Get started
  1. Marketplace
  2. OpenChatly
  3. Use-case pack
Source
OpenChatly
Workspace
Use-case pack
Files
1
View source
Back

Ad performance review

Skill

Daily runbook for budget pacing, CPA/ROAS drift, underperformer detection, and anomaly flags across Google Ads and Meta Ads, plus how to rank and word optimization recommendations.

kortix marketplace install kortix-starter:ad-performance-review-skill

Step 1 — Pull spend and performance from Google Ads (read-only)

For every active campaign, ad group, ad, and keyword, pull: daily spend, monthly budget, clicks, impressions, conversions, cost per acquisition (CPA), and return on ad spend (ROAS) where conversion value is tracked. Pull the trailing 30-day baseline for the same metrics.

Step 2 — Pull spend and performance from Meta Ads (read-only)

For every active campaign, ad set, and ad across Facebook and Instagram placements, pull the same fields: daily spend, budget, clicks, impressions, conversions, CPA, and ROAS, plus the trailing 30-day baseline.

Step 3 — Check budget pacing

For each campaign, compare spend-to-date against the elapsed fraction of its budget period.
Pacing signalCriteria
On paceSpend-to-date within ±15% of the expected linear pace
OverpacingSpend-to-date more than 15% ahead of expected pace — will exhaust budget early
UnderpacingSpend-to-date more than 20% behind expected pace — budget is going unused

Step 4 — Check CPA/ROAS drift

Compare each campaign's/ad's trailing 7-day CPA and ROAS against its 30-day baseline.
Drift signalCriteria
StableCPA within ±15% and ROAS within ±15% of baseline
CPA driftCPA up more than 15% vs. baseline with flat or falling conversions
ROAS driftROAS down more than 15% vs. baseline
Compounding driftCPA up AND ROAS down in the same window — flag first

Step 5 — Flag underperforming ads and keywords

Underperformer signalCriteria
Low-CTR adClick-through rate less than half the ad set's/ad group's average, with 1,000+ impressions
High-cost, no-convert keyword/adSpend above the account's median per-unit spend with zero conversions over the trailing window
Wasted-spend keywordSearch term with 3+ clicks and zero conversions over 14+ days (Google Ads search terms report)

Step 6 — Detect anomalies

Flag anything that breaks the normal pattern rather than drifting gradually:
  • A single day's spend more than 2x the campaign's trailing 7-day daily average.
  • A sudden CTR drop of more than 50% day-over-day on a previously stable ad.
  • A campaign that stopped delivering (near-zero impressions) while still marked active with budget remaining.

Step 7 — Draft the recommendation for each finding

Every finding gets exactly one concrete, human-actionable recommendation:
  • Overpacing → suggest lowering the daily budget or adding a spend cap so it doesn't exhaust the period early.
  • Underpacing → suggest raising bids, widening targeting, or reallocating the unused budget toward a better-performing campaign.
  • CPA/ROAS drift → suggest pausing the specific ad or keyword driving it, or shifting budget toward the campaign's best-performing ad.
  • Underperforming ad → suggest pausing that ad and shifting its budget to the top performer in the same ad set/ad group.
  • Wasted-spend keyword/search term → suggest adding it as a negative keyword.
  • Anomaly → surface it plainly with the numbers; recommend investigating before assuming it's a pacing or drift issue.

Step 8 — Rank and post

Sort findings highest-impact first (compounding drift and overpacing that risks exhausting budget rank above a single underperforming keyword). Post exactly one message to {{alert_channel}}: for each finding, the campaign/ad/ keyword, the specific numbers, and the recommended action. Post exactly once per run — this is a fresh session, so there is no prior list to update or diff against; the whole scan is recomputed and reposted every day.

Related skills

Access policy

The role-to-grant policy, extra-scrutiny cases, the approval handshake, and how an applied grant gets logged.

account-research

Get a complete picture of any company or person before outreach. This skill always works with web search, and gets significantly better with enrichment and CRM data.

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

AP invoice matching

Extract-and-match runbook for incoming vendor invoices: line-item extraction, PO/prior-invoice matching, duplicate + overcharge detection, and the ledger + approval hand-off.

Brand mention monitor

Search, dedupe against the seen-mentions ledger, classify sentiment and notability, and post a digest with suggested response drafts — the daily brand-monitor runbook.

Call recap

Runbook for turning a finished call's transcript into a HubSpot deal update (or a flagged handoff when no deal matches), filed Linear tasks, and a drafted recap email.

Own your AI.Start today, in our cloud.

Start for free

OpenChatly is the AI workspace for everything. One person directing, agents executing, from goal to finished work.

©2026 OpenChatly AI.沪ICP备2025124785号-5

Resource guide

  • Product overview
  • Skills marketplace

Terms of service

  • User agreement
  • Privacy policy

Contact us