placement-exclusion-manager

Use when the user asks to "build my brand-safety exclusion lists", "set placement / topic / content exclusions before launch", "add network and audience exclusions", or "prep the A1 brand-safety evidence for the auditor"; produces a placement/network exclusion list, a content-suitability & sensitive-topic block list, an audience/negative-audience exclusion set, and a packaged A1 brand/placement-safety evidence file for the gate. Not for building the audiences you target — use audience-segment-builder; not for computing the RQS or issuing the A1 verdict — use ad-account-auditor. 品牌安全/排除位置/否定受众列表

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, actionable instruction skill with a clear validated workflow and good progressive disclosure. Its main weakness is mild repetition of scope boundaries across several sections, which slightly inflates token use without adding clarity.

Suggestions

Consolidate the repeated scope/non-ownership boundaries (audience exclusions, RQS/A1 verdict) into a single 'Scope guard' section and reference it from the Skill Contract and Next Best Skill rather than restating each time.

Tighten the Quick Start and Instructions to remove near-duplicate phrasing of the 'Unknown / NEEDS_INPUT' gate, which currently appears in Data Sources, step 2, the Done-when clause, and Next Best Skill.

If roas-benchmark.md, CONNECTORS.md, and SECURITY.md are intended as loadable bundle references, co-locate them under references/ so the one-level-deep navigation is self-contained rather than pointing to external repo paths.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the scope/non-ownership boundaries (no audience exclusions, no RQS/verdict) are restated across Skill Contract, Instructions step 6, the Scope guard box, and Next Best Skill, which is mild repetition rather than severe padding.	4 / 5
Actionability	Concrete, specific guidance throughout — numbered steps name exact outputs, require a one-line rationale per exclusion, label each as 'Measured from the report vs User-provided constraint', and specify network opt-out decisions with a stated reach-vs-safety tradeoff; minor gaps only because no executable code is given, which is acceptable for an instruction-only ad-ops skill.	4 / 5
Workflow Clarity	A clear 7-step sequence with explicit validation checkpoints — missing placements report → mark qualified A1 evidence Unknown, stop with NEEDS_INPUT, do not infer; absent audience set → note as dependency — providing the feedback loops expected for a batch/evidence operation.	5 / 5
Progressive Disclosure	Well-organized sections with one-level-deep references (skill-contract.md, CONNECTORS.md, SECURITY.md, roas-benchmark.md) and clear signaling; no local bundle files exist, so structure is judged on sectioning and reference clarity, which is good but references external repo paths rather than co-located bundle files.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is comprehensive, concrete, and trigger-rich, with explicit what/when coverage and clear de-confliction routing to sibling skills. It is a strong, well-scoped skill description with no notable gaps.

Dimension	Reasoning	Score
Specificity	Names multiple concrete outputs — 'placement/network exclusion list', 'content-suitability & sensitive-topic block list', 'audience/negative-audience exclusion set', and 'packaged A1 ... evidence file' — giving comprehensive coverage of what the skill produces.	5 / 5
Completeness	Explicitly answers both 'what' (the four produced artifacts) and 'when' (the 'Use when the user asks to...' clause with concrete trigger phrases), matching the anchor for clearly and explicitly answering both.	5 / 5
Trigger Term Quality	Includes multiple natural quoted phrases a user would actually say — 'build my brand-safety exclusion lists', 'set placement / topic / content exclusions before launch', 'add network and audience exclusions', 'prep the A1 brand-safety evidence for the auditor' — covering the common ways the need is expressed.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche and explicitly routes adjacent work away ('Not for building the audiences you target — use audience-segment-builder; not for computing the RQS ... use ad-account-auditor'), minimizing overlap with sibling skills.	5 / 5
	Total	20 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 18 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: ad/activate/placement-exclusion-manager/SKILL.md
Commit: 9df28a0

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.