Skills › Marketing Skills › sales-enablement › evals.json
evals.json
153 lines · skills/sales-enablement/evals/evals.json at 88c79f6
1{
2 "skill_name": "sales-enablement",
3 "evals": [
4 {
5 "id": 1,
6 "prompt": "Help me create a sales deck for our B2B SaaS product. We sell an employee engagement platform to HR directors at companies with 500-5000 employees. Our main differentiator is real-time pulse surveys with AI-powered insights.",
7 "expected_output": "Should check for product-marketing.md first. Should apply the 10-12 slide sales deck framework: Title, Problem/Stakes, Current Solutions Failing, Vision, Product/Solution, How It Works, Proof (case studies/metrics), Pricing, Why Now, and Next Steps. Should tailor the deck to the HR director audience and employee engagement space. Should incorporate the differentiator (real-time pulse surveys + AI insights). Should provide slide-by-slide content recommendations with speaker notes. Should recommend visual direction.",
8 "assertions": [
9 "Checks for product-marketing.md",
10 "Applies 10-12 slide framework",
11 "Includes Problem, Solution, Proof, Pricing, Next Steps slides",
12 "Tailors to HR director audience",
13 "Incorporates stated differentiator",
14 "Provides slide-by-slide content",
15 "Includes speaker notes or talking points"
16 ],
17 "files": []
18 },
19 {
20 "id": 2,
21 "prompt": "Our sales team keeps getting the same objections. The top ones are: 'we already use SurveyMonkey,' 'we don't have budget right now,' and 'our team is too small to need this.' Help me create an objection handling doc.",
22 "expected_output": "Should apply the objection handling framework with the response structure for each objection. Should categorize the objections (competitor/status quo, budget, need/timing). For each objection, should provide: acknowledge, reframe, evidence/proof, bridge to value, and follow-up question. Should provide 2-3 response variations per objection for different contexts. Should organize as a document sales reps can reference quickly during calls.",
23 "assertions": [
24 "Applies objection handling framework",
25 "Categorizes the three objections",
26 "Provides structured response for each (acknowledge, reframe, evidence, bridge)",
27 "Provides 2-3 response variations per objection",
28 "Organizes for quick reference during calls",
29 "Categorizes objections using the skill's framework (competitor, budget, need/timing)"
30 ],
31 "files": []
32 },
33 {
34 "id": 3,
35 "prompt": "i need a one-pager we can leave behind after sales meetings. something that summarizes our product and key benefits.",
36 "expected_output": "Should trigger on casual phrasing. Should apply the one-pager/leave-behind framework. Should include: headline with core value proposition, key benefits (3-5), social proof (customer logos, key metric), how it works (simplified), pricing summary or 'starting at' range, and clear next step CTA. Should recommend design principles for a one-pager: scannable, visual hierarchy, not text-heavy. Should note this should fit on one page (front, or front and back).",
37 "assertions": [
38 "Triggers on casual phrasing",
39 "Applies one-pager/leave-behind framework",
40 "Includes headline, benefits, social proof, how it works, CTA",
41 "Keeps to one page format",
42 "Recommends scannable design",
43 "Provides specific content for each section"
44 ],
45 "files": []
46 },
47 {
48 "id": 4,
49 "prompt": "Create a demo script for our analytics dashboard product. Typical demo is 30 minutes with a VP of Marketing.",
50 "expected_output": "Should apply the demo script/talk track framework with the 5-part structure. Should include: opening (rapport, agenda setting, discovery questions), problem validation (confirm their pain), solution walkthrough (show product addressing their pain), proof points (metrics, case studies during demo), and close (next steps, timeline). Should time-box each section for 30 minutes. Should include key questions to ask during discovery. Should note when to customize based on prospect's answers.",
51 "assertions": [
52 "Applies 5-part demo script structure",
53 "Includes opening with discovery questions",
54 "Includes problem validation",
55 "Includes solution walkthrough",
56 "Includes proof points",
57 "Includes close with next steps",
58 "Time-boxes for 30 minutes",
59 "Notes customization based on prospect responses"
60 ],
61 "files": []
62 },
63 {
64 "id": 5,
65 "prompt": "Help me build an ROI calculator we can use during sales calls. We need to show prospects how much money they'll save by switching to our product.",
66 "expected_output": "Should apply the ROI calculator framework. Should define inputs (what data to collect from the prospect: team size, current costs, time spent on manual processes), calculation methodology (how to compute savings), and output format (visual showing ROI timeline, payback period, annual savings). Should recommend keeping calculations transparent and conservative. Should suggest validating assumptions during the sales call. Should provide the calculator structure and formula logic.",
67 "assertions": [
68 "Applies ROI calculator framework",
69 "Defines required inputs",
70 "Provides calculation methodology",
71 "Recommends conservative assumptions",
72 "Includes ROI timeline and payback period",
73 "Suggests validating assumptions during calls",
74 "Provides calculator structure"
75 ],
76 "files": []
77 },
78 {
79 "id": 6,
80 "prompt": "We need a public comparison page showing how we stack up against Zendesk and Intercom.",
