{ "skill_name": "email", "evals": [ { "id": 1, "source": "cold-outreach", "prompt": "Write a cold email to VP of Marketing at mid-size B2B SaaS companies. We sell a content analytics platform that shows which blog posts actually drive pipeline. Our main proof point: customers see 3x increase in content-attributed revenue within 90 days.", "expected_output": "Should check for product-marketing-context.md first. Should route to cold-outreach mode. Should write like a peer, not a vendor. Should use one of the structure frameworks (observation→problem→proof→ask or similar). Subject line should be 2-4 words, lowercase, internal-looking. Every sentence should earn its place. Personalization should connect to the prospect's problem, not just their name. Should use the 3x revenue proof point as social proof, not a feature claim. CTA should be low-friction (not 'book a demo'). Should provide 2-3 variations. Should include a quality check against the guidelines.", "assertions": [ "Checks for product-marketing-context.md", "Routes to cold-outreach mode", "Writes like a peer, not a vendor", "Uses a structure framework from the skill", "Subject line is short, lowercase, internal-looking", "Every sentence earns its place (concise)", "Personalization connects to prospect's problem", "Uses proof point as social proof", "CTA is low-friction", "Provides 2-3 variations" ], "files": [] }, { "id": 2, "source": "cold-outreach", "prompt": "Help me write a cold email to CTOs at enterprise companies. I sell cybersecurity training. My current email has a 2% open rate and 0% reply rate.", "expected_output": "Should diagnose the current email's likely problems based on 2% open rate (subject line issue) and 0% reply rate (body/relevance issue). Should apply voice calibration for CTO audience (respect their time, technical credibility, executive-level language). Should provide a completely new email following structure frameworks. Subject line should be 2-4 words, look internal. Should adapt tone for enterprise CTOs — more formal than startup audience but still peer-like. Should provide the email plus analysis of why each element works.", "assertions": [ "Diagnoses problems from the performance data", "Identifies subject line as likely open rate issue", "Applies voice calibration for CTO audience", "Subject line is short, lowercase, internal-looking", "Adapts tone for enterprise audience", "Uses structure framework from the skill", "Explains why each element works" ], "files": [] }, { "id": 3, "source": "cold-outreach", "prompt": "write me a follow-up sequence. prospect didn't reply to my first email about our HR software. how many should I send and how far apart?", "expected_output": "Should trigger on casual phrasing. Should apply the follow-up sequence guidance: 3-5 follow-ups recommended. Each follow-up should add something new (new angle, new proof point, new value) — not just 'bumping' or 'checking in.' Should provide timing recommendations between emails. Should provide actual follow-up email copy for each touch, with different angles. Should include a breakup email at the end. Should note that each follow-up should be shorter than the previous.", "assertions": [ "Triggers on casual phrasing", "Recommends 3-5 follow-up emails", "Each follow-up adds something new", "Does not use 'just bumping' or 'checking in' language", "Provides timing between emails", "Provides actual copy for each follow-up", "Includes a breakup email", "Follow-ups get progressively shorter" ], "files": [] }, { "id": 4, "source": "cold-outreach", "prompt": "Review this cold email and tell me what's wrong: 'Dear Sir/Madam, I hope this email finds you well. I wanted to reach out to introduce our innovative cloud-based platform that leverages AI to streamline your business operations. We have helped over 500 companies transform their workflows. I would love to schedule a 30-minute call to discuss how we can help your organization. Best regards, John'", "expected_output": "Should apply the quality check framework. Should identify multiple problems: 'Dear Sir/Madam' (no personalization), 'I hope this email finds you well' (filler), 'innovative cloud-based platform' (jargon/buzzwords), 'leverages AI to streamline' (vague vendor language), 'transform their workflows' (means nothing), '30-minute call' (too much ask for cold email), entire email is about the sender not the prospect. Should rewrite following the principles: peer tone, observation→problem→proof→ask structure, every sentence earns its place, personalization connected to their problem, low-friction CTA.", "assertions": [ "Identifies lack of personalization", "Identifies filler phrases", "Identifies jargon and buzzwords", "Identifies vendor language vs peer language", "Identifies CTA as too high-friction", "Notes email is sender-focused not prospect-focused", "Provides a rewritten version", "Rewrite follows cold email principles" ], "files": [] }, { "id": 5, "source": "cold-outreach", "prompt": "What are the best subject lines for cold emails? I want to maximize open rates.", "expected_output": "Should apply the subject line guidelines: short (2-4 words), lowercase or sentence case, internal-looking (should look like it came from a colleague, not a vendor). Should provide examples following these principles. Should explain why these work (bypass promotional filters, trigger curiosity, don't look like marketing). Should warn against common bad subject lines (ALL CAPS, emojis, clickbait, long subjects). Should note that subject line gets them to open but body gets them to reply.", "assertions": [ "Applies subject line guidelines (2-4 words, lowercase, internal-looking)", "Provides specific examples", "Explains why the format works", "Warns against common bad subject line patterns", "Notes distinction between open rate and reply rate" ], "files": [] }, { "id": 6, "source": "cold-outreach", "prompt": "Can you help me set up an automated email drip campaign for leads who download our whitepaper?", "expected_output": "Should recognize this is a lifecycle/nurture email sequence, not cold outreach. Should route to the sequences mode, which handles drip campaigns, lead nurture sequences, and lifecycle emails. Cold outreach is specifically for unsolicited outbound outreach to prospects who haven't opted in. Should make this distinction clear.", "assertions": [ "Recognizes this as lifecycle/nurture email, not cold