Writing & Content paid-advertisingbrand-safetyplacement-exclusionsaudience-exclusionscontent-suitabilityroas-a1

Brand Safety Exclusion Manager

Build placement, network, content, and audience exclusion rules before paid campaigns go live.

FollowSkills review · FSRS-2.0
Not recommended
56/ 100 5-point scale 2.8 / 5
Trust15 / 25 · 3.0/5

The skill treats exports as untrusted data, forbids following embedded instructions, stops A1 evidence construction when the placements report is absent, saves only after user confirmation, and keeps connectors optional. Deductions reflect missing detail on sensitive-data handling, exact pre-write confirmation, rollback, and external-platform mutation boundaries; publisher identity is unverified.

Reliability9 / 20 · 2.3/5

The contract, input dependencies, NEEDS_INPUT behavior, scope guard, and handoff path are clear, with repository-level tests and CI evidence. Static review cannot reproduce the key path, and malformed-report handling, platform-rule failures, and output/error diagnostics are not sufficiently specified; the static cap keeps this at 9.

Adaptability10 / 15 · 3.3/5

Audience, trigger phrases, inputs, outputs, non-goals, and multi-platform use cases are clearly stated, including a manual-export path without connectors. Deductions reflect limited Chinese-language coverage, no evidence of mainland-China platform reachability, and insufficiently specified differences among platform exclusion fields and policies.

Convention10 / 15 · 3.3/5

The skill provides versioning, Apache-2.0 licensing, a shared contract structure, quick starts, input/output notes, references, a save template, and repository documentation. Deductions reflect no skill-specific changelog, clearly assigned maintainer, or explicit update path; SECURITY.md says the supported line is 17.x while the skill and README state 18.0.0.

Effectiveness7 / 15 · 2.3/5

The skill targets a concrete task and produces exclusion lists, content and sensitive-topic blocks, an A1 evidence package, and a handoff summary while avoiding audience construction and audit verdicts; missing reports do not default to pass. Deductions reflect no skill-specific representative output or third-party execution evidence, and insufficient output-template detail means manual review may remain substantial; the static cap keeps this at 7.

Verifiability5 / 10 · 2.5/5

The skill identifies placements, campaign/search-term exports, contract references, and security guidance, and distinguishes measured report data from user constraints. Deductions reflect no dedicated tests, sample result, or independent third-party validation, while static reading cannot establish end-to-end reproducibility; the static cap keeps this at 5.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision ebd436747f8f
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • Confirm the placements report, account goal, sensitive-topic constraints, and audience-exclusion dependency before use; without the placements report the result should remain NEEDS_INPUT.
  • Do not treat the A1 evidence package as an audit verdict, and do not re-derive the audience exclusion set in this skill.
  • Reconcile the skill's 18.0.0 version with SECURITY.md's 17.x support statement, and manually verify network choices, content-suitability tiers, and exclusions on the actual platforms.
  • Minimize or redact personal data, audience identifiers, and platform credentials before providing account exports.
Review evidence [1][2][3][4][5][6][7][8][9]
See the full review method →

What does this skill do, and when should you use it?

This skill supports the activation phase of paid advertising by preparing brand-safety controls before spend starts. It covers site, app, channel, network opt-out, content-suitability, and sensitive-topic exclusions. It consumes the audience exclusion set produced by the audience-segment-builder and packages evidence for the ROAS A1 brand and placement safety gate. It does not build target audiences, re-derive audience exclusions, calculate RQS, or issue the A1 verdict.

Reads the account or campaign goal, brand-safety constraints, placement report, and campaign and search-terms reports; identifies low-quality, off-brand, made-for-advertising, or irrelevant sites, apps, and channels when placement data is available; decides on Search-partner, Display-expansion, and Audience-network opt-outs; lists content-suitability tiers, sensitive topics, and keyword blocks; references the audience exclusion set from audience-segment-builder; and packages the placement report plus rationale-backed exclusion decisions as an A1 evidence file with a handoff summary. If the placement report is missing, it marks the work NEEDS_INPUT.

  1. A paid media manager preparing a Google Ads or other advertising campaign needs to remove unsafe or irrelevant placements before launch.
  2. A brand with rules against news, politics, user-generated content, or tragedy adjacency needs reusable topic and content blocks.
  3. An advertising team preparing for a ROAS A1 review needs to organize placement evidence and exclusion rationales.
  4. An ad operator has audience segments already defined but needs to align placement and network controls with them.

What are this skill's strengths and limitations?

