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 skills add S3YED/appie-kit --skill ad-creative-analyze-winnergit clone --depth 1 https://github.com/S3YED/appie-kitWrote 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/s3yed/appie-kit/ad-creative-analyze-winner)<a href="https://agentmods.dev/skills/s3yed/appie-kit/ad-creative-analyze-winner"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/ad-creative-analyze-winner/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.
<a href="https://agentmods.dev/skills/s3yed/appie-kit/ad-creative-analyze-winner"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/ad-creative-analyze-winner.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00080 | $0.01020 |
| Opus 5 | $0.00040 | $0.00510 |
| Sonnet 5 | $0.00016 | $0.00204 |
| Haiku 4.5 | $0.00008 | $0.00102 |
Grade A, and why
ad-creative-analyze-winner 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Creative — Analyze Winner (Prompt 1)
Part of the ad-creative-variations family. Full context: ../ad-creative-variations/SKILL.md and ../ad-creative-variations/references/ad-creative-system-source.md.
When to use
- First step whenever asked to scale/vary a winning ad.
- Never skip this even if the user only wants "just the new angles" — every downstream prompt (new angles, new backgrounds, hook generation, weak-angle fix) needs this brief verbatim.
Prerequisites
- The winning ad, as an image.
- Confirm the ad actually qualifies as a winner first (Step 0 in the parent skill: minimum spend + ROAS/CPA threshold the user has set). If unproven, stop and say so.
- Know the target market/language (ask if unclear — do not assume Swiss German).
Procedure
- Load the winning ad image.
- Run this analysis (adapt
[LANGUAGE/MARKET]to the actual target, e.g. "Schweizer Hochdeutsch — Swiss Standard German, no ß, always 'ss'", or "German (Germany)", "Dutch", etc.):
Analyse this winning ad and extract the following elements.
START your answer with two clear labels:
A) RECOMMENDATION: "USE PROMPT 2" or "USE PROMPT 3" or "USE BOTH"
+ one sentence why.
B) TEXT ANGLE SCORE: "STRONG" or "WEAK" + a score from 1-10
+ one sentence why. Score 6 or lower = WEAK.
Then extract:
1. VISUAL STYLE: How is the image composed?
(close-up, lifestyle, product shot, before/after etc.)
2. FORMAT: What is the ad format?
(split screen, single image, text overlay, two-zone with bottom strip etc.)
List every layout element that is actually present. Do not assume elements
that are not visible.
3. HOOK STYLE: What emotional trigger does the headline use?
(curiosity, fear, social proof, problem-aware, authority etc.)
4. CORE MESSAGE: What is the main promise or benefit?
5. TEXT ELEMENTS: List all text visible in the ad exactly as written.
6. PRODUCT PLACEMENT: Where and how is the product shown?
If no product is visible, say so.
7. MAIN SUBJECT: Is there a person in the image? If yes: age, gender,
expression, pose. If no: describe the main subject (product, scene, object).
8. TARGET AUDIENCE: Who is this ad clearly targeting?
9. WINNING DNA: Summarize in 2-3 sentences what makes this ad work
and what must be preserved in all variations.
Recommendation logic you must follow:
* USE PROMPT 3 if the TEXT is the main reason this ad wins.
The text must stay exactly as is; only the background image gets refreshed.
* USE PROMPT 2 if the VISUAL FORMAT is the main reason this ad wins.
The format stays; the text angle can be varied.
* USE BOTH if text AND format are both clearly strong.
Output this as a structured brief I can use to brief an AI image generator.
All ad copy in [LANGUAGE/MARKET].
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.
- 8d ago First seen · 89 lines · 80 tokens per session scan A f7ab0bf7eea6
ad-creative-analyze-winner is a skill published in the GitHub repository S3YED/appie-kit (9 stars, last pushed 16d ago), licensed MIT. It adds 80 tokens to every session and 1,020 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 2026-09-03.
Other skills, from other repositories
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
aws-patterns
Lambda best practices, S3 event patterns, SQS/SNS fanout, and DynamoDB access patterns for serverless AWS architectures.
review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use…
agents-md-protocol
Create or review an AGENTS.md file so coding agents get stable repo-local instructions: environment setup, testing, style, security boundaries, PR policy, and handoff rules. Use when a repo lacks durable agent guidance or when a custom harness needs a predictable context file.
investment-memo-generator
Investment memo creation combining financial analysis, document generation, and structured templates. Use when creating investment memos, pitch decks, deal summaries, or investment committee materials.
python-memory-safe-scripts
Memory-safe Python script patterns for long-running processes under systemd MemoryMax constraints. Covers allocator purge (mimalloc/glibc malloctrim), HTTP response lifecycle, DataFrame cleanup, thread-local connection reuse, and periodic GC cadence. Battle-tested through 5 OOM optimization cycles on production GPU…