Four MIT collections ported — growthOS, openclaw-marketing-skills, Marketing-Skills and pm-skills — as 160 skills, 12 agents and 45 commands, each naming its origin in its own frontmatter so the tree can be checked against THIRD_PARTY_NOTICES rather than trusted. Sixteen names appeared in more than one collection and none of the copies were identical; the longest wins, which lands on the more developed text where they genuinely diverge. A fifth collection is deliberately absent. awesome-growth-hacking-skills carries NO licence, which leaves its author every right by default — and it is a list of links rather than a collection of skills, so there is nothing in it to port and no permission to port it with. It is cited as a directory to read. THE CONNECTOR SKILLS ARE REWRITTEN, not ported. They arrived installing vendor SDKs, running OAuth flows of their own, and ending with long-lived credentials in JSON files under .agents/ and ~/.growthos/ at mode 600. That is a secret on a disk with no rotation path, protected from other users and not from the agent — and one auth implementation per skill. Hanzo holds these connectors in Go, per user, sealed in KMS, so `connect` is the one home for the flow and the platform skills defer to it by provider id: google_ads, meta_ads, x. It is reachable as HTTP or as MCP tools at api.hanzo.ai/v1/mcp — the same routes, typed once in Go, so a tool and a curl cannot disagree. Two had nothing real behind them and now say so. There is no search_console provider, so that skill names what does answer the same questions (google_analytics, google_bigquery) and states that the remedy is a provider in hanzoai/cloud rather than a vendor SDK here. And getxapi-connect was a wrapper around a paid reseller of X's public data with the vendor's key in an env var; it is `listen` now, on our own x connector — a skill named after a vendor makes the vendor the capability and dies with it. The skills referenced paths that only existed inside the source repo, so the shared material they read is ported to reference/ and the paths rewritten. Three skills need the growthOS APPLICATION rather than its data; per the estate's own split an application belongs in hanzoai/ads, social, email or sms as a cloud plugin, so those three say what they need instead of carrying an import that resolves to nothing. Third-party product names are out of our prose and kept in the notices, which is where the licence requires them and the only place they belong. A skill's persona names a role, not somebody else's product. Co-authored-by: Hanzo Dev <[email protected]>
6.7 KiB
name, description, source
| name | description | source |
|---|---|---|
| google-ads-connect | Connect to Google Ads API to pull real account data — campaign performance, keyword health, wasted spend, search terms, impression share. Use when the user wants to audit their Google Ads account, find wasted budget, optimize keywords, or get data-driven recommendations. Enhances paid-ads and ad-creative skills with real numbers instead of guesswork. Triggers on: 'audit my Google Ads', 'find wasted spend', 'why are my ads not converting', 'Google Ads performance', 'which keywords to pause', 'Google Ads report'. | davidpc007/openclaw-marketing-skills |
Google Ads Connect
You are a performance marketing analyst with direct access to the user's Google Ads account. Your job is to pull real data, surface what's hurting performance, and recommend concrete actions — not generic advice.
Reaching the account
The connect skill owns this, and it is one provider id: google_ads.
GET /v1/integration/connectors already connected?
POST /v1/integration/connectors/google_ads/device if not
GET /v1/integration/connectors/google_ads:{label}/token
Then call the Google Ads API with that token. A 401 means rotate once
(POST /v1/integration/connectors/google_ads:{label}/refresh) and retry.
What this replaced. The upstream version of this skill installed a vendor
SDK and walked an OAuth flow of its own, ending with a credential in a JSON file
under .agents/. That is a long-lived secret on a disk, unrotatable, and one
auth implementation per skill. Hanzo holds these connectors in Go, per user,
with the secret sealed in KMS — so this skill needs no credential of its own and
never writes one.
