novahiz 0.1.0

package/bundled-skills/product-marketing/evals/evals.json

@@ -0,0 +1,98 @@
+{
+  "skill_name": "product-marketing",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "I want to set up my product marketing context. We're a B2B SaaS company that sells a customer feedback platform to product teams.",
+      "expected_output": "Should check if .agents/product-marketing.md already exists. If not, should offer two options: (1) Auto-draft from codebase (recommended) or (2) Start from scratch. If user chooses start from scratch, should walk through sections conversationally one at a time. Should cover all applicable sections: Product Overview, Target Audience, Personas, Problems You Solve, Competitive Landscape, Differentiation, Objections, Switching Dynamics, Customer Language, Brand Voice, Proof Points, and Goals. Should create the file at .agents/product-marketing.md when complete.",
+      "assertions": [
+        "Checks for existing product-marketing.md",
+        "Offers two options: auto-draft or start from scratch",
+        "Covers applicable sections",
+        "Walks through sections conversationally one at a time",
+        "Creates file at .agents/product-marketing.md"
+      ],
+      "files": []
+    },
+    {
+      "id": 2,
+      "prompt": "Update our product marketing context. We just added a new enterprise tier and our target audience has expanded to include VP of Engineering, not just Product Managers.",
+      "expected_output": "Should check for existing .agents/product-marketing.md and read it. Should identify which sections need updating based on the changes: Target Audience (add VP of Engineering), Personas (add new persona), Product Overview (new enterprise tier, including pricing updates within that section), Objections (enterprise-specific), and Competitive Landscape (enterprise competitors). Should update only the relevant sections, preserving existing content that hasn't changed.",
+      "assertions": [
+        "Reads existing product-marketing.md",
+        "Identifies sections that need updating",
+        "Updates Target Audience with VP of Engineering",
+        "Adds new persona for the expanded audience",
+        "Updates Product Overview for enterprise tier",
+        "Preserves unchanged sections"
+      ],
+      "files": []
+    },
+    {
+      "id": 3,
+      "prompt": "create a product context doc for my app. it's a mobile app that helps people find hiking trails. we're just getting started.",
+      "expected_output": "Should trigger on casual phrasing. Should check for existing context doc. Should offer auto-draft or start-from-scratch options. Should adapt questions for an early-stage B2C mobile app (outdoor/fitness niche). Should note that some sections may be sparse for an early-stage product and that's okay — they can be filled in as the business matures. Should skip non-applicable sections (e.g., Personas section is B2B-focused) rather than forcing all 12. Should accept lighter answers for sections like Proof Points or Competitive Landscape if the company is new.",
+      "assertions": [
+        "Triggers on casual phrasing",
+        "Checks for existing context doc",
+        "Offers auto-draft or start-from-scratch options",
+        "Adapts questions for early-stage B2C mobile app",
+        "Notes some sections may be sparse early on",
+        "Skips non-applicable sections rather than forcing all 12",
+        "Creates file at .agents/product-marketing.md"
+      ],
+      "files": []
+    },
+    {
+      "id": 4,
+      "prompt": "Can you auto-draft our product marketing context from our existing codebase and marketing materials?",
+      "expected_output": "Should activate the auto-draft workflow mode. Should scan the codebase for existing marketing context: README, landing page copy, pricing page, about page, meta descriptions, any existing documentation. Should draft the product-marketing.md from what it finds, filling in sections where information is available and flagging sections that need manual input. Should present the draft for review before saving.",
+      "assertions": [
+        "Activates auto-draft workflow mode",
+        "Scans codebase for existing marketing materials",
+        "Drafts context from found information",
+        "Flags sections needing manual input",
+        "Presents draft for review before saving"
+      ],
+      "files": []
+    },
+    {
+      "id": 5,
+      "prompt": "Do we have a product marketing context set up? I want to make sure the other marketing skills have context about our product.",
+      "expected_output": "Should check for .agents/product-marketing.md (and the older .claude/product-marketing.md location). Should report whether it exists and summarize its contents if found. If it doesn't exist, should offer to create one and explain why it's valuable (other skills like copywriting, cro, seo-audit check for it first). Should explain how other skills use this context document.",
+      "assertions": [
+        "Checks both file locations",
+        "Reports whether context doc exists",
+        "Summarizes contents if found",
+        "Offers to create if missing",
+        "Explains how other skills use it"
+      ],
+      "files": []
+    },
+    {
+      "id": 6,
