marketing-automation
Generate marketing deliverables across CRO, copywriting, SEO, analytics, and growth using 23 specialized sub-skills with clear objectives, constraints, and validation.
58
41%
Does it follow best practices?
Impact
83%
2.96xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent-skills/marketing-automation/SKILL.mdQuality
Discovery
32%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 a clear marketing domain with multiple sub-disciplines but lacks the specificity and explicit trigger guidance needed for reliable skill selection. It tells Claude this skill handles marketing tasks but doesn't provide concrete examples of deliverables or clear 'Use when...' triggers that would help distinguish it from other content or analytics skills.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user asks for landing page copy, SEO audits, conversion optimization, email campaigns, or marketing analytics'
Replace 'generate marketing deliverables' with specific concrete actions like 'Write landing page copy, conduct keyword research, analyze conversion funnels, create email sequences'
Include natural user terms like 'blog post', 'ad copy', 'A/B test', 'traffic analysis', 'content strategy' that users would actually say
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (marketing) and lists categories (CRO, copywriting, SEO, analytics, growth), but 'generate marketing deliverables' is somewhat vague. The mention of '23 specialized sub-skills' adds structure but doesn't specify concrete actions like 'write landing page copy' or 'analyze conversion funnels'. | 2 / 3 |
Completeness | Describes what it does (generate marketing deliverables) but completely lacks a 'Use when...' clause or any explicit trigger guidance. The 'when' is entirely missing, which per the rubric should cap this at 2, but the 'what' is also weak, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords (CRO, copywriting, SEO, analytics, growth) that users might mention, but misses common natural variations like 'conversion rate', 'blog post', 'keyword research', 'A/B testing', or 'content marketing'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of marketing disciplines (CRO, SEO, copywriting) provides some distinctiveness, but 'marketing deliverables' is broad enough to potentially conflict with other content creation or analytics skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive framework for marketing deliverables with good structural organization and useful examples. However, it suffers from being too abstract - the sub-skills are listed but not defined with actionable detail, the validation steps lack concrete criteria, and the workflow relies on placeholder templates rather than executable guidance. The skill would benefit from either linking to detailed sub-skill files or providing more concrete decision trees and validation methods.
Suggestions
Replace placeholder templates with concrete, filled-in examples showing exact inputs and outputs for at least 2-3 sub-skills
Add specific validation criteria for Step 4 (e.g., 'KPI alignment passes if the asset mentions the target metric at least once in the CTA')
Create separate files for each sub-skill category (CRO.md, COPYWRITING.md, etc.) and link to them, keeping SKILL.md as a routing overview
Remove the metadata/version section and multi-agent workflow details which don't add actionable value for Claude
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary elements like the metadata section, multi-agent workflow details, and version information that don't add actionable value. The 23 sub-skills table is useful but the descriptions are minimal to the point of being redundant with the names. | 2 / 3 |
Actionability | Provides structured templates and examples, but the guidance is largely abstract YAML/markdown templates with placeholders rather than executable code or concrete commands. The 'claude task' command shown is pseudocode, and the sub-skill selection is vague ('select the appropriate sub-skill') without concrete decision criteria. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced, but validation is weak - Step 4's checklist is superficial (just checkboxes for 'KPI alignment') without concrete validation methods. No feedback loops for error recovery or specific criteria for what constitutes passing validation. | 2 / 3 |
Progressive Disclosure | Content is organized with clear sections and tables, but it's monolithic - all 23 sub-skills are listed inline rather than linked to detailed sub-skill files. The 'Related Skills' links at the bottom suggest a structure exists but the main content doesn't leverage progressive disclosure effectively. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- supercent-io/skills-template
- Commit
c033769
- Reviewed
Table of Contents
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.