菜单
Safely update data on the production Your Project database via Fly SSH. Use when fixing tool metadata, pushing autopsy data, or running DB queries on prod.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Translate git history and orchestrator logs into authentic social content. Use when turning recent technical work into tweets, Dev.to posts, or changelog entries without manual summarisation.
Red team the staging environment with injection attacks, rate limit probes, and auth bypass attempts. Use before major releases or when adding new user-input surfaces.
Deploy Your Project to production safely. Use before any deployment, after code changes, or when asked to push to prod.
Facilitate a structured CONVERSATIONAL meeting between department agents via claude-peers — named phases (Diverge, Clarify, Challenge, Build, Stress Test, Converge, Decide) with state machine navigation. Agents push back on each other and build on each other's ideas. Minimum path: Diverge → Challenge → Build → Stress Test. Early exit only after Stress Test. NOT for simple task dispatch (use orchestra-management). NOT for solo research (use rd-architect).
Manage the 6-department orchestra via claude-peers. Use when dispatching tasks, coordinating departments, reviewing results, or shaping department behavior.
Write emails, social posts, and newsletter submissions for Your Project. Use when creating maker outreach, blog content, social media posts, or press pitches.
| name | production-data-patch |
| description | Safely update data on the production Your Project database via Fly SSH. Use when fixing tool metadata, pushing autopsy data, or running DB queries on prod. |
| metadata | {"version":"2.0.0","author":"Master Agent","category":"operations","updated":"2026-03-31T00:00:00.000Z"} |
You are responsible for safely modifying production data on Your Project's SQLite database via Fly SSH.
Check:
~/.fly/bin/fly ssh console -a your-project -C 'echo ok'Update one or a few specific tools — install_command, description, name, etc.
Push autopsy data (migration_paths, verified_combos) from local to production.
Read-only queries to check analytics, find targets, or audit data quality.
~/.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()
"'
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"].
UPDATE tools SET install_command = 'npm install X' WHERE slug = 'tool-slug';
SELECT slug, install_command FROM tools WHERE slug = 'tool-slug';
# 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()
"'
SELECT slug, name, github_stars FROM tools
WHERE status='approved' AND maker_id IS NULL AND github_stars > 1000
ORDER BY github_stars DESC LIMIT 20;
| Request | Deliverable |
|---|---|
| "Fix tool X" | Confirmation with before/after values |
| "Push autopsy data" | Row counts: N migrations, N combos pushed |
| "Find outreach targets" | slug, name, stars, email list |
| "Check analytics" | Claim token counts, page views, signup counts |
PRAGMA journal_mode=WAL should be set before bulk writes