+      "prompt": "Write homepage copy for our SaaS product.",
+      "expected_output": "Should recognize this is a copywriting task, not a product marketing context task. Should check for product-marketing.md (as other skills do), and if it doesn't exist, may suggest creating one first. But should defer to the copywriting skill for actually writing the homepage copy.",
+      "assertions": [
+        "Recognizes this as a copywriting task",
+        "May check for or suggest creating product-marketing.md",
+        "References or defers to copywriting skill for the actual copy",
+        "Does not attempt to write homepage copy using context creation patterns"
+      ],
+      "files": []
+    },
+    {
+      "id": 7,
+      "prompt": "We just repositioned — we're no longer an 'email tool,' we're a 'deliverability platform,' and our ICP now includes RevOps teams. Update our product marketing context.",
+      "expected_output": "Should recognize an existing .agents/product-marketing.md, read it, note its current Document version and recent Changelog entries, and update only the affected sections (product overview/positioning, target audience/ICP). On save, should bump the Document version (e.g. v2 → v3), update the Last updated date, and PREPEND a new newest-first Changelog entry summarizing what changed and why in one line — e.g. 'Repositioned from email tool to deliverability platform; added RevOps to the ICP' — naming the sections touched and the reason, not just 'updated the doc.' Should not rewrite or reorder past changelog entries. Should tell the user the changelog tracks revisions and that downstream skills will now use the new context.",
+      "assertions": [
+        "Reads the existing doc and surfaces its current version + recent changelog",
+        "Updates only the affected sections (positioning + ICP)",
+        "Bumps the Document version and updates Last updated",
+        "Prepends a newest-first changelog entry naming what changed and why",
+        "Preserves prior changelog entries unchanged"
+      ],
+      "files": []
+    }
+  ]
+}

package/bundled-skills/prospecting/SKILL.md

@@ -0,0 +1,262 @@
+---
+name: prospecting
+description: When the user wants to find, qualify, and build a list of prospects to reach out to — across B2B SaaS, general B2B, or local small businesses. Also use when the user mentions "prospecting," "build a prospect list," "find prospects," "find leads," "lead gen list," "find SaaS companies that," "find B2B companies," "find local businesses," "ICP-fit accounts," "who should we go after," "outbound list," "target account list," "find clients near me," "businesses without websites," "prospect research," "qualified leads," "find my first customers," "early adopters," "design partners," "beta users," or "who has this problem." Use this for the list-building and qualification phase. For writing the outbound copy after the list is built, see cold-email. For deep competitive research on specific accounts, see competitor-profiling.
+metadata:
+  version: 1.1.0
+---
+
+# Prospecting
+
+You are an expert at building qualified prospect lists across four motions: B2B SaaS, general B2B, local small businesses, and early-stage demand-signal discovery (finding your first customers from public pain signals). Your goal is to turn an ICP definition into a verified, scored, ready-to-outreach lead sheet — using the right data sources, qualification signals, and compliance posture for each motion.
+
+## Before Starting
+
+**Check for product marketing context first:**
+If `.agents/product-marketing.md` exists (or `.claude/product-marketing.md`, or the legacy `product-marketing-context.md` filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
+
+## Pick the Branch
+
+Prospecting motions differ enough that the workflow forks at intake. Pick **one** branch based on who the user is selling to:
+
+| Branch | Sell to | What "qualified" looks like | Primary sources |
+|--------|---------|----------------------------|----------------|
+| **SaaS** | Other SaaS companies / digital businesses | ICP fit + tech stack match + growth signals (funding, hiring, product velocity) | LinkedIn, BuiltWith, Crunchbase, Apollo, Clay, Clearbit, ProductHunt |
+| **B2B** | Non-SaaS B2B (services, manufacturers, enterprises, mid-market) | Industry + size + geographic fit + buying signals (trigger events, vendor changes) | Apollo, ZoomInfo, Clay, Clearbit, LinkedIn Sales Nav, industry directories |
+| **Local SMB** | Local small businesses (shops, gyms, restaurants, clinics, salons, services) | Active business + website status + proximity + decision-maker access | Google Maps, Yelp, local directories, Facebook, business websites |
+| **Demand-signal** | Early-stage: your first customers, design partners, or beta users | Evidence of the exact pain/demand/timing signal — a cited public source, not just firmographic fit | Forums, communities, reviews, GitHub issues, job posts, launch announcements (via last30days, social-fetch, scraping) |
+
+If the user describes a hybrid motion (e.g., "SMBs that are also SaaS"), pick the dominant branch and pull in qualification signals from the other. If the user is early-stage and needs their *first* customers or design partners — evidence of demand over list coverage — use the **Demand-signal** branch.
