PaidSync publishes six Agent Skills, SKILL.md files your AI agent follows step by step. They cover wasted spend and negative keywords on Google Ads, a Meta audit and creative fatigue, LinkedIn campaign QA, and tracking health across Tag Manager, GA4, Google Ads and the Meta pixel.
Install all six with npx skills add https://paidsync.ai. Each skill reads live data through the PaidSync MCP server, proposes a change, and applies it only after a dry run and your yes.
Install all six skills
npx skills add https://paidsync.aiThe skills CLI reads the index at paidsync.ai/.well-known/skills/index.json, checks every file against its sha256 digest, and asks which agents to install into. Three flags cover most setups.
# straight into Claude Code, no prompts
npx skills add https://paidsync.ai -a claude-code -y
# one skill only
npx skills add https://paidsync.ai --skill wasted-spend-hunter
# list the six without installing
npx skills add https://paidsync.ai --listUse the bare domain. With a path such as paidsync.ai/skills, the CLI looks for a separate index under that path and finds none.
Connect the PaidSync MCP server first
Every skill reads and writes through the PaidSync MCP server at https://mcp.paidsync.ai/mcp. In Claude Code, run:
claude mcp add --transport http paidsync https://mcp.paidsync.ai/mcpThen type /mcp and sign in with your PaidSync login. For Codex, Cursor, ChatGPT and other assistants, follow the setup guides, or start from the Claude Code guide. If the server is missing, each skill tells the agent to stop and say so.
The six skills
Wasted Spend Hunter Skill for Google Ads
Blocks Google Ads search terms that spend and never convert. One table of zero-conversion terms above a $25 spend floor, each with a match type and a level, closed by the 30-day spend added up from the report rows.
Negative Keyword Triage Skill for Google Ads
Weekly search term triage into block, watch and harvest. Every new term in one of three buckets. Block for intent mismatch, watch for ambiguous terms below the account's cost per conversion, harvest for converting terms that are not keywords yet.
Meta Ads Audit Skill for AI Agents
Eight-check Meta audit that composes read tools, one check at a time. One scorecard with a pass, watch or fix status per check, the evidence numbers and a proposed fix, sorted by the spend each fix touches.
Creative Fatigue Scan Skill for Meta Ads
Finds tired Meta ads, then pauses or rebalances them. A fatigue table with one of two verdicts per ad, pause or rebalance, and the creative angles that decayed slowest.
LinkedIn Campaign QA Skill for AI Agents
Launch checklist for every live LinkedIn campaign. A QA table of the checks each campaign failed, with the evidence and one of three fixes. Adjust settings, adjust budget, or pause.
Tracking Health Skill for Tag Manager, GA4 and Ads
Finds broken conversion tracking and reads tag consent settings. A repair plan. Each defect gets its evidence, what it breaks in plain words, and the exact fix.
How the skills handle changes
Over MCP, PaidSync writes no approval card, so each skill makes your assistant the approval step. A write runs first as a dry run where the tool supports one, then waits for your yes. Destructive operations, such as pauses, need confirm_destructive. Applied changes are logged, on a best-effort basis, with a 7-day before-and-after outcome. Approval cards and one-tap undo exist in the PaidSync workspace, not over MCP.
The full list of controls, and what is not built yet, is on the security page.
Install by hand
Each skill is one SKILL.md file. Download it and save it as ~/.claude/skills/<name>/SKILL.md for Claude Code, or wherever your agent loads skills from.
- Wasted Spend Hunter SKILL.md, saved as
wasted-spend-hunter/SKILL.md - Negative Keyword Triage SKILL.md, saved as
negative-keyword-triage/SKILL.md - Meta Ads Audit SKILL.md, saved as
meta-ads-audit/SKILL.md - Creative Fatigue Scan SKILL.md, saved as
creative-fatigue-scan/SKILL.md - LinkedIn Campaign QA SKILL.md, saved as
linkedin-campaign-qa/SKILL.md - Tracking Health SKILL.md, saved as
tracking-health/SKILL.md
Frequently asked questions
What is an Agent Skill?
A folder with a SKILL.md file: a short YAML header with a name and a description, then plain instructions the agent follows when the skill is relevant or when you call it by name. The format is the open Agent Skills standard, so the same file works in Claude Code, Codex, Cursor and other agents that read skills.
Which agents can install these skills?
Any agent the skills CLI installs into, including Claude Code, Codex and Cursor, or any agent that loads SKILL.md files from a folder. The agent also needs the PaidSync MCP server connected, because every skill reads and writes through it.
Do the skills work without PaidSync?
No. Each skill names PaidSync MCP tools and tells the agent to stop if they are missing. The free plan is $0 for 15 tasks a month with no card, enough to connect an account and run a skill.
Can a skill change my ad account without asking?
Not by design. Each skill previews a change as a dry run where the tool supports one, shows it to you, and waits for an explicit yes. Silence is not a yes. Over MCP, PaidSync writes no approval card, so your assistant is the approval step, and destructive operations need confirm_destructive.
How do I know a skill file was not changed on the way?
The index at paidsync.ai/.well-known/skills/index.json lists a sha256 digest for every SKILL.md, and the skills CLI refuses a file whose bytes do not match its digest.