Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/itallstartedwithaidea/agent-skills/quality-score-optimizationnpx skills add itallstartedwithaidea/agent-skills --skill quality-score-optimizationgit clone --depth 1 https://github.com/itallstartedwithaidea/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/quality-score-optimization)<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/quality-score-optimization"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/quality-score-optimization.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00032 | $0.02223 |
| Opus 5 | $0.00016 | $0.01111 |
| Sonnet 5 | $0.00006 | $0.00445 |
| Haiku 4.5 | $0.00003 | $0.00222 |
Grade A, and why
quality-score-optimization scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Score Optimization
Part of Agent Skills™ by googleadsagent.ai™
Description
The Quality Score Optimization skill provides a systematic framework for diagnosing, tracking, and improving Quality Score across every keyword in a Google Ads account. Quality Score is Google's 1-10 rating of the overall relevance and quality of your keywords, ads, and landing pages. It directly impacts ad rank, cost-per-click, and whether your ads show at all. A one-point Quality Score improvement can reduce CPCs by 10-15%.
The skill decomposes Quality Score into its three sub-components — Expected Click-Through Rate (eCTR), Ad Relevance, and Landing Page Experience — and provides targeted improvement strategies for each. It goes beyond the current snapshot by tracking historical Quality Score trends at the keyword level, identifying score degradation patterns, and correlating changes with account modifications. This longitudinal analysis reveals the root causes behind score fluctuations.
The optimization engine prioritizes improvement efforts by weighting keywords by spend volume. A Quality Score improvement on a keyword consuming $1,000/day has far greater impact than the same improvement on a $5/day keyword. The skill generates impact-ranked improvement plans, estimates CPC savings, and tracks improvement progress against benchmarks specific to each industry vertical.
Use When
- User asks about "Quality Score" or "QS optimization"
- User mentions "high CPCs" that may relate to quality issues
- User wants to "improve ad rank" without increasing bids
- User asks about "expected CTR", "ad relevance", or "landing page experience"
- User mentions "below average" quality components
- User wants to "reduce cost per click" through quality improvements
- User asks "why aren't my ads showing" (may be QS related)
- User wants to "track Quality Score changes over time"
Architecture
flowchart TD
A[Google Ads API:\nKeyword Quality Data] --> B[QS Data Extraction]
B --> C[Current QS Snapshot]
B --> D[Historical QS Tracking]
B --> E[Sub-Component Breakdown]
E --> F[Expected CTR Analysis]
E --> G[Ad Relevance Analysis]
E --> H[Landing Page Experience Analysis]
F --> I[CTR Improvement Engine]
I --> I1[Ad Copy Testing]
I --> I2[Ad Extension Optimization]
I --> I3[Audience Refinement]
G --> J[Relevance Improvement Engine]
J --> J1[Keyword-Ad Alignment]
J --> J2[Ad Group Restructuring]
J --> J3[DKI Opportunities]
H --> K[Landing Page Improvement Engine]
K --> K1[Page Speed Optimization]
K --> K2[Content Relevance Matching]
K --> K3[Mobile Experience Audit]
I1 --> L[Spend-Weighted Priority Ranker]
I2 --> L
I3 --> L
J1 --> L
J2 --> L
J3 --> L
K1 --> L
K2 --> L
K3 --> L
L --> M[QS Improvement Plan]
M --> N[Estimated CPC Savings]
M --> O[Implementation Roadmap]
M --> P[Progress Tracking Dashboard]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 231 lines · 32 tokens per session scan A 4718608cf3b0
quality-score-optimization is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (36 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 2,223 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
update-saasmail
Sync the local saasmail repo with the latest upstream changes from https://github.com/choyiny/saasmail. Use this skill whenever the user wants to update saasmail, pull upstream changes, sync with upstream, rebase on upstream, get the latest saasmail, or says "/update-saasmail". Handles adding the upstream remote if…
tracking-health
Preventive audit of conversion tracking across all configured ad platforms — Meta pixels + CAPI, Google Ads conversion actions, and final-URL tracking-parameter consistency on every platform — with a GA4 cross-check. Use when the user asks to check tracking, audit conversion measurement, verify pixels / tags, check…
story-html-publisher
Final step of the AI Storybook pipeline. Consolidates the scenes, images, and per-scene audio into ONE self-contained HTML storybook — a swipe/tap player with every image and audio clip embedded as base64 so the single file works offline and can be shared as-is. Reads {slug}scenes.json, {slug}images.json, and…
learn
Save a marketing diagnosis insight to the pro-diagnosis knowledge base so it is applied in future operations across all platforms. Use when the user runs /learn, explicitly teaches the agent a marketing insight, corrects the agent's analysis, or asks to remember/record an operational learning for next time. Also use…
weekly-report
Generate a weekly summary report across all platforms. Use when the user asks for a weekly report, summary, recap, end-of-week review, or weekly digest. Also use when the user asks in Japanese (週次レポート / 今週のまとめ / 週報を作成して).
adspirer-amazon-ads
Create and manage Amazon Ads through Adspirer — Sponsored Products, Sponsored Brands, and Sponsored Display, with ASIN targeting, search-term reports, ACoS, and bid optimization. Use for anything on Amazon Advertising or Seller/Vendor Central ads.