production-data-patch

Production Data Patch — Backend Department

You are responsible for safely modifying production data on Your Project's SQLite database via Fly SSH.

Before Starting

Check:

• Is Fly SSH tunnel available? ~/.fly/bin/fly ssh console -a your-project -C 'echo ok'
• What exactly needs changing? (Get specific slugs, values, columns from Master)
• Is this a single fix or a bulk operation?
• Has Master/S&QA approved this change?

How This Skill Works

Mode 1: Single Tool Fix

Update one or a few specific tools — install_command, description, name, etc.

Mode 2: Bulk Data Push

Push autopsy data (migration_paths, verified_combos) from local to production.

Mode 3: Query & Report

Read-only queries to check analytics, find targets, or audit data quality.

Access Pattern

~/.fly/bin/fly ssh console -a your-project -C 'python3 -c "
import sqlite3
conn = sqlite3.connect(\"/data/your-project.db\")
conn.execute(\"PRAGMA journal_mode=WAL\")
# ... queries here ...
conn.commit()
conn.close()
"'

CRITICAL: aiosqlite Row Access

ALWAYS use column name access, NEVER integer indexing:

# BAD — causes silent bugs
row[0], row[1], row[2]

# GOOD — explicit column names
row["slug"], row["name"], row["count"]

This has caused production bugs TWICE. Always use SELECT ... as alias and row["alias"].

Common Operations

Update a tool

UPDATE tools SET install_command = 'npm install X' WHERE slug = 'tool-slug';

Verify after update

SELECT slug, install_command FROM tools WHERE slug = 'tool-slug';

Bulk push (autopsy data)

# Generate SQL locally, pipe via SSH
cat /tmp/data.sql | ~/.fly/bin/fly ssh console -a your-project -C 'python3 -c "
import sys, sqlite3
conn = sqlite3.connect(\"/data/your-project.db\")
conn.execute(\"PRAGMA journal_mode=WAL\")
sql = sys.stdin.read()
stmts = [s.strip() for s in sql.split(\";\") if s.strip()]
for s in stmts:
    try: conn.execute(s)
    except: pass
conn.commit()
conn.close()
"'