arkaos 4.26.0 → 4.27.0

package/config/evals/sales.yaml

@@ -0,0 +1,437 @@
+# --- BEGIN imported (marketing-skills, MIT) — regenerated by scripts/tools/evals_import.py ---
+- id: sales-prospecting-01
+  department: sales
+  prompt: We're a B2B SaaS selling RevOps tooling at $30K ACV. Build me a list of 25 prospects.
+  expected_properties:
+  - Checks for product-marketing.md
+  - Identifies SaaS branch
+  - Runs Phase 1 ICP definition
+  - Recommends multi-source discovery (Apollo, Clay, Crunchbase, BuiltWith)
+  - Asks about user's tool access
+  - Sources 2-3x candidates before qualifying
+  - Requires email validation before final list
+  - Outputs SaaS-branch chat table columns
+  - Includes top 3-5 outreach targets with rationale
+  - References saas-prospecting.md
+  rubric: 'Should check for product-marketing.md first. Should identify this as the SaaS branch.
+    Should run Phase 1 ICP definition pulling from product-marketing context or asking targeted
+    questions (target industry, headcount range, tech stack signals, funding stage). Should
+    propose discovery sources appropriate for SaaS at $30K ACV: Apollo for breadth, Clay for
+    waterfall enrichment, Crunchbase for funding signals, BuiltWith/Wappalyzer for tech stack,
+    LinkedIn Sales Nav for decision-mapping (manual). Should ask about user''s tool access
+    before assuming. Should source 50-75 candidates (2-3x target) before qualifying. Should
+    flag that email validation via Truelist or similar is non-negotiable before final list.
+    Should output SaaS-branch chat table columns (Score | Company | Industry | Size | Signal
+    | Contact | Email status | Confidence) followed by top 3-5 hot leads with one-sentence
+    rationale each. Should reference references/saas-prospecting.md.'
+  tags:
+  - prospecting
+  - imported
+- id: sales-prospecting-02
+  department: sales
+  prompt: Find me 25 SaaS companies that just raised a Series B in the last 60 days and use
+    HubSpot.
+  expected_properties:
+  - Identifies as SaaS branch
+  - Identifies funding signal + tech stack filter
+  - Recommends Crunchbase or Pitchbook for funding
+  - Recommends BuiltWith or Clay for HubSpot verification
+  - Notes data freshness concerns
+  - Recommends cross-source verification
+  - Outputs signal column showing round + date
+  - Requires email validation
+  rubric: 'Should recognize this as a SaaS branch prospecting task with very specific signals.
+    Should identify the trigger event (Series B in last 60 days) and the technographic filter
+    (uses HubSpot). Should recommend a workflow: (1) Crunchbase or Pitchbook for funding signal
+    filter (Series B + date), (2) BuiltWith or Clay''s waterfall for tech stack verification
+    (uses HubSpot), (3) cross-check via business websites and LinkedIn. Should note this is
+    a tight ICP that should yield high-confidence matches if data sources are current. Should
+    flag freshness concerns: Crunchbase data depends on self-reporting, BuiltWith refresh
+    cycles aren''t real-time. Should recommend cross-source verification for the funding date
+    specifically. Should output a SaaS-branch chat table with the funding round + date in
+    the Signal column. Should include verified email validation before delivering.'
+  tags:
+  - prospecting
+  - imported
+- id: sales-prospecting-03
+  department: sales
+  prompt: I run a marketing agency. Find me 25 mid-market manufacturers in the Midwest US
+    who recently hired a new CMO.
+  expected_properties:
+  - Identifies B2B branch (not SaaS)
+  - Runs Phase 1 ICP definition with NAICS or industry classification
+  - Specifies mid-market size band
+  - Specifies Midwest US geography
+  - Identifies trigger event (CMO hire)
+  - Recommends Apollo/ZoomInfo + LinkedIn Sales Nav
+  - Notes CMO hires often only on LinkedIn
+  - Outputs B2B-branch chat table
+  - Mentions CAN-SPAM and source URL capture
+  - References b2b-prospecting.md
+  rubric: 'Should identify this as the B2B branch (manufacturers, not SaaS). Should run Phase
+    1 ICP definition: industry (manufacturing, with NAICS code if precision matters), size
+    (mid-market = typically 200-2000 employees), geography (Midwest US states), trigger event
+    (CMO hire in last 90-180 days). Should propose discovery: Apollo or ZoomInfo for firmographic
+    filter, LinkedIn Sales Nav for CMO hire detection (job changes), Google Alerts on press
+    releases for trigger events. Should warn that CMO hires aren''t always in public databases
+    — LinkedIn Sales Nav alerts on job changes is the most reliable source. Should output
+    B2B-branch chat table with the CMO trigger as the signal. Should reference references/b2b-prospecting.md.