+
+For the branch-specific deep dives:
+- **SaaS** → see [references/saas-prospecting.md](references/saas-prospecting.md)
+- **B2B** → see [references/b2b-prospecting.md](references/b2b-prospecting.md)
+- **Local SMB** → see [references/local-prospecting.md](references/local-prospecting.md)
+- **Demand-signal** (find your first customers) → see [references/demand-signals.md](references/demand-signals.md)
+
+---
+
+## Shared Framework (all branches)
+
+Every prospecting engagement follows the same five phases. Tools and qualification signals change per branch; the phases don't.
+
+### Phase 1 — Define the ICP
+
+Pull from `product-marketing.md` if available. Otherwise, gather:
+
+1. **Firmographic fit** — industry, company size, revenue band, geography, business model
+2. **Technographic fit** (SaaS branch) — what tools they already use, what they're missing
+3. **Buying signal** — why now? (trigger event, funding, hiring, new initiative, dissatisfaction with current vendor, recent move/expansion)
+4. **Decision-maker profile** — role, seniority, what they care about
+5. **Disqualifiers** — what makes a prospect a clear "skip"
+
+Output the ICP as a one-paragraph statement plus a checklist of pass/fail criteria. Don't move to discovery without this.
+
+### Phase 2 — Build the candidate list (discovery)
+
+Source 2–3× more candidates than the user wants in the final list — qualification will cull aggressively.
+
+- **SaaS / B2B**: combine 2–3 sources for cross-verification. Apollo or ZoomInfo for firmographics; Clearbit or Clay for enrichment; LinkedIn Sales Nav for decision-maker mapping.
+- **Local SMB**: browser-assisted research starting with Google Maps for the target category in the target area; cross-check with Yelp, the business website, social pages, and public directories.
+
+If the user's list quality bar is high, smaller is better. 25 verified leads beats 250 mostly-junk ones.
+
+### Phase 3 — Qualify each candidate
+
+Score every candidate against the ICP checklist. Add **evidence** (a source URL or two) for each qualification — never assert without backing.
+
+**Confidence levels** (used across all branches):
+- **High**: confirmed by at least two independent sources or official business page
+- **Medium**: one credible source plus consistent search evidence
+- **Low**: incomplete or ambiguous evidence — flag what remains uncertain
+
+For email contacts (B2B / SaaS branches), **always verify deliverability before adding to the final list** — see Truelist integration in [references/data-sources.md](references/data-sources.md). Don't ship leads with invalid or risky emails.
+
+### Phase 4 — Score and prioritize
+
+Apply this rubric for the **SaaS, B2B, and Local SMB** branches. The **Demand-signal** branch scores differently — 0–100 demand-fit, not Hot/Warm/Cold — see [references/demand-signals.md](references/demand-signals.md).
+
+| Score | Definition |
+|-------|------------|
+| **Hot** | Strong ICP fit + clear buying signal + decision-maker accessible + verified contact |
+| **Warm** | ICP fit + softer or older signal + contact verifiable |
+| **Cold** | Loose ICP fit OR no clear signal OR contact unverified |
+| **Skip** | Disqualifier hit (out of ICP, closed business, duplicate, irrelevant, low confidence) |
+
+Branch-specific signals refine the scoring — see each reference file. Default ratio target: ~20% Hot, ~30% Warm, rest Cold/Skip.
+
+### Phase 5 — Output the lead sheet
+
+(SaaS / B2B / Local SMB. The **Demand-signal** branch ships an evidence report instead — see [references/demand-signals.md](references/demand-signals.md).)
+
+Default to a markdown table in chat. Switch to CSV when the list is >25 rows or the user explicitly asks for a file.
+
+After the table, always add **"Top outreach targets"** — the top 3–5 hot leads with one sentence each on why this lead should be reached out to first.
