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 kelpi-ai/meta-ads-skills --skill angle-writergit clone --depth 1 https://github.com/kelpi-ai/meta-ads-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/kelpi-ai/meta-ads-skills/angle-writer)<a href="https://agentmods.dev/skills/kelpi-ai/meta-ads-skills/angle-writer"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/angle-writer/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/kelpi-ai/meta-ads-skills/angle-writer"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/angle-writer.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 | $0.00048 | $0.00551 |
| Opus 5 | $0.00024 | $0.00275 |
| Sonnet 5 | $0.00010 | $0.00110 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
angle-writer 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 11d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Angle Writer
Doctrine
The offer is fixed. The angle is the experiment. An angle is not a tone of voice: it is who the ad is for + the pain it names + the outcome it promises. Watermelon juice is one offer with four angles: fun drink for kids, hydration for lifters, weight loss without losing nutrients, better skin. Since Andromeda, Meta's delivery system reads the ad itself to decide who sees it, so a specific angle is literally your targeting. Generic creative ("essential nutrients, for everyone") gives the machine nothing to aim with.
When to use
- Before building any campaign (feed it the Brand Reader output).
- When results plateau: you need a new angle, not a 7th variation of the old one.
Run it
Using this brand kit: [PASTE BRAND READER OUTPUT]
Write 6 ad angles for this offer. For each angle give me:
1. WHO: the specific person (situation, not demographics: "parent packing school lunches", not "women 25-45").
2. PAIN: the problem they would say out loud, in their words.
3. PROMISE: the outcome this offer gets them, specific enough that the WHO recognizes it in one second.
4. The ad: primary text (under 125 words), headline (under 40 characters), description.
Make the 6 angles genuinely different: different WHO or different PAIN, not the same idea reworded. Spread them across pain, aspiration, proof, curiosity, and urgency framings. For the proof angle, use only the verbatim proof from the brand kit; if there is none, write a "how it works" angle instead and tell me proof is missing.
Then add one line per angle: what the Meta algorithm learns about who to find from this ad.
Guardrails
- The one-second test: if a stranger from the WHO group would not recognize the ad as "for me" in one second, the angle is too generic. Rewrite it.
- No invented proof, statistics, or fake urgency (no countdown that resets).
- Angles get tested one per ad, never blended. Judge an angle only after it has spent 2-3x your target cost-per-result.
Good output looks like
Six ads a media buyer could launch as-is, where reading only the WHO lines gives you six visibly different people.
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.
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.
- 11d ago First seen · 39 lines · 48 tokens per session scan A 7359381a9176
angle-writer is a skill published in the GitHub repository kelpi-ai/meta-ads-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 551 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…