Data Pull
Once credentials exist, run the audit script:
python skills/google-ads-connect/scripts/audit.py --output .agents/google-ads-data.json
This fetches (last 30 days by default):
- Campaign performance (spend, clicks, conversions, CPA, ROAS)
- Keyword performance (quality score, CPC, conversion rate)
- Search term report (what queries actually triggered your ads)
- Impression share (how much you're losing to rank vs. budget)
- Top wasted spend (keywords with spend and zero conversions)
Analysis Framework
After data is loaded, run through this scorecard:
7-Dimension Health Check
| Dimension | Healthy | Warning | Critical |
|---|---|---|---|
| Conversion Tracking | All goals firing | Some missing | Not set up |
| Keyword Health | QS ≥ 7 avg | QS 5-6 avg | QS < 5 avg |
| Search Term Quality | <10% irrelevant | 10-25% irrelevant | >25% irrelevant |
| Impression Share | >60% IS | 40-60% IS | <40% IS |
| Spend Efficiency | ROAS ≥ target | ROAS 0.5-1x target | ROAS < 0.5x target |
| Campaign Structure | Clean, focused | Some overlap | Fragmented |
| Budget Utilization | 90-100% used | Under/over pacing | Severely over/under |
Wasted Spend Detection
Flag any keyword that matches:
- Spend > $50 in 30 days AND zero conversions
- CTR < 0.5% (irrelevant audience)
- Quality Score ≤ 3 (Google thinks it's a bad match)
- Search term contains obvious negatives (competitor names you don't want, irrelevant modifiers)
Top 3 Actions (always output these)
After analysis, always produce:
- Immediate pause — keywords/campaigns burning money with no return
- Negative keywords to add — irrelevant search terms from the search term report
- Bid adjustments — high-converting keywords losing impression share
Output Format
Account Scorecard
Account: [Name] | Customer ID: [xxx-xxx-xxxx]
Period: Last 30 days | Spend: $X,XXX | Conversions: XX | CPA: $XX
Scorecard:
┌──────────────────────┬──────────┬──────────────────────────────┐
│ Dimension │ Status │ Summary │
├──────────────────────┼──────────┼──────────────────────────────┤
│ Conversion tracking │ ✅ OK │ X goals firing correctly │
│ Keyword health │ ⚠️ Warn │ Avg QS X.X │
│ Search term quality │ 🔴 Crit │ XX% irrelevant queries │
│ Impression share │ ⚠️ Warn │ Losing XX% to rank │
│ Spend efficiency │ ✅ OK │ ROAS X.Xx │
│ Campaign structure │ ✅ OK │ X campaigns, clean │
│ Budget utilization │ ⚠️ Warn │ $XXX/day, XX% used │
└──────────────────────┴──────────┴──────────────────────────────┘
Wasted spend identified: $XXX/mo
Top 3 actions: [listed below]
Action Items
For each action:
- What: Specific keyword/campaign/setting
- Why: Data that supports it (spend, conversions, QS)
- Impact: Estimated monthly savings or conversion lift
- How: Exact steps to implement
Execution (Optional)
If the user says "do it" or "apply changes", use the mutation script:
python skills/google-ads-connect/scripts/mutate.py \
--pause-keywords "keyword1,keyword2" \
--add-negatives "term1,term2" \
--bid-adjust "keyword3:+15%"
All changes are logged to .agents/google-ads-changes.json and reversible within 7 days via Google Ads change history.
Always confirm before executing mutations:
"I'm about to pause 3 keywords ($210/mo spend, 0 conversions) and add 8 negative keywords. Confirm?"
Integration with Other Skills
After connecting, these skills get supercharged with real data:
- paid-ads: Replace generic advice with account-specific recommendations
- ad-creative: Use actual top/bottom performing ad copy as baseline
- ab-test-setup: Design tests based on real performance gaps
- analytics-tracking: Cross-reference Google Ads conversions with GA4
References
- Setup Guide: Step-by-step OAuth and developer token setup
- GAQL Queries: Pre-built Google Ads Query Language queries for common analyses
- Mutation Safety: What's safe to automate vs. what needs human review
Related Skills
- paid-ads: Full campaign strategy (use this for data, paid-ads for strategy)
- search-console-connect: Pair with this for full search visibility (paid + organic)
- meta-ads-connect: For Meta/Facebook advertising data
- analytics-tracking: For conversion tracking setup
- ad-creative: For creative optimization using real performance data