safe-write-operations

Solid

Reference — rules for safely executing write/destructive operations against ad accounts. Always loaded into the performance-marketer agent.

AI & Automation 48 stars 8 forks Updated today MIT

Install

View on GitHub

Quality Score: 83/100

Stars 20%
56
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Safe write operations Calls to `run_write_operation` can **spend money, pause campaigns, change budgets, edit live creatives, send emails, or charge customers**. Treat every one as a production change. ## When this protocol applies The trigger is the **`requires_approval: true`** flag on the operation in the `find_operations` response. If `requires_approval: true`, you **must** use `run_write_operation` and **must** follow the four-step protocol below. If `requires_approval: false`, use `run_operation` and skip this protocol — no confirmation needed. ## The four-step write protocol **Always** follow this exact sequence before calling `run_write_operation`: 1. **State the change in plain English.** Include the platform, account, object name/ID, and what will change. Example: > "I'm about to **pause** the Google Ads campaign **'Brand — US Search'** (ID `1234567890`) in account **Acme US (MCC 999-888-7777)**. This will stop spend immediately." 2. **State the blast radius.** What spend, traffic, revenue, or audience is affected? Pull a quick number from `run_operation` if you don't know. 3. **Ask for explicit confirmation.** Wait for a yes. "Looks good", "go ahead", or "do it" all count. Anything ambiguous = ask again. 4. **Execute, then verify.** After the call returns, fetch the object's current state with `run_operation` and confirm the change landed. ## Hard rules - **Never batch more than 5 write operations without re-confirming.** If a workflow needs 20 pauses,...

Details

Author
markifact
Repository
markifact/markifact-mcp
Created
4 months ago
Last Updated
today
Language
Shell
License
MIT

Integrates with

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

safe-effects

Use when preparing a deploy, message, charge, migration, destructive query, DNS change, external API write, or any action with a real-world side effect.

6 Updated today
lawzava
AI & Automation Listed

google-ads-live-ops

Operate a live Google Ads account safely — read-only analysis via the API/MCP with GAQL, PPC math and forecasting, and guarded write operations. Use when the user wants to connect Claude to a live Google Ads account, run GAQL queries, pull live performance/search-terms/auction data, forecast budgets or CPA/CPL, calculate break-even bids, or make account changes (pause, bids, budgets, keywords) safely. Triggers on "connect to my account", "live data", "GAQL", "run a query", "MCP", "pull my campaigns", "forecast", "break-even CPC", "budget projection", "pause campaign", "change bids", "update budget", "make this change". Do NOT use for strategy without live data (use the relevant strategy sub-skill) — this is the operational/execution layer.

4 Updated yesterday
Growth-Today
AI & Automation Listed

destructive-ops-approval

Obtain explicit confirmation before irreversible or outward-facing operations such as force-pushes, history rewrites, mass deletion, data migrations, or production changes, and prefer the reversible alternative when one exists. Use when an action could destroy data, rewrite shared history, or change systems other people depend on; do not use to stall routine, easily reversible work.

2 Updated yesterday
26zl