+    Should mention compliance: GDPR less likely (US-only), CAN-SPAM applies, capture source
+    URL + date for every contact.'
+  tags:
+  - prospecting
+  - imported
+- id: sales-prospecting-04
+  department: sales
+  prompt: We sell to industrial distributors. Build a list of 25 prospects.
+  expected_properties:
+  - Identifies B2B branch
+  - Runs Phase 1 ICP definition asking targeted questions
+  - Recommends industry-specific directories beyond Apollo/ZoomInfo
+  - Mentions trade show exhibitor lists
+  - Identifies relevant trigger events
+  - Warns about data spottiness for industrial
+  - Recommends cross-verification with business websites + LinkedIn
+  - Notes ICP fit precision over volume
+  rubric: 'Should identify this as the B2B branch. Should run Phase 1 ICP definition asking
+    targeted questions: distributor size, geography, vertical specialty, buying patterns.
+    Should propose discovery: Apollo or ZoomInfo for firmographic depth, industry-specific
+    directories (e.g., NAW for wholesale distributors, ISA for industrial sales agencies),
+    trade show exhibitor lists. Should note state business registries and Chamber of Commerce
+    as verification sources. Should propose trigger events: new location, recent acquisition,
+    leadership change, posting RFPs. Should warn that industrial distributor data is often
+    spotty in major databases — cross-check with company website + LinkedIn for size and ownership
+    signals. Should output B2B-branch chat table. Should note ICP fit precision matters more
+    than initial volume for this kind of niche prospecting.'
+  tags:
+  - prospecting
+  - imported
+- id: sales-prospecting-05
+  department: sales
+  prompt: I build websites for local businesses. Find me 15 prospects near Austin, TX who
+    don't have a website.
+  expected_properties:
+  - Identifies Local SMB branch
+  - Asks about business category if not specified
+  - Defaults radius to 20km
+  - Runs browser research workflow
+  - Applies 4-tier website status classification
+  - Uses Hot/Warm/Cold/Skip scoring
+  - Outputs Local SMB chat table columns
+  - Adds top 3 outreach targets
+  - References local-prospecting.md
+  - Warns against bulk-scraping Google Maps
+  rubric: 'Should identify as Local SMB branch. Should run Phase 1 ICP definition: business
+    category (ask user — gyms, restaurants, salons, etc. matter), radius (default 20 km from
+    Austin), target count (15). Should run the browser research workflow: search Google Maps
+    for category + Austin, build candidate list from visible results, cross-check via business
+    name + city web search to verify website status. Should apply the 4-tier website status
+    classification (No site found / Social only / Weak site / Has site) — prioritize No site
+    + Social only as Hot. Should score: Hot (no site + active + phone + within radius), Warm
+    (weak site), Cold (has site), Skip (closed/duplicate/out of scope). Should output Local
+    SMB chat table (Score | Business | Category | Area | Distance | Website status | Website/Social
+    | Phone | Why prospect | Confidence). Should add ''Best first outreach targets'' top 3
+    with reasoning. Should reference references/local-prospecting.md. Should warn against
+    bulk-scraping Google Maps (ToS violation) — browser-assisted research only.'
+  tags:
+  - prospecting
+  - imported
+- id: sales-prospecting-06
+  department: sales
+  prompt: I have a list of 200 prospect emails from Apollo. How do I know which ones are deliverable
+    before I start outreach?