outreach", "Routes to or references sequences mode", "Explains the distinction between cold email and lifecycle email", "Does not attempt to design a nurture sequence using cold email patterns" ], "files": [] }, { "id": 7, "source": "sequences", "prompt": "Create a welcome email sequence for new users who sign up for our project management tool's free trial. The trial is 14 days. We want to get them to their aha moment (creating their first project and inviting a team member).", "expected_output": "Should check for product-marketing-context.md first. Should route to sequences mode. Should create a welcome sequence (5-7 emails) following the core principles: one email one job, value before ask. Should map each email to a specific goal in the 14-day trial journey. Should include timing/delays between emails. Each email should follow the email copy structure: hook → context → value → CTA → sign-off. Should include subject lines following the subject line strategy. Should align sequence with the aha moment (first project + team invite). Output should follow the structured format with sequence overview and per-email specs.", "assertions": [ "Checks for product-marketing-context.md", "Routes to sequences mode", "Creates 5-7 email welcome sequence", "Follows one email one job principle", "Maps emails to trial timeline (14 days)", "Includes timing between emails", "Each email has hook, context, value, CTA", "Includes subject lines for each email", "Aligns with stated aha moment", "Output follows structured per-email format" ], "files": [] }, { "id": 8, "source": "sequences", "prompt": "We need a lead nurture sequence for people who download our 'State of DevOps 2024' report. Goal is to get them to book a demo of our CI/CD platform.", "expected_output": "Should create a lead nurture sequence (6-8 emails). Should follow value before ask — first emails should provide related value, not immediately push for demo. Should map the sequence from awareness (report download) through consideration (related content, case studies) to decision (demo request). Should include timing between emails. Each email should have clear subject line, hook, single CTA. Should gradually increase commitment asks across the sequence.", "assertions": [ "Creates 6-8 email lead nurture sequence", "Follows value before ask principle", "Maps from awareness through consideration to decision", "Includes timing between emails", "Each email has clear subject line and single CTA", "Gradually increases commitment asks", "Connects to original download topic" ], "files": [] }, { "id": 9, "source": "sequences", "prompt": "our email open rates have tanked. used to be 35% now we're at 18%. what's going on and how do we fix our subject lines?", "expected_output": "Should trigger on casual phrasing. Should diagnose potential causes of declining open rates: sender reputation, list hygiene, subject line quality, sending frequency, deliverability issues. Should apply the subject line strategy from the skill: test curiosity vs benefit vs urgency patterns, personalization, optimal length. Should recommend a re-engagement campaign to clean the list. Should provide specific subject line formulas and examples. Should suggest testing framework for subject lines.", "assertions": [ "Triggers on casual phrasing", "Diagnoses potential causes beyond just subject lines", "Addresses sender reputation and deliverability", "Recommends list hygiene or re-engagement", "Applies subject line strategy with specific patterns", "Provides subject line formulas and examples", "Suggests testing framework" ], "files": [] }, { "id": 10, "source": "sequences", "prompt": "Build a re-engagement sequence for subscribers who haven't opened any emails in 90 days. We have about 5,000 inactive subscribers.", "expected_output": "Should create a re-engagement sequence (3-4 emails). Should follow the re-engagement pattern: first email acknowledges absence and offers value, middle emails escalate with compelling reasons to re-engage, final email is a clear 'last chance' before removal. Should recommend aggressive subject lines to break through. Should include a sunset policy (remove non-responders after sequence completes). Should address the impact on deliverability of keeping inactive subscribers.", "assertions": [ "Creates 3-4 email re-engagement sequence", "Acknowledges absence in first email", "Escalates through the sequence", "Includes 'last chance' final email", "Recommends sunset policy for non-responders", "Addresses deliverability impact of inactive subscribers", "Uses compelling subject lines" ], "files": [] }, { "id": 11, "source": "sequences", "prompt": "What's the ideal timing for our onboarding email sequence? We send the first email immediately after signup, but we're not sure about the rest.", "expected_output": "Should provide timing guidance for onboarding sequences. Should reference the timing and delays framework: immediate first email (welcome/confirmation), then suggest data-driven timing based on user behavior triggers vs fixed time delays. Should recommend behavior-triggered emails when possible (user completed action → next email) with time-based fallbacks. Should provide typical timing patterns for SaaS onboarding (day 0, day 1, day 3, day 5, day 7, etc.). Should note that optimal timing depends on product complexity and trial length.", "assertions": [ "Provides timing guidance for onboarding sequences", "Recommends immediate first email", "Discusses behavior-triggered vs time-based timing", "Provides typical timing patterns", "Notes timing depends on product and trial length", "Recommends behavior triggers with time-based fallbacks" ], "files": [] }, { "id": 12, "source": "sequences", "prompt": "Help me optimize our post-signup onboarding experience. Users sign up but 60% never complete setup.", "expected_output": "Should recognize this is an in-app onboarding optimization task, not an email sequence task. Should defer to or cross-reference the cro skill, which handles in-app onboarding flows, checklists, and activation optimization. May offer to help with the email component of onboarding but should make clear that cro is the primary skill for this task.", "assertions": [ "Recognizes this as in-app onboarding optimization", "References or defers to cro skill", "Does not attempt full onboarding redesign using email patterns", "May offer email component support" ], "files": [] } ] }