+
+Columns vary by branch (see reference files), but every lead sheet includes:
+- score, business/company name, contact (where applicable), why-it's-a-prospect, source(s), confidence, last verified date
+
+---
+
+## Compliance Guardrails
+
+These apply to every branch. **Read first, every engagement.**
+
+1. **No bulk scraping** of LinkedIn, Google Maps, paywalled sites, or rate-limited APIs. Browser is an assisted research tool, not a scraper.
+2. **No CAPTCHA, login wall, or bot protection bypass.** If a site requires it, work with what's publicly visible.
+3. **Public business contact channels only.** Use info@, hello@, contact@, and named-role emails (founder, owner) where they're published on the business's own site. Personal/private emails require a lawful basis (existing relationship, opt-in, etc.).
+4. **GDPR / CAN-SPAM / CASL aware.** Capture and retain the source URL and date for every contact you add to a list — required for downstream outreach compliance.
+5. **No reselling extracted data** from Google Maps, LinkedIn, or any platform whose terms prohibit it. List building for the user's own outreach is fine; productizing the list to sell is not.
+6. **Rate limit yourself.** Even on public sources, space requests. Don't fingerprint as a bot.
+7. **No breached, leaked, or unprovenanced data.** Don't source prospects from breached datasets, scraped-contact marketplaces, or list brokers with no source lineage. Licensed B2B data providers (Apollo, ZoomInfo, Clearbit, Clay) are fine when used within their ToS and with a lawful basis — the ban is on illicit/unprovenanced data, not on legitimate enrichment vendors.
+8. **Never target or infer sensitive traits.** Don't qualify, segment, or personalize on health, financial hardship, political belief, sexuality, religion, or other protected/sensitive attributes — even when a public post reveals them.
+
+For the full compliance reference (GDPR, CAN-SPAM, CASL, LinkedIn ToS, Google Maps ToS, Clay/Apollo/ZoomInfo use restrictions): see [references/compliance.md](references/compliance.md).
+
+---
+
+## Inputs to Collect
+
+If missing, ask once, then infer reasonable defaults and continue:
+
+- **Branch** (SaaS / B2B / Local SMB / Demand-signal) — usually inferable from context; pick Demand-signal for early-stage first-customer discovery
+- **ICP description** — pull from `product-marketing.md` if present
+- **Target count** — default 25 for SaaS / B2B, 15 for Local SMB
+- **Geography** (essential for Local SMB; useful for B2B; less critical for SaaS)
+- **Tools the user has access to** — Apollo? Clay? ZoomInfo? Hunter? Truelist? Defaults to what's free + browser
+- **Output format** — chat table (default) or CSV
+- **Buying signal preference** — what triggers should they prioritize? (funding rounds, hiring, recent move, etc.)
+
+---
+
+## Tool Selection Quick Picks
+
+Full breakdown in [references/data-sources.md](references/data-sources.md). Quick picks:
+
+| If the user has access to... | Use it for |
+|------------------------------|------------|
+| **Apollo** | B2B / SaaS firmographic + contact discovery |
+| **Clay** | Multi-source enrichment, waterfall lookups, custom scoring |
+| **Clearbit** | Email-to-company and company enrichment |
+| **ZoomInfo** | Enterprise B2B contact + intent data |
+| **Hunter or Snov** | Email pattern guessing and verification |
+| **Truelist** | Email deliverability validation (before adding to outreach list) |
+| **LinkedIn Sales Navigator** | Decision-maker mapping (manual, no scraping) |
+| **BuiltWith / Wappalyzer** | Tech stack qualification (SaaS branch) |
+| **Crunchbase** | Funding signals (SaaS branch) |
+| **GitHub** | Stargazers / forks of competitor or adjacent repos (dev-tool SaaS branch) |
+| **Google Maps + browser** | Local SMB discovery |
+| **Firecrawl / Browserbase** | Programmatic extraction from individual prospect websites — never from platforms |
+
+**If the user has no enrichment tools**: lean on browser-assisted research with public sources — company website, About page, LinkedIn company page, news mentions. Slower but works.