+  expected_properties:
+  - Recommends Truelist for bulk validation
+  - Explains email_state values (ok, email_invalid, risky, unknown, accept_all)
+  - Warns Apollo accuracy is 60-80%
+  - Cites 2% bounce rate threshold for reputation damage
+  - 'Recommends workflow: validate, keep ok, exclude email_invalid'
+  - Mentions Truelist MCP server for agent workflows
+  - Mentions cold email reputation is hard to recover
+  - References truelist.md or data-sources.md
+  rubric: 'Should explain the deliverability validation step in Phase 3. Should recommend
+    Truelist (the integration in this pack) for bulk validation. Should explain the email_state
+    classification output: ok (deliverable), email_invalid (bounces, exclude), risky (deliverable
+    with risk like role or disposable, include cautiously), unknown (couldn''t determine,
+    skip or re-verify), accept_all (catch-all domain, include cautiously). Should warn that
+    Apollo data accuracy is typically 60-80% — sending without validation will tank sender
+    reputation (bounce rate >2% triggers ISP throttling and reputation damage). Should recommend
+    the workflow: bulk POST to /api/v1/verify or CSV upload → keep ok, include risky/accept_all
+    cautiously, exclude email_invalid, re-verify unknown → hand off to outreach. Should note
+    Truelist also has an official MCP server for agent-driven validation. Should note cold
+    email reputation is hard to recover once damaged — validation is non-negotiable, not optional.
+    Should mention Hunter and Snov as alternatives with built-in verification. Should reference
+    truelist.md integration guide.'
+  tags:
+  - prospecting
+  - imported
+- id: sales-prospecting-07
+  department: sales
+  prompt: I just built a tool that automates failed-payment follow-up for gym owners. I have
+    no customers yet. Help me find my first ten — the people who are actually dealing with
+    this problem right now.
+  expected_properties:
+  - Selects the Demand-signal branch, not the SMB/B2B/SaaS list-building branches
+  - Mines the five signal buckets from public discourse rather than contact databases
+  - Uses recency/original-source tooling (last30days, social-fetch, scraping) and does not
+    qualify from snippets
+  - Scores on the demand-fit rubric (0-100 weighted), not ICP-fit Hot/Warm/Cold
+  - Requires a cited public signal for every primary-shortlist prospect
+  - Drafts openers but never auto-sends; labels prospects as potential-based-on-public-signals
+  - Produces the evidence report structure with a 7-day manual outreach plan and limits
+  rubric: Should select the Demand-signal branch (early-stage, first customers, evidence-of-demand)
+    and load references/demand-signals.md — NOT the SMB/B2B list-building branches. Should
+    start with a product brief, then mine the five signal buckets (explicit demand / pain
+    / workaround / switching / timing) across public discourse (forums, communities, reviews,
+    GitHub issues, job posts) — using last30days for recency, social-fetch/scraping to read
+    original pages, not qualifying from snippets. Should score prospects on demand-fit (pain
+    25 / product fit 25 / timing 20 / reachability 15 / evidence quality 15, 0-100 with bands)
+    rather than ICP-fit Hot/Warm/Cold, and require a cited public signal for every primary-shortlist
+    prospect. Should draft source-based openers but never auto-send. Should produce an evidence
+    report (verdict → ICP → top prospect → shortlist with sources+scores → repeated patterns
+    → 7-day manual outreach plan → limits) and label prospects as 'potential customers based
+    on public signals,' not confirmed buyers. Should honor the compliance guardrails including
+    no data brokers/leaked data and no sensitive-trait targeting.
+  tags:
+  - prospecting
+  - imported
+- id: sales-revops-01
+  department: sales
+  prompt: Help me set up our lead lifecycle stages. We're a B2B SaaS company selling to mid-market.
+    We use HubSpot as our CRM and have marketing and sales teams that aren't aligned on lead
+    definitions.
+  expected_properties:
+  - Checks for product-marketing.md
+  - Applies lead lifecycle framework with all stages
+  - Defines criteria for each stage transition
+  - Addresses marketing-sales alignment
+  - Provides CRM implementation guidance for HubSpot
+  - Includes lead scoring setup
+  - Provides handoff process between teams
+  rubric: 'Should check for product-marketing.md first. Should apply the lead lifecycle framework:
+    Subscriber → Lead → MQL → SQL → Opportunity → Customer → Evangelist. Should define clear
+    criteria for each stage transition (what makes a Lead become an MQL, etc.). Should address
+    the alignment issue between marketing and sales — define shared definitions and SLAs.
+    Should recommend CRM implementation steps for HubSpot. Should include lead scoring setup.
+    Should provide a handoff process between marketing and sales.'
