competitor-creative-audit

competitor-creative-audit is a skill for Codex from creativescope/creativescope-mcp. It costs 77 tokens per session (1,912 once invoked), scanned A, original, MIT.

A process for creating a structured report about a mobile game's or game studio's advertising creatives using CreativeScope tools. An advertising creative is an ad's visual and message content.

In plain words
What is it for?
Use it to investigate a named game, studio, or advertiser, find the matching advertiser, review its ads, and produce a competitor creative report.
Why use it?
It turns scattered competitor-ad information into an organized creative-strategy analysis, while reporting when requested data requires a paid tool tier.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to investigate a named game, studio, or advertiser, find the matching advertiser, review its ads, and produce a competitor creative report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/creativescope/creativescope-mcp/competitor-creative-audit
Install

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.

Any agent
npx skills add creativescope/creativescope-mcp --skill competitor-creative-audit
Clone the repo
git clone --depth 1 https://github.com/creativescope/creativescope-mcp

Made for: Codex.

Wrote 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.

agentmods badge for competitor-creative-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/creativescope/creativescope-mcp/competitor-creative-audit/github.svg)](https://agentmods.dev/skills/creativescope/creativescope-mcp/competitor-creative-audit)
Your own site
<a href="https://agentmods.dev/skills/creativescope/creativescope-mcp/competitor-creative-audit"><img src="https://agentmods.dev/badge/skills/creativescope/creativescope-mcp/competitor-creative-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for competitor-creative-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/creativescope/creativescope-mcp/competitor-creative-audit"><img src="https://agentmods.dev/badge/skills/creativescope/creativescope-mcp/competitor-creative-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,912 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.01912
Opus 5 $0.00039 $0.00956
Sonnet 5 $0.00015 $0.00382
Haiku 4.5 $0.00008 $0.00191

Measured 8d ago against content hash d45662c07921, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

competitor-creative-audit 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 8d 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.

skills/competitor-creative-audit/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Competitor Creative Audit

Produce a structured creative-strategy report for one advertiser (game or studio) using CreativeScope tools. Work through the phases in order; do not skip phase 1. For tool parameters, filter values, and empty-result debugging, follow the creativescope-best-practices skill.

Plan wall: Every tool in Phases 1–3 is Pro-tier (get_creative_rankings in Phase 4 is the only Free one). On PLAN_UPGRADE_REQUIRED, state it honestly with the upgrade link, deliver only what Free allows, and label the blocked sections — never fill them with invented data.


Phase 1: Advertiser Landscape

Step 1 — Resolve the advertiser

Call search_advertisers with the user's game/studio name as query.

  • If several candidates come back, pick the best match and state which one you chose (name + advertiser_id). Ask the user only if genuinely ambiguous.
  • If nothing matches, try a shorter/alias name once, then tell the user the advertiser was not found and suggest checking spelling or region.

Save both advertiser_id and game_id — they are interchangeable for the ranking tools.

Step 2 — Pull the profile

Call get_advertiser_profile with the advertiser_id. Extract: recent ad activity, creative volume, target countries, platforms. These become the "Overview" section of the report.


Phase 2: App Store Performance

CreativeScope now includes App Store / Google Play ranking data. Use the two tools below to paint the game's store performance picture.

Step 3 — Ranking markets overview

Call get_game_rank_markets with the game_id from Step 1.

  • Default: store: "all", rank_types: ["free","store_paid","grossing"].
  • Default date range is last 90 days; do not exceed 365 days.

Extract for the report:

  • Which markets the game is charting in (country + category + store)
  • Best rank achieved in each dimension
  • Latest rank and how many days it has held a rank
  • Dominant store (Google Play vs iPhone App Store) and rank type (free / paid / grossing)

Read the full file on GitHub · 193 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 8d ago First seen · 193 lines · 77 tokens per session scan A d45662c07921

Subscribe to this mod's changes

competitor-creative-audit is a skill published in the GitHub repository creativescope/creativescope-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 1,912 once invoked, about $0.0004 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 2026-08-31.