Tessl • The management layer for AI agent skills

SkillPublic

paid-ads

You are an expert performance marketer with direct access to ad platform accounts. Your goal is to help create, optimize, and scale paid advertising campaigns that drive efficient customer acquisition.

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/paid-ads/SKILL.md

Quality

Content

50%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-organized, genuinely concrete paid-ads playbook — specific thresholds, naming examples, worked copy examples, and setup checklists make it highly actionable for strategy and copy tasks. Its weaknesses are token efficiency (much of it restates marketing knowledge Claude already has), the absence of an explicit end-to-end workflow with validation gates, and a fully monolithic structure with no reference files despite section content that clearly warrants them.

Suggestions

Cut knowledge Claude already has — PAS/BAB formula explanations, metric definitions (CPM/CTR/CPA/ROAS parentheticals), generic CTA lists, and the boilerplate "When to Use" line — keeping only the skill-specific judgment calls (thresholds, platform selection heuristics, checklists).

Add an explicit sequenced workflow with validation gates, e.g.: 1) gather context (Before Starting) → 2) confirm conversion tracking is installed and tested → 3) select platform → 4) structure and launch per checklist → 5) wait through learning phase before optimizing → 6) weekly review checklist.

Split platform-specific material (Google/Meta/LinkedIn setup checklists, per-platform audience details) into one-level-deep reference files (e.g., references/google-ads.md, references/meta.md) linked from a concise overview section in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The ~550-line body spends substantial space on concepts Claude already knows: PAS and BAB copy formulas, metric definitions like "CPM (cost per 1,000 impressions)" and "CTR (click-through rate)", generic CTA lists ("Learn More", "Buy Now"), and boilerplate video-structure advice, plus a filler "When to Use" line ("This skill is applicable to execute the workflow or actions described in the overview."). This is noticeably verbose with several padded sections rather than only minor trim opportunities.	2 / 5
Actionability	The guidance is concrete and specific: "70% to proven/safe campaigns", "Increase budgets 20-30% at a time", "50+ conversions" before automated bidding, LinkedIn CPCs "$8-15+", example naming strings ("META_Conv_Lookalike-Customers_FreeTrial_2024Q1"), worked ad-copy examples, and platform setup checklists. It falls short of 5 because the description promises "direct access to ad platform accounts" yet the body provides no mechanism (API, tool, or script) for actually accessing or executing against those accounts.	4 / 5
Workflow Clarity	Sections imply a lifecycle (context gathering → platform selection → structure → optimization → reporting) and the setup checklists act as implicit checkpoints, but there is no explicit end-to-end sequence tying the phases together, and validation/feedback loops (e.g., verify conversion tracking before scaling) are not stated as gates. This matches the anchor of steps present but checkpoints missing or implicit.	3 / 5
Progressive Disclosure	The body is well-sectioned with clear headers, but everything is inlined in a single ~550-line SKILL.md with no bundle files: the platform-specific setup guides, per-platform audience tables, and ad-copy frameworks are natural candidates for one-level-deep reference files. This fits the anchor of some structure but with content that should be separate kept inline.	3 / 5
	Total	12 / 20 Passed

Description

45%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 identifies the paid-ads domain and a set of actions, but is written in role-play second person, uses generic verbs ("optimize", "scale") rather than concrete capabilities, and provides no "Use when..." trigger guidance. It also omits the platform names (Google Ads, Meta, LinkedIn) that would both sharpen specificity and distinguish it from neighboring marketing skills.

Suggestions

Rewrite in third person, e.g.: "Creates, optimizes, and scales paid advertising campaigns across Google Ads, Meta, LinkedIn, and TikTok — campaign structure, audience targeting, ad copy, budget allocation, and performance optimization toward CPA/ROAS targets."

Add an explicit trigger clause, e.g.: "Use when the user mentions paid ads, ad campaigns, ad spend, PPC, Facebook/Instagram/Meta ads, Google Ads, LinkedIn ads, retargeting, or wants to improve CPA/ROAS."

Replace vague claims like "direct access to ad platform accounts" and "efficient customer acquisition" with the concrete deliverables the skill actually provides (setup checklists, copy frameworks, optimization levers).

Dimension	Reasoning	Score
Specificity	The description names the domain ("paid advertising campaigns") and three actions ("create, optimize, and scale"), but the verbs are generic and no concrete capabilities (platforms, campaign types, tracking setup) are stated. The second-person voice ("You are an expert...", "Your goal is to help...") triggers the rubric's mandatory 1-point specificity penalty, reducing the base level of 3 to 2.	2 / 5
Completeness	The "what" is reasonably clear ("help create, optimize, and scale paid advertising campaigns that drive efficient customer acquisition") but there is no "Use when..." clause or equivalent explicit trigger guidance, which the rubric caps at 3. Not level 4 because the "when" is entirely absent rather than merely imprecise; not level 2 because the "what" is specific to the paid-ads domain.	3 / 5
Trigger Term Quality	Phrases like "paid advertising campaigns", "ad platform accounts", and "customer acquisition" are relevant, but the description misses the natural terms users would actually say such as "Facebook/Meta ads", "Google Ads", "PPC", or "ad spend". This matches the anchor for some relevant keywords while missing common variations or synonyms.	3 / 5
Distinctiveness Conflict Risk	"Paid advertising campaigns" and "efficient customer acquisition" carve out a specific niche, but without platform names or concrete triggers the description could still overlap with adjacent marketing skills the body itself lists (copywriting, page-cro, analytics-tracking). This fits the "somewhat specific but could still overlap with similar skills" anchor.	3 / 5
	Total	11 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (558 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/paid-ads/SKILL.md
Revision: 64adc55

Reviewed: 14 days ago

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.

paid-ads

Table of Contents

Is this your skill?