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-generate-hooksgit 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-generate-hooks)<a href="https://agentmods.dev/skills/s3yed/appie-kit/ad-creative-generate-hooks"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/ad-creative-generate-hooks/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-generate-hooks"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/ad-creative-generate-hooks.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 | $0.00081 | $0.00736 |
| Opus 5 | $0.00041 | $0.00368 |
| Sonnet 5 | $0.00016 | $0.00147 |
| Haiku 4.5 | $0.00008 | $0.00074 |
Grade A, and why
ad-creative-generate-hooks 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Creative — Generate Hooks (Step 3 / Hook Prompt)
Part of the ad-creative-variations family. Full context: ../ad-creative-variations/SKILL.md.
When to use
- Optional step, only relevant when the Prompt 2 route (new angles) is in play.
- Requires the brief from
ad-creative-analyze-winneralready produced. - Never use this for the Prompt 3 / new-backgrounds route — that route keeps the existing headline 100% identical, a new hook never fits there.
Prerequisites
- The full brief from
ad-creative-analyze-winner, verbatim. - The winning ad image again.
- The target market/language.
Procedure
Run this prompt (adapt [LANGUAGE/MARKET]):
Based on this winning ad brief:
[PASTE HERE: full output from Prompt 1]
I will upload the winning ad as a reference image.
Generate 15 new hooks for this ad that can replace the existing
headline while keeping the same winning format and visual DNA.
A hook replaces ONLY the headline. For each hook, also write one short
matching subheadline (1 line) so the ad text stays complete.
Deliver 3 hooks for each of these 5 angles:
Angle 1 - Problem Awareness
Hook directly into the pain point the target audience already
feels but hasn't named yet.
Angle 2 - Myth/Belief Breaker
Challenge a common assumption or mistake the target audience is making.
Angle 3 - Pure Proof
Show the result without selling it. A real before/after, a number,
a timeline. Let the proof speak — no commentary needed.
Angle 4 - Educational / Informational
Teach the audience something they didn't know. Position the product
as the logical conclusion of useful information.
Angle 5 - Direct Result / Transformation
Lead with the outcome. Bold, specific, no fluff.
Rules for every hook:
* All text in [LANGUAGE/MARKET]
* Maximum 8 words per hook
* Each hook must feel scroll-stopping on its own
* No hooks that sound similar to each other
* Match the tone and register of the winning ad
* Do not invent claims that weren't present or implied in the winning ad
Output format — for each hook deliver:
* The hook text
* The matching subheadline
* Which angle it uses
* One sentence on why it works for this specific audience
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 · 83 lines · 81 tokens per session scan A 7ebb940e078b
ad-creative-generate-hooks is a skill published in the GitHub repository S3YED/appie-kit (9 stars, last pushed 16d ago), licensed MIT. It adds 81 tokens to every session and 736 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…