agentsclimarketplace

Cross platform

Skill foxgeeek/adskills/.claude/skills/cross-platform

Claude Code Skills framework for multi-platform ad operations — Meta, Google, LinkedIn Ads from the terminal / Framework de Claude Code Skills pra gestão de tráfego multi-plataforma

Install
npx -y skills add foxgeeek/adskills --skill cross-platform

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Orchestrate workflows that span Meta, Google, and LinkedIn Ads simultaneously. Sub-skills cover CRM audience sync across all platforms, unified performance dashboards, and efficiency-based budget rebalancing recommendations.

SKILL.md

1.2 KB, 213 tokens by cl100k_base, as published. Nobody here has run it

Cross-Platform — Root Skill

Sub-skills:

  • crm-sync/ — single CSV → Meta custom audience + Google customer match + LinkedIn DMP segment in one run
  • dashboard/ — consolidated HTML dashboard of spend, clicks, conversions, CPA across all 3 platforms
  • budget-rebalance/ — efficiency-weighted budget reallocation recommendations (read-only)

Prerequisites

  • All three platforms authenticated via adskills init
  • config/accounts.json has meta, google, and/or linkedin sections under the same accountRef
  • At least one platform must return conversion data for budget-rebalance

Destructive action policy

  • crm-sync creates audiences/lists/segments on each platform — requires explicit confirmation
  • dashboard and rebalance are read-only

Partial success behavior

  • If one platform fails in crm-sync, the others still attempt — failures are surfaced in the HTML report
  • dashboard skips platforms missing from accounts.json silently

Gives 0 of the 12 instructions most performance cost skills give in 213 tokens

Counted across 803 of the 1,058 authors here whose files we hold, read 2026-08-06

  • keep skill files under 500 linesin 82 of 803, across 17 files
  • use imperative form in instructionsin 81 of 803, across 10 files
  • draft assertions while test runs are in progressin 75 of 803, across 9 files
  • create two to three realistic test promptsin 74 of 803, across 8 files
  • write skill descriptions to be pushyin 72 of 803, across 7 files
  • save test cases to evals jsonin 72 of 803, across 6 files
  • ask questions about edge cases and input formatsin 71 of 803, across 6 files
  • save timing data immediately when runs completein 70 of 803, across 5 files
  • include all trigger conditions in the skill descriptionin 69 of 803, across 3 files
  • launch all test runs in a single turnin 69 of 803, across 3 files
  • capture intent before writing a skillin 67 of 803, across 1 file
  • import directly instead of barrel filesin 52 of 803, across 15 files

Said here and by no other author read

  • authenticate all platforms before running
  • configure all platforms under one accountRef
  • request explicit confirmation before running crm-sync
  • continue syncing remaining platforms on partial failure
  • surface sync failures in the HTML report
  • skip missing platforms silently during dashboarding

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.