+
+---
+
+## Output Formats
+
+### Default — chat table
+
+For SaaS / B2B (≤25 rows):
+
+```
+| Score | Company | Industry | Size | Signal | Contact | Email status | Source | Confidence |
+| --- | --- | --- | --- | --- | --- | --- | --- | --- |
+```
+
+For Local SMB (≤15 rows) — port from the local-prospector reference:
+
+```
+| Score | Business | Category | Area | Website status | Website/Social | Phone | Why it's a prospect | Confidence |
+| --- | --- | --- | --- | --- | --- | --- | --- | --- |
+```
+
+### CSV — when >25 rows or user requests a file
+
+SaaS / B2B columns:
+
+```csv
+score,company,domain,industry,size_band,country,signal,contact_name,contact_title,contact_email,email_status,linkedin,source_urls,why_prospect,confidence,verified_date,notes
+```
+
+Local SMB columns:
+
+```csv
+score,business,category,area,distance_km,website_status,website_url,social_urls,phone,email,source_urls,why_prospect,confidence,verified_date,notes
+```
+
+### Always include after the table
+
+- **Top outreach targets**: top 3–5 hot leads with one-sentence outreach rationale each
+- **Search parameters**: branch, ICP, location/radius, target count, date generated
+- **Open questions**: anything you couldn't verify and the user should look at
+
+---
+
+## Quality Checks (before finalizing)
+
+- [ ] Remove duplicates (by domain for SaaS/B2B, by business + address for Local SMB)
+- [ ] Every "Hot" lead has a verified contact + at least one source URL
+- [ ] No lead has an email that failed Truelist (or your validator) verification — move to a separate "invalid" bucket and flag for the user
+- [ ] No lead labeled "Hot" lacks a clear buying signal
+- [ ] Confidence levels honest — "High" requires 2 independent sources, not just two of your own searches
+- [ ] No leads sourced from prohibited scraping (LinkedIn at scale, Google Maps bulk extract, etc.)
+- [ ] Source URL + date captured for every contact (GDPR / CAN-SPAM lineage)
+- [ ] Final count matches user's request, or you've explained why it's smaller (quality bar)
+
+---
+
+## Common Mistakes
+
+1. **Starting discovery without an ICP**. Build candidates against vague criteria and you'll qualify the wrong things.
+2. **Treating data sources as authoritative without cross-checks**. Apollo and ZoomInfo are out of date often; verify before scoring as "Hot."
+3. **Adding contacts without email verification**. Cold email reputation tanks fast with bounces — always validate.
+4. **Bulk scraping LinkedIn or Google Maps**. Real risk: account suspension + ToS violation. Browser as an assisted tool only.
+5. **Mixing branches**. Don't apply Local SMB scoring (website status) to a B2B SaaS prospect, or vice versa.
+6. **"Hot" labels without buying signals**. ICP fit alone is not enough — the signal is what makes the timing right.
+7. **No source URLs**. Every claim should be traceable to a public source. Future outreach depends on this lineage.
+8. **Ignoring quiet hours / time zone** when scheduling the downstream outreach (handoff to cold-email).
+9. **Forgetting to retain consent / lineage records**. Required for GDPR DSARs and CAN-SPAM audits.
+
+---
+
+## Task-Specific Questions
+
+1. Which branch — SaaS, B2B, Local SMB, or Demand-signal (early-stage, finding your first customers)?
+2. What's your ICP? (Or: should I pull from your product-marketing context?)
+3. How many qualified leads do you want?
+4. What tools do you have access to (Apollo / Clay / ZoomInfo / Hunter / Truelist / browser only)?
+5. What's the triggering buying signal you care most about?
+6. Geography or radius (Local SMB / B2B)?
+7. Chat table or CSV?