+  tags:
+  - revops
+  - imported
+- id: sales-revops-02
+  department: sales
+  prompt: Set up lead scoring for us. We want to prioritize which leads sales should call
+    first. We sell enterprise software ($50k+ ACV).
+  expected_properties:
+  - Applies lead scoring with explicit, implicit, and negative dimensions
+  - Provides specific scoring criteria for enterprise
+  - Weights firmographic signals appropriately
+  - Includes behavioral scoring signals
+  - Includes negative scoring signals
+  - Defines MQL and SQL score thresholds
+  - Recommends lead routing based on scores
+  rubric: 'Should apply the lead scoring framework with three dimensions: explicit scoring
+    (firmographics — company size, industry, title match), implicit scoring (behavioral —
+    page visits, content downloads, email engagement), and negative scoring (unsubscribes,
+    competitor emails, student emails). Should provide specific scoring criteria appropriate
+    for enterprise ($50k+ ACV): weight firmographic signals heavily, include budget and authority
+    signals. Should define score thresholds for MQL and SQL. Should recommend lead routing
+    based on scores.'
+  tags:
+  - revops
+  - imported
+- id: sales-revops-03
+  department: sales
+  prompt: our pipeline is a mess. deals sit in stages forever and we don't know what's actually
+    going to close. how do we fix this?
+  expected_properties:
+  - Triggers on casual phrasing
+  - Applies pipeline stage management
+  - Defines stages with entry/exit criteria
+  - Recommends maximum time per stage
+  - Addresses deal hygiene and pipeline reviews
+  - Recommends CRM automation for enforcement
+  - Provides practical cleanup plan
+  rubric: 'Should trigger on casual phrasing. Should apply the pipeline stage management guidance.
+    Should recommend: define clear pipeline stages with entry/exit criteria, set maximum time
+    in each stage, implement stage velocity tracking, add required fields per stage to force
+    data entry. Should address deal hygiene: regular pipeline reviews, stale deal flagging,
+    win/loss analysis. Should recommend CRM automation to enforce stage rules. Should provide
+    a practical cleanup plan for the current mess.'
+  tags:
+  - revops
+  - imported
+- id: sales-revops-04
+  department: sales
+  prompt: What RevOps metrics should we be tracking? We want to build a dashboard for our
+    leadership team.
+  expected_properties:
+  - Applies RevOps metrics dashboard
+  - Covers full-funnel metrics
+  - Includes conversion rates between stages
+  - Includes pipeline velocity and coverage
+  - Includes CAC, LTV, LTV:CAC
+  - Organizes by audience
+  - Recommends dashboard structure and review cadence
+  rubric: 'Should apply the RevOps metrics dashboard framework. Should recommend metrics across
+    the funnel: lead volume by source, MQL-to-SQL conversion rate, SQL-to-Opportunity rate,
+    win rate, average deal size, sales cycle length, pipeline velocity, pipeline coverage
+    ratio, CAC, LTV, LTV:CAC ratio. Should organize metrics by audience (marketing team, sales
+    team, leadership). Should recommend dashboard structure and cadence for reviews.'
+  tags:
+  - revops
+  - imported
+- id: sales-revops-05
+  department: sales
+  prompt: Our CRM data is a disaster. Duplicate records, missing fields, inconsistent naming.
+    How do we clean it up and keep it clean?
+  expected_properties:
+  - Applies data hygiene guidance
+  - Recommends duplicate detection and merging
+  - Recommends required field enforcement
+  - Addresses standardized naming conventions
+  - Covers both cleanup and prevention
+  - Recommends CRM automation for hygiene
+  - Provides prioritized cleanup plan
+  rubric: 'Should apply the data hygiene guidance. Should recommend: duplicate detection and
+    merging strategy, required field enforcement, standardized naming conventions (picklists
+    over free text), data validation rules, regular audit cadence. Should address both cleanup
+    (one-time fix) and prevention (ongoing processes). Should recommend CRM automation for
+    data hygiene. Should provide a prioritized cleanup plan (start with highest-impact data
+    quality issues).'
+  tags:
+  - revops
+  - imported
+- id: sales-revops-06
+  department: sales
+  prompt: Can you help me write cold outreach emails to prospects in our pipeline?