Pros
  • Covers placements, sites, apps, channels, network opt-outs, content suitability, and sensitive-topic blocks.
  • Separates measured findings from the placement report from user-provided constraints.
  • Packages exclusion decisions and rationales into evidence for the A1 gate.
  • Works with pasted or exported user data and does not require paid advertising APIs.
Limitations
  • The placement report is a load-bearing input; without it, A1 evidence cannot be built and the result is NEEDS_INPUT.
  • It does not create or re-derive audience exclusion sets and depends on audience-segment-builder for that work.
  • It does not calculate RQS or issue a Pass, Partial, or Fail decision for A1.
  • The supplied material provides no platform-specific test results or standalone test suite evidence.

How do you install this skill?

For Claude Code, run /plugin marketplace add aaron-he-zhu/aaron-marketing-skills, then /plugin install aaron-marketing@aaron. On other Agent Skills-compatible hosts, run npx skills add aaron-he-zhu/aaron-marketing-skills, or clone the repository with git clone https://github.com/aaron-he-zhu/aaron-marketing-skills. The skill is located at ad/activate/placement-exclusion-manager/SKILL.md.

How do you use this skill?

Provide the account or campaign goal, platforms, brand-safety constraints, and a placement report. Example: Build brand-safety exclusion lists for [goal] on [platforms] before launch. Here is my placements report: [paste/path]. To package audit evidence, use: Package the A1 brand/placement-safety evidence for the auditor from this placements + campaign export: [paths].

FAQ

Can I use it without a placement report?
You can provide the goal and constraints first, but the A1 evidence package cannot be completed and must be marked NEEDS_INPUT.
Does it decide which audiences to exclude?
No. It consumes the audience exclusion set from audience-segment-builder and does not re-derive existing-customer, converter, or off-fit exclusions.
Does it decide whether the account passes the audit?
No. It packages brand and placement safety evidence for ad-account-auditor, which calculates the full RQS and judges A1.

More skills from this repository

All from aaron-he-zhu/aaron-marketing-skills

Data & Analysis

Paid Ads Account Auditor

Decide whether a paid-media account is safe to launch or scale using its own evidence.

Writing & Content

Ad Fatigue & Frequency Manager

Diagnose creative fatigue or audience saturation from frequency, CTR, and CVR trends, then choose rotate, widen, or hold.

Writing & Content

Paid Ads Campaign Architect

Designs paid account structure and reduces internal bidding and paid-organic overlap.

Writing & Content

Paid Ads Audience Segment Builder

Turn your customer, CRM, or GA4 exports into seed, exclusion, and funnel-stage audiences for paid media.

Data & Analysis

Paid Ad Budget Pacing Monitor

Measure campaign spend against plan and flag when budget reallocation is warranted.

Data & Analysis

Ad Experiment Designer

Design rigorous paid-ad A/B and incrementality tests, then determine whether results are statistically and practically meaningful.

Data & Analysis

Paid Attribution Reconciler

Deduplicate paid conversions against order-ID truth and read incrementality.

Writing & Content

Creator Content Auditor

A STAR pre-publish gate that catches disclosure, claim, and authenticity risks and returns a release decision.

Writing & Content

Paid Measurement Loop

Use a control and a fixed readback window to decide whether a paid-ad change should scale, keep testing, roll back, or remain unproven.

Writing & Content

Paid Search Term Miner

Turn search-term reports into converting keywords and spend-saving negatives.

Writing & Content

Influencer Discovery

Build and screen a tiered creator shortlist from scratch for a defined brand, niche, or platform.

Writing & Content

Ad Creative Builder

Generate paid-ad variants that stay faithful to the landing page.

Writing & Content

Paid Ads Bid Strategy Planner

Choose a paid-media bidding model, set a defensible starting target, and protect the campaign’s learning phase.

Writing & Content

Paid Conversion Value Mapper

Map ad conversions to profit so tROAS optimizes contribution value instead of raw revenue or order count.

Writing & Content

Paid Ads Conversion Signal QA

Validate conversion events, UTMs, and cross-platform deduplication before paid campaigns launch or scale.

Writing & Content

Ad Landing Experience Checker

Preflight paid-traffic landing pages for message match, visibility, speed, form friction, and mobile readiness before launch.

Writing & Content

Dynamic Email Personalizer

Safely add merge tags, conditional modules, and fallbacks to an existing email.

Writing & Content

Evergreen Social Calendar

Plan a capacity-aware social rhythm across channels, from content pillars to batching and evergreen recycling.

Writing & Content

Brand Voice Dossier Builder

Extract a reusable brand and founder voice system from the organization’s own content.

Writing & Content

Narrative Cascade Planner

Map an approved brand narrative across every marketing surface and hand precise briefs to the teams that build them.

Related skills