+
+---
+
+## Tool Integrations
+
+For implementation, see the [tools registry](../../tools/REGISTRY.md). Key prospecting tools:
+
+| Tool | Best For | MCP | Guide |
+|------|----------|:---:|-------|
+| **Apollo** | B2B / SaaS firmographic + contact discovery | - | [apollo.md](../../tools/integrations/apollo.md) |
+| **Clay** | Multi-source enrichment + waterfall | ✓ | [clay.md](../../tools/integrations/clay.md) |
+| **Clearbit** | Email-to-company enrichment | - | [clearbit.md](../../tools/integrations/clearbit.md) |
+| **ZoomInfo** | Enterprise B2B contact + intent | ✓ | [zoominfo.md](../../tools/integrations/zoominfo.md) |
+| **Hunter** | Email pattern + verification | - | [hunter.md](../../tools/integrations/hunter.md) |
+| **Snov** | Email finder + verifier | - | [snov.md](../../tools/integrations/snov.md) |
+| **Truelist** | Email deliverability validation | - | [truelist.md](../../tools/integrations/truelist.md) |
+| **Outreach** | Sales engagement (post-list) | ✓ | [outreach.md](../../tools/integrations/outreach.md) |
+| **RB2B** | Visitor identification (warm intent) | - | [rb2b.md](../../tools/integrations/rb2b.md) |
+| **GitHub** | Stargazers/forks/watchers as developer-intent signal | - | [github.md](../../tools/integrations/github.md) |
+| **Firecrawl** | Single-target site extraction (prospect's own website) | ✓ | [firecrawl.md](../../tools/integrations/firecrawl.md) |
+| **Browserbase** | Real-browser site research when rendering or interaction needed | ✓ | [browserbase.md](../../tools/integrations/browserbase.md) |
+
+---
+
+## Related Skills
+
+- **cold-email**: For writing outbound sequences against the qualified list (the natural next step after prospecting)
+- **customer-research**: For understanding why current customers buy — informs the ICP definition
+- **competitor-profiling**: For deeper research on individual accounts (different from list-building qualification)
+- **revops**: For lead routing, lifecycle, and CRM handoff after prospecting
+- **sales-enablement**: For battle cards and one-pagers used in the outreach
+- **directory-submissions**: For inbound discovery surfaces (the prospects might find you back)
+- **product-marketing**: For the ICP definition that anchors every prospecting engagement

package/bundled-skills/prospecting/evals/evals.json

@@ -0,0 +1,122 @@
+{
+  "skill_name": "prospecting",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "We're a B2B SaaS selling RevOps tooling at $30K ACV. Build me a list of 25 prospects.",
+      "expected_output": "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.",
+      "assertions": [
+        "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"
+      ],
+      "files": []
+    },
+    {
+      "id": 2,
+      "prompt": "Find me 25 SaaS companies that just raised a Series B in the last 60 days and use HubSpot.",
+      "expected_output": "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.",
+      "assertions": [
+        "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"
+      ],
+      "files": []
+    },
+    {
+      "id": 3,
+      "prompt": "I run a marketing agency. Find me 25 mid-market manufacturers in the Midwest US who recently hired a new CMO.",
+      "expected_output": "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.",
+      "assertions": [
+        "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"
+      ],
+      "files": []
+    },
+    {
+      "id": 4,
+      "prompt": "We sell to industrial distributors. Build a list of 25 prospects.",
+      "expected_output": "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.",
+      "assertions": [
+        "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"
+      ],
+      "files": []
+    },
+    {
+      "id": 5,
+      "prompt": "I build websites for local businesses. Find me 15 prospects near Austin, TX who don't have a website.",
+      "expected_output": "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.",
+      "assertions": [
+        "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"
+      ],
+      "files": []
+    },
+    {
+      "id": 6,
+      "prompt": "I have a list of 200 prospect emails from Apollo. How do I know which ones are deliverable before I start outreach?",
+      "expected_output": "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.",
+      "assertions": [
+        "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"
+      ],
+      "files": []
+    },
+    {
+      "id": 7,
+      "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_output": "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.",
+      "assertions": [
+        "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"
+      ],
+      "files": []
+    }
+  ]
+}

package/bundled-skills/prospecting/references/b2b-prospecting.md

@@ -0,0 +1,106 @@
+# B2B Prospecting Reference
+
+For when the user sells to non-SaaS B2B — services, agencies, manufacturers, mid-market and enterprise companies, professional services firms.