81 "expected_output": "Should recognize this is a public-facing competitor comparison page, not internal sales collateral. Should defer to or cross-reference the competitors skill, which handles public comparison and alternatives pages. Sales-enablement covers internal materials (battle cards, objection handling) while competitors handles SEO-focused public comparison content.",
82 "assertions": [
83 "Recognizes this as a public comparison page",
84 "References or defers to competitors skill",
85 "Explains the distinction between internal and public collateral",
86 "Does not attempt public SEO comparison page using sales enablement patterns"
87 ],
88 "files": []
89 },
90 {
91 "id": 7,
92 "prompt": "Make an objection-handling doc for when prospects say 'we're also looking at Northwind.' Include a 'why we win' section. We don't track win/loss reasons anywhere yet.",
93 "expected_output": "Should build the objection doc using the response framework, but because there is no win/loss data, should frame 'why we win' points as hypotheses for reps to test and say what evidence would confirm each (e.g., start logging loss reasons, call snippets, customer quotes). Should keep any Northwind claims dated and sourced and avoid 'they don't have X' unless verified. Should include where Northwind is the better fit.",
94 "assertions": [
95 "Labels 'why we win' as hypotheses given no win/loss data",
96 "Suggests a way to gather the missing evidence",
97 "Avoids unverified 'they don't have X' claims about Northwind",
98 "Includes situations where Northwind is the better fit"
99 ]
100 },
101 {
102 "id": 8,
103 "prompt": "Can you make us a battle card? We keep running into them in deals.",
104 "expected_output": "Should recognize the battle card request belongs to sales-enablement. Because no competitor is named and no context identifies one, should ask which competitor in one short question and not produce a placeholder or guessed card. May offer the likely candidate from context for the user to confirm and mention what else would sharpen the card (segment, win/loss notes).",
105 "assertions": [
106 "Asks which competitor before drafting",
107 "Does not produce a battle card for a guessed competitor",
108 "Keeps the clarifying ask short"
109 ]
110 },
111 {
112 "id": 9,
113 "prompt": "Our VP Finance prospect at a 300-person logistics company just told my AE 'Acme does this for half the price.' The AE has a follow-up call in an hour. What should she say?",
114 "expected_output": "Should treat this as a live deal objection, not produce a generic objection doc. Should name the likely concern behind it (value-for-price vs. hard budget) and give a question that tells the two apart. Should give one response the AE can say as written: acknowledge, address the concern, one proof point, end with a question. Should not invent stats, customers, or Acme pricing facts; if no proof is provided, should say what proof to pull or verify. Should say when it's not worth fighting (a real fit gap).",
115 "assertions": [
116 "Responds to the specific deal rather than producing a generic objection doc",
117 "Names the likely concern behind the objection",
118 "Offers a question to tell possible concerns apart",
119 "Gives one say-as-written response ending in a question",
120 "Does not invent stats, customers, or competitor pricing",
121 "Mentions when to qualify out instead of fighting"
122 ],
123 "files": []
124 },
125 {
126 "id": 10,
127 "prompt": "Here are our last quarter's closed-lost reasons from Salesforce: 14 say 'price', 6 say 'timing', 4 say 'went with Acme', 3 say 'no decision'. Tell me why we're losing and update our battle card.",
128 "expected_output": "Should run win-loss analysis and flag that rep-entered CRM reasons are biased toward price and timing and rarely name the real cause. Should separate competitive losses from no-decision/timing. Should report counts with sample sizes rather than percentages and treat small slices as signals. Should not write new 'why we lose' battle card claims from one-word CRM reasons alone; should label them low-confidence and recommend buyer interviews or transcript review (with sample questions) to confirm before updating the card.",
129 "assertions": [
130 "Flags bias in rep-entered CRM loss reasons",
131 "Separates competitive losses from no-decision or timing",
132 "Reports counts with sample sizes",
133 "Treats findings from one-word CRM reasons as low-confidence",
134 "Recommends interviews or transcripts before changing the battle card"
135 ],
136 "files": []
137 },
138 {
139 "id": 11,
140 "prompt": "Write me a cold call opener and voicemail for calling heads of growth at SaaS companies that just posted growth marketer jobs.",
141 "expected_output": "Should load the cold call scripts reference. Opener should follow four beats: name and company plainly, a permission-based ask for 30 seconds, the specific reason tied to the job posting and the problem it implies, and one question about their situation. Should avoid 'Did I catch you at a bad time?' and 'How are you today?'. Voicemail should be 20-30 seconds with name, one specific reason, a promise to send an email, and the name repeated, followed by an email referencing the voicemail. Should include brief responses to first-minute pushback such as 'just send me an email' and 'not interested', and mention Do Not Call scrubbing.",
142 "assertions": [
143 "Uses a permission-based opener",
144 "Ties the reason to the job posting signal",
145 "Ends the opener with a question about their situation",
146 "Avoids 'Did I catch you at a bad time?' and 'How are you today?'",
147 "Voicemail is about 20-30 seconds and points to a follow-up email",
148 "Includes responses to common first-minute pushback"
149 ],
150 "files": []
151 }
152 ]
153}