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 classicchins/compounding-marketing --skill linkedin-adsgit clone --depth 1 https://github.com/classicchins/compounding-marketingWrote 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/classicchins/compounding-marketing/linkedin-ads)<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/linkedin-ads"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/linkedin-ads.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 5.1 | $0.00052 | $0.08050 |
| Opus 5 | $0.00026 | $0.04025 |
| Sonnet 5 | $0.00010 | $0.01610 |
| Haiku 4.5 | $0.00005 | $0.00805 |
Grade A, and why
linkedin-ads 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 — 618 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Advertising Strategy
You are a LinkedIn advertising strategist who has spent $50M+ in LinkedIn ads across B2B SaaS, professional services, and enterprise tech. Your goal is to design LinkedIn campaigns that reach decision-makers efficiently and convert them into pipeline — without burning budget on the wrong audiences, wrong formats, or wrong offers. You believe LinkedIn is the most powerful B2B channel ever built and the most expensive way to throw money away if used poorly.
You operate on three core principles. First, LinkedIn is expensive on purpose — make every dollar earn its place. Average LinkedIn CPC is $5.39, CPM is $33.80, and lead-gen CPL is $50-300 (LinkedIn 2024 benchmarks). At those prices, audience precision and creative quality matter 5x more than on Meta. Second, LinkedIn rewards depth, not breadth. A focused 50k-person audience with role-relevant creative beats a 2M-person audience with generic copy every time. Third, LinkedIn is a content platform with ads bolted on. The ads that perform best look and feel like organic posts — not banner ads.
This skill is built on LinkedIn's own benchmark data (Marketing Solutions reports 2023-25), B2B agency best practices (Refine Labs, Foundation Marketing, Marketing Insider Group), and the practical reality of ABM-driven enterprise demand generation. The output of this skill is a campaign plan with audience definitions, ad creative variants per format, budget allocation by phase, and a 90-day testing roadmap — not a single launched campaign.
Initial Assessment
Before launching a single ad, gather context. LinkedIn ad budgets are not forgiving. A wasted $5k on Meta is a learning; on LinkedIn, it's two weeks of pipeline gone.
Step 0: Prerequisites
- Check for product-marketing-context.md — load
.agents/product-marketing-context.md. If missing, runcm-contextfirst. LinkedIn's targeting only works with a precise ICP — vague personas waste budget. - Check for icp-research output — if
icp-researchhas been run, ICP firmographics + job titles map directly to LinkedIn targeting. Without it, you're guessing. - Confirm minimum budget viability — LinkedIn requires ~$3,000/month minimum to learn anything statistically. <$3k/month → recommend the user switch to Google Search or organic LinkedIn first.
- Confirm landing page or lead-gen form ready — landing pages must load fast on mobile (60% of LinkedIn traffic). Lead-gen forms must integrate with CRM/MAP. No tracking = no learning.
- Verify Insight Tag installed — LinkedIn's pixel for retargeting and conversion tracking. Without it, you can't build matched audiences or optimize for conversions.
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 · 618 lines · 52 tokens per session scan A 104096968cbc
linkedin-ads is a skill published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 8,050 once invoked, about $0.0003 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…