+
+---
+
+## ICP Signals That Matter (B2B branch)
+
+### Firmographic signals
+
+- **Industry / vertical** — NAICS or SIC codes if precision matters
+- **Company size** — headcount band, revenue band, location count
+- **Geography** — relevant for time zones, regulations, on-site requirements
+- **Business model** — service vs product vs distribution; B2B vs B2B2C
+- **Ownership** — independent, PE-backed, public, family-owned — affects buying motion
+
+### Buying signals
+
+- **Trigger events**: new C-level hire, recent acquisition or divestiture, IPO/funding, opening a new location, recent rebrand, expansion announcement
+- **Vendor signals**: posting RFPs publicly, switching costs in last quarterly report, contract renewal windows
+- **Operational signals**: recent layoffs (cost pressure) or rapid hiring (capacity pressure)
+- **News mentions**: launching new initiative, entering new market, regulatory change forcing action
+- **PR / press**: anything that signals "this company is changing right now"
+
+### Decay signals
+
+- Multiple bankruptcies or PE-stripped operations
+- Negative growth + cost-cutting headlines
+- Ownership stagnation (small family-owned, no growth incentive)
+- Buyer turnover (3+ Marketing Directors in 2 years)
+
+---
+
+## Discovery Sources (B2B branch)
+
+### Tier 1 — primary discovery
+
+- **Apollo**: best general B2B firmographic + contact discovery
+- **ZoomInfo**: enterprise B2B + intent signals (mid-market+)
+- **LinkedIn Sales Navigator**: industry + role + signal search; the gold standard for decision-maker mapping (manual)
+- **Clay**: when you need custom waterfall lookups (e.g., enrich Apollo records with Hunter + Clearbit)
+
+### Tier 2 — industry-specific directories
+
+- **Crunchbase / Pitchbook**: funded businesses
+- **D&B Hoovers**: large traditional B2B firmographics
+- **State / national business registries**: for verified incorporation data
+- **Industry association membership rosters**: trade groups often publish member lists
+- **Trade show exhibitor lists**: signals active participation in a vertical
+- **Procurement databases** (Procore for construction, e.g.): vertical-specific signals
+
+### Tier 3 — trigger event monitoring
+
+- **Google Alerts / Feedly**: trigger keywords ("acquired," "hires," "expansion," "raises," "announces")
+- **PR Newswire / Business Wire**: company-controlled announcements
+- **SEC filings** (public companies): material change disclosures
+- **State filings**: new entity formation, dissolution
+
+---
+
+## Qualification Checklist (B2B branch)
+
+- [ ] Industry / vertical matches ICP (use a recognized classification if possible)
+- [ ] Company size within range (employees or revenue)
+- [ ] Geography fits
+- [ ] At least one trigger event in last 90–180 days
+- [ ] Decision-maker role exists (CEO, COO, VP Operations, Director of X — match buyer profile)
+- [ ] Email contact verifiable (named role > info@ catchall)
+- [ ] Source URLs captured for firmographic claims
+- [ ] No disqualifiers (closed, acquired-paused, multi-bankrupt, off-ICP)
+
+---
+
+## Output Columns (B2B branch)
+
+Recommended CSV columns:
+
+```csv
+score,company,domain,industry,naics_code,size_band,revenue_band,country,city,trigger_event,trigger_date,contact_name,contact_title,contact_email,email_status,linkedin_url,source_urls,why_prospect,confidence,verified_date,notes
+```
+
+For chat table, condense to: Score | Company | Industry | Size | Trigger | Contact | Email status | Confidence.
+
+---
+
+## Top Outreach Targets Selection (B2B)
+
+Prioritize for the top 3–5 hot leads:
+
+1. **Trigger event recency** — 30 days beats 6 months
+2. **Trigger event specificity** — new CMO hire in your buyer's role beats "company in the news"
+3. **Decision-maker access** — named contact with verified email + LinkedIn beats role-only
+4. **Vertical fit precision** — exact NAICS match beats "adjacent industry"
+
+Each top target rationale names the trigger and decision-maker: "Hired new VP of Marketing 14 days ago; verified email; mid-market manufacturer matching ICP."
+
+---
+
+## Common Mistakes (B2B)
+
+1. **Treating B2B like SaaS** — funding rounds matter less; PE ownership and acquisition activity matter more.
+2. **Trying to verify private company revenue precisely** — most public databases approximate. Use size bands, not point estimates.
+3. **Ignoring procurement complexity** at enterprise scale — your prospect contact list may not include the actual approver.
+4. **Cold-emailing executive assistants** — they're not the buyer and they will flag your outreach as spam.
+5. **Source URL hygiene** — without source lineage, you can't defend a contact under GDPR DSAR or CAN-SPAM challenge.
+6. **Stopping at one source** — Apollo can be 60% accurate on small businesses. Cross-verify with LinkedIn or the business website.