+  expected_properties:
+  - Recognizes this as cold email writing, not RevOps
+  - References or defers to cold-email skill
+  - Explains RevOps covers systems and processes, not email content
+  rubric: Should recognize this is a cold email / outbound writing task, not RevOps. Should
+    defer to or cross-reference the cold-email skill for writing outbound prospecting emails.
+    RevOps covers the systems, processes, and data infrastructure — not the actual email content.
+  tags:
+  - revops
+  - imported
+- id: sales-sales-enablement-01
+  department: sales
+  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.
+  expected_properties:
+  - Checks for product-marketing.md
+  - Applies 10-12 slide framework
+  - Includes Problem, Solution, Proof, Pricing, Next Steps slides
+  - Tailors to HR director audience
+  - Incorporates stated differentiator
+  - Provides slide-by-slide content
+  - Includes speaker notes or talking points
+  rubric: '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.'
+  tags:
+  - sales-enablement
+  - imported
+- id: sales-sales-enablement-02
+  department: sales
+  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.'
+  expected_properties:
+  - Applies objection handling framework
+  - Categorizes the three objections
+  - Provides structured response for each (acknowledge, reframe, evidence, bridge)
+  - Provides 2-3 response variations per objection
+  - Organizes for quick reference during calls
+  - Categorizes objections using the skill's framework (competitor, budget, need/timing)
+  rubric: '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.'
+  tags:
+  - sales-enablement
+  - imported
+- id: sales-sales-enablement-03
+  department: sales
+  prompt: i need a one-pager we can leave behind after sales meetings. something that summarizes
+    our product and key benefits.
+  expected_properties:
+  - Triggers on casual phrasing
+  - Applies one-pager/leave-behind framework
+  - Includes headline, benefits, social proof, how it works, CTA
+  - Keeps to one page format
+  - Recommends scannable design
+  - Provides specific content for each section
+  rubric: '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).'
+  tags:
+  - sales-enablement
+  - imported
+- id: sales-sales-enablement-04
+  department: sales
+  prompt: Create a demo script for our analytics dashboard product. Typical demo is 30 minutes
+    with a VP of Marketing.
+  expected_properties:
+  - Applies 5-part demo script structure
+  - Includes opening with discovery questions
+  - Includes problem validation
+  - Includes solution walkthrough
+  - Includes proof points
+  - Includes close with next steps
+  - Time-boxes for 30 minutes
+  - Notes customization based on prospect responses
+  rubric: '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.'
+  tags:
+  - sales-enablement
+  - imported
+- id: sales-sales-enablement-05
+  department: sales
+  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.
+  expected_properties:
+  - Applies ROI calculator framework
+  - Defines required inputs
+  - Provides calculation methodology
+  - Recommends conservative assumptions
+  - Includes ROI timeline and payback period
+  - Suggests validating assumptions during calls
+  - Provides calculator structure
+  rubric: '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.'
+  tags:
+  - sales-enablement
+  - imported
+- id: sales-sales-enablement-06
+  department: sales
+  prompt: We need a public comparison page showing how we stack up against Zendesk and Intercom.
+  expected_properties:
+  - Recognizes this as a public comparison page
+  - References or defers to competitors skill
+  - Explains the distinction between internal and public collateral
+  - Does not attempt public SEO comparison page using sales enablement patterns
+  rubric: 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.
+  tags:
+  - sales-enablement
+  - imported
+# --- END imported ---

package/config/skills-curated.yaml

@@ -6,7 +6,7 @@
 #
 # The cut: the default install carries the structural surface (main
 # /arka, the 17 department hubs, the 14 meta skills — 32 in total) plus
-# the curated sub-skills below (37) = 69 skills, inside the 60-80 band.
+# the curated sub-skills below (39) = 71 skills, inside the 60-80 band.
 # Every OTHER sub-skill still ships in the repo and deploys via the
 # per-department marketplace plugins (arkaos-<dept>@arkaos), where the
 # plugin namespace also disambiguates the later-wins collision slugs —
@@ -30,7 +30,7 @@ curated_subskills:
   kb: [search-kb, zettelkasten-process]
   landing: [funnel-design, landing-gen]
   leadership: [feedback-give]
-  marketing: [growth-loop, seo-audit]
+  marketing: [growth-loop, seo-audit, marketing-plan, product-marketing]
   ops: [sop-create, workflow-automate]
   org: [org-design]
   pm: [roadmap-build, sprint-plan]