Content
71%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A dense, well-structured playbook with genuinely actionable channel-specific numbers and validation checkpoints on every workflow. Its main weaknesses are re-teaching basic on-page SEO and, critically, a progressive-disclosure structure that references five bundle files which are entirely missing from the skill directory.
Suggestions
Ship the referenced bundle files (references/hubspot-workflows.md, references/campaign-templates.md, references/international-playbooks.md, references/attribution-guide.md, scripts/calculate_cac.py) or remove the dead links and inline the essential content.
Add a one-line error-recovery path after each **Validation:** step (e.g., what to check when UTMs don't appear in HubSpot or the Screaming Frog crawl reports critical errors).
Trim the On-Page Optimization checklist down to the skill-specific thresholds and drop generic SEO guidance (title length, meta description length, one H1 per page) that Claude already knows.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Dense tables and checklists (channel matrix, budget allocation, benchmarks) keep token cost low and assume competence, but the On-Page Optimization section ("Title tag: Primary keyword + brand (60 chars)", "Meta description: CTA + value prop (155 chars)") re-teaches standard SEO knowledge Claude already has. | 4 / 5 |
Actionability | Concrete, executable specifics throughout ("Start $50/day per campaign", "Scale 20% weekly if CAC < target", "Maintain negative keyword list (100+)", "switch to Target CPA after 50+ conversions", exact UTM parameter block), but much of the guidance is benchmark-level rather than copy-paste ready, and the sole script invocation (`python scripts/calculate_cac.py`) points to a file that does not exist in the bundle. | 4 / 5 |
Workflow Clarity | Every major workflow (campaign planning, LinkedIn/Google Ads setup, attribution, MQL→SQL handoff) is numbered and ends in an explicit validation checkpoint ("**Validation:** LinkedIn Insight Tag firing on all pages", "**Validation:** UTM parameters appear in HubSpot contact records"), but no error-recovery guidance is given for when a validation fails, which the top anchor requires. | 4 / 5 |
Progressive Disclosure | In-body structure is well organized (References table, per-section "See [campaign-templates.md](references/campaign-templates.md)" links), but scored against the actual bundle: no references/, scripts/, or assets/ directories exist, so all five referenced paths (hubspot-workflows.md, campaign-templates.md, international-playbooks.md, attribution-guide.md, calculate_cac.py) are dead links. | 3 / 5 |
Total | 15 / 20 Passed |