Placement Exclusion Manager
Builds pre-launch brand-safety exclusion lists and packages A1 evidence for the ad auditor.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 20, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 6f0fbaa
Fetched the real SKILL.md (v18.0.0) plus evals/placement-exclusion-manager/cases.md, and confirmed all referenced files resolve (HTTP 200 on references/skill-contract.md, references/roas-benchmark.md, CONNECTORS.md, SECURITY.md, and both sibling skills ad-account-auditor and audience-segment-builder). roas-benchmark.md confirms the A1 placement-safety veto and NEEDS_INPUT rule the skill leans on. No exfil/base64/hidden-instruction/secret patterns found. Trigger phrasings judged — SHOULD load: (1) "Build my brand-safety exclusion lists before I launch this Google Ads campaign", (2) "Set placement, network, and content-suitability exclusions for my account before spend goes live", (3) "Package the A1 brand-safety evidence for the auditor from these placements + campaign exports"; should NOT: (4) "Build my lookalike/seed target audiences for this campaign" (routes to audience-segment-builder), (5) "Score my ad account and give me the ROAS/A1 verdict" (routes to ad-account-auditor) — 5/5 correct. Docs are honest and explicitly scope-bounded, no overselling.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What Placement Exclusion Manager does
Builds placement/site/app/network and content-suitability exclusion lists before ad spend goes live, then packages an "A1" brand/placement-safety evidence file for a separate auditor skill to score. Triggers on requests like "build my brand-safety exclusion lists", "set placement/content exclusions before launch", or "prep the A1 evidence for the auditor". It deliberately does not build target audiences or issue the verdict itself.
How to install Placement Exclusion Manager
Clone the repo and copy the `ad/activate/placement-exclusion-manager/` skill into your agent's skills directory. Note: its body links to sibling files (`references/skill-contract.md`, `references/roas-benchmark.md`) and companion skills (`ad-account-auditor`, `audience-segment-builder`), so copy the whole repo (or at least those paths) to keep the relative references intact. No external CLI, MCP, or binary required.
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Placement Exclusion Manager
-
/placement-exclusion-managerBuilds pre-launch brand-safety exclusion lists and packages A1 evidence for the ad auditor.
It also activates on plain-language prompts like these:
-
Build my brand-safety exclusion lists before launch -
Set placement and content exclusions for this campaign -
Add negative audience exclusions to my ad account
Frequently asked questions
- Is the Placement Exclusion Manager skill free?
- Yes. The skill itself is free from aaron-he-zhu/aaron-marketing-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Placement Exclusion Manager work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 20, 2026. Verdict: Tested · Works. Fetched the real SKILL.md (v18.0.0) plus evals/placement-exclusion-manager/cases.md, and confirmed all referenced files resolve (HTTP 200 on references/skill-contract.md, references/roas-benchmark.md, CONNECTORS.md, SECURITY.md, and both sibling skills ad-account-auditor and audience-segment-builder). roas-benchmark.md confirms the A1 placement-safety veto and NEEDS_INPUT rule the skill leans on. No exfil/base64/hidden-instruction/secret patterns found. Trigger phrasings judged — SHOULD load: (1) "Build my brand-safety exclusion lists before I launch this Google Ads campaign", (2) "Set placement, network, and content-suitability exclusions for my account before spend goes live", (3) "Package the A1 brand-safety evidence for the auditor from these placements + campaign exports"; should NOT: (4) "Build my lookalike/seed target audiences for this campaign" (routes to audience-segment-builder), (5) "Score my ad account and give me the ROAS/A1 verdict" (routes to ad-account-auditor) — 5/5 correct. Docs are honest and explicitly scope-bounded, no overselling.
- What is the Placement Exclusion Manager SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install Placement Exclusion Manager?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Placement Exclusion Manager with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.