin/bash
# process-large-file.sh

# Process 1000 lines at a time
split -l 1000 large-file.csv chunks/chunk-

for chunk in chunks/chunk-*; do
    cat "$chunk" | ./analyze.md >> results.txt
    rm "$chunk"
done

echo "Processing complete"

#!/usr/bin/env -S ai --sonnet --live
Analyze the log stream on stdin.

Print a summary every 100 lines:
- Error count
- Warning count
- Unusual patterns

Continue until EOF.

tail -f /var/log/app.log | ./stream-analyze.md

#!/bin/bash
# aggregate-sources.sh

# Fetch from multiple sources
curl -s https://api1.example.com/metrics > /tmp/source1.json &
curl -s https://api2.example.com/stats > /tmp/source2.json &
wait

# Combine and analyze
jq -s '.[0] + .[1]' /tmp/source1.json /tmp/source2.json | \
    ./analyze-combined.md > report.txt

#!/bin/bash
# process-with-retry.sh

MAX_RETRIES=3
RETRY=0

while [ $RETRY -lt $MAX_RETRIES ]; do
    if cat data.json | ./process.md > output.txt 2>error.log; then
        echo "Success"
        exit 0
    fi
    
    RETRY=$((RETRY + 1))
    echo "Attempt $RETRY failed, retrying..."
    sleep 2
done

echo "Failed after $MAX_RETRIES attempts"
exit 1

# .github/workflows/daily-metrics.yml
name: Daily Metrics Analysis
on:
  schedule:
    - cron: '0 1 * * *'  # 1 AM daily

jobs:
  analyze:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      
      - name: Install AIRun
        run: |
          curl -fsSL https://claude.ai/install.sh | bash
          git clone https://github.com/andisearch/airun.git
          cd airun && ./setup.sh
      
      - name: Fetch and analyze metrics
        run: |
          curl -s https://api.example.com/daily-metrics | \
            ai --apikey --haiku << 'EOF' > daily-report.md
          Analyze the daily metrics JSON on stdin.
          Compare to typical values.
          Flag any anomalies.
          EOF
        env:
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
      
      - name: Email report
        uses: dawidd6/action-send-mail@v3
        with:
          server_address: smtp.gmail.com
          server_port: 465
          username: ${{ secrets.MAIL_USERNAME }}
          password: ${{ secrets.MAIL_PASSWORD }}
          subject: Daily Metrics Report
          body: file://daily-report.md
          to: team@example.com

#!/bin/bash
# process-s3-data.sh

# Download from S3
aws s3 cp s3://my-bucket/data/latest.json - | \
    ai --apikey --haiku --skip << 'EOF' > summary.txt
Analyze the JSON data on stdin.
Generate a one-paragraph summary.
EOF

# Upload results
aws s3 cp summary.txt s3://my-bucket/reports/$(date +%Y%m%d).txt

# Cheap: Simple format conversion
cat data.json | ai --haiku json-to-csv.md

# Balanced: Anomaly detection
cat metrics.csv | ai --sonnet detect-anomalies.md

# Expensive: Complex statistical analysis
cat dataset.csv | ai --opus deep-analysis.md

#!/usr/bin/env -S ai --haiku --skip
Analyze all JSON files in data/ directory.

For each file:
1. Read contents
2. Extract key metrics
3. One-line summary

Output: Markdown list of summaries.

./analyze-all.md > summary.md

#!/bin/bash
# monitored-pipeline.sh

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

log "Starting data processing pipeline"

log "Stage 1: Extract data"
if ! ./extract.md > stage1.json 2>>pipeline.log; then
    log "ERROR: Stage 1 failed"
    exit 1
fi

log "Stage 2: Transform data"
if ! cat stage1.json | ./transform.md > stage2.csv 2>>pipeline.log; then
    log "ERROR: Stage 2 failed"
    exit 1
fi

log "Stage 3: Generate report"
if ! cat stage2.csv | ./report.md > final-report.md 2>>pipeline.log; then
    log "ERROR: Stage 3 failed"
    exit 1
fi

log "Pipeline complete: final-report.md"

#!/usr/bin/env -S ai --haiku
Validate the data pipeline output on stdin (JSON).

Checks:
1. Valid JSON structure
2. Required fields present: [timestamp, value, status]
3. No null values
4. Timestamp in ISO 8601 format
5. Status in [active, pending, completed]

Output: PASS or FAIL with specific issues.

cat output.json | ./validate.md || echo "Pipeline validation failed!"

# Check each stage
cat input.json | tee /dev/stderr | ./process.md | tee /dev/stderr > output.txt

./stage1.md > stage1.out
cat stage1.out | ./stage2.md > stage2.out
cat stage2.out | ./stage3.md > final.out

export LC_ALL=en_US.UTF-8
cat data.json | ./process.md > output.txt