Prospecting
Unverified●24/40Claude Code◐PartialHas SKILL.md but declares no allowed-tools — Claude Code will ask for permission each time
Cursor◐PartialPlain prose you can paste in — but no Cursor rules file
Codex◐PartialPlain prose you can paste in — but no AGENTS.md
Gemini CLI◐PartialPlain prose you can paste in
Copilot◐PartialPlain prose you can paste in — but no Copilot instructions file
npx agentalley add prospectingWho is stuck, and on what
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 lis
The whole source
Frontmatter — 3 properties
| 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 |
| 1 | --- |
| 2 | name: prospecting |
| 3 | 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.B1 — Line is 842 characters — unreadable by eye |
| 4 | metadata: |
| 5 | version: 1.1.0 |
| 6 | ---A5 — No allowed-tools declared — no way to tell what this skill may touch |
| 7 | |
| 8 | # Prospecting |
| 9 | |
| 10 | 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. |
| 11 | |
| 12 | ## Before Starting |
| 13 | |
| 14 | **Check for product marketing context first:** |
| 15 | 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. |
| 16 | |
| 17 | ## Pick the Branch |
| 18 | |
| 19 | Prospecting motions differ enough that the workflow forks at intake. Pick **one** branch based on who the user is selling to: |
| 20 | |
| 21 | | Branch | Sell to | What "qualified" looks like | Primary sources | |
| 22 | |--------|---------|----------------------------|----------------| |
| 23 | | **SaaS** | Other SaaS companies / digital businesses | ICP fit + tech stack match + growth signals (funding, hiring, product velocity) | LinkedIn, BuiltWith, Crunchbase, Apollo, Clay, Clearbit, ProductHunt | |
| 24 | | **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 | |
| 25 | | **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 | |
| 26 | | **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) |A4 — This skill pulls in web or user content but never says to treat that content as data. A signal, not proof. |
| 27 | |
| 28 | 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. |
| 29 | |
| 30 | For the branch-specific deep dives: |
| 31 | - **SaaS** → see [references/saas-prospecting.md](references/saas-prospecting.md) |
| 32 | - **B2B** → see [references/b2b-prospecting.md](references/b2b-prospecting.md) |
| 33 | - **Local SMB** → see [references/local-prospecting.md](references/local-prospecting.md) |
| 34 | - **Demand-signal** (find your first customers) → see [references/demand-signals.md](references/demand-signals.md) |
| 35 | |
| 36 | --- |
| 37 | |
| 38 | ## Shared Framework (all branches) |
| 39 | |
| 40 | Every prospecting engagement follows the same five phases. Tools and qualification signals change per branch; the phases don't. |
| 41 | |
| 42 | ### Phase 1 — Define the ICP |
| 43 | |
| 44 | Pull from `product-marketing.md` if available. Otherwise, gather: |
| 45 | |
| 46 | 1. **Firmographic fit** — industry, company size, revenue band, geography, business model |
| 47 | 2. **Technographic fit** (SaaS branch) — what tools they already use, what they're missing |
| 48 | 3. **Buying signal** — why now? (trigger event, funding, hiring, new initiative, dissatisfaction with current vendor, recent move/expansion) |
| 49 | 4. **Decision-maker profile** — role, seniority, what they care about |
| 50 | 5. **Disqualifiers** — what makes a prospect a clear "skip" |
| 51 | |
| 52 | Output the ICP as a one-paragraph statement plus a checklist of pass/fail criteria. Don't move to discovery without this. |
| 53 | |
| 54 | ### Phase 2 — Build the candidate list (discovery) |
| 55 | |
| 56 | Source 2–3× more candidates than the user wants in the final list — qualification will cull aggressively. |
| 57 | |
| 58 | - **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. |
| 59 | - **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. |
| 60 | |
| 61 | If the user's list quality bar is high, smaller is better. 25 verified leads beats 250 mostly-junk ones. |
| 62 | |
| 63 | ### Phase 3 — Qualify each candidate |
| 64 | |
| 65 | Score every candidate against the ICP checklist. Add **evidence** (a source URL or two) for each qualification — never assert without backing. |
| 66 | |
| 67 | **Confidence levels** (used across all branches): |
| 68 | - **High**: confirmed by at least two independent sources or official business page |
| 69 | - **Medium**: one credible source plus consistent search evidence |
| 70 | - **Low**: incomplete or ambiguous evidence — flag what remains uncertain |
| 71 | |
| 72 | 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. |
| 73 | |
| 74 | ### Phase 4 — Score and prioritize |
| 75 | |
| 76 | 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). |
| 77 | |
| 78 | | Score | Definition | |
| 79 | |-------|------------| |
| 80 | | **Hot** | Strong ICP fit + clear buying signal + decision-maker accessible + verified contact | |
| 81 | | **Warm** | ICP fit + softer or older signal + contact verifiable | |
| 82 | | **Cold** | Loose ICP fit OR no clear signal OR contact unverified | |
| 83 | | **Skip** | Disqualifier hit (out of ICP, closed business, duplicate, irrelevant, low confidence) | |
| 84 | |
| 85 | Branch-specific signals refine the scoring — see each reference file. Default ratio target: ~20% Hot, ~30% Warm, rest Cold/Skip. |
| 86 | |
| 87 | ### Phase 5 — Output the lead sheet |
| 88 | |
| 89 | (SaaS / B2B / Local SMB. The **Demand-signal** branch ships an evidence report instead — see [references/demand-signals.md](references/demand-signals.md).) |
| 90 | |
| 91 | Default to a markdown table in chat. Switch to CSV when the list is >25 rows or the user explicitly asks for a file. |
| 92 | |
| 93 | 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. |
| 94 | |
| 95 | Columns vary by branch (see reference files), but every lead sheet includes: |
| 96 | - score, business/company name, contact (where applicable), why-it's-a-prospect, source(s), confidence, last verified date |
| 97 | |
| 98 | --- |
| 99 | |
| 100 | ## Compliance Guardrails |
| 101 | |
| 102 | These apply to every branch. **Read first, every engagement.** |
| 103 | |
| 104 | 1. **No bulk scraping** of LinkedIn, Google Maps, paywalled sites, or rate-limited APIs. Browser is an assisted research tool, not a scraper. |
| 105 | 2. **No CAPTCHA, login wall, or bot protection bypass.** If a site requires it, work with what's publicly visible. |
| 106 | 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.). |
| 107 | 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. |
| 108 | 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. |
| 109 | 6. **Rate limit yourself.** Even on public sources, space requests. Don't fingerprint as a bot. |
| 110 | 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. |
| 111 | 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. |
| 112 | |
| 113 | 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). |
| 114 | |
| 115 | --- |
| 116 | |
| 117 | ## Inputs to Collect |
| 118 | |
| 119 | If missing, ask once, then infer reasonable defaults and continue: |
| 120 | |
| 121 | - **Branch** (SaaS / B2B / Local SMB / Demand-signal) — usually inferable from context; pick Demand-signal for early-stage first-customer discovery |
| 122 | - **ICP description** — pull from `product-marketing.md` if present |
| 123 | - **Target count** — default 25 for SaaS / B2B, 15 for Local SMB |
| 124 | - **Geography** (essential for Local SMB; useful for B2B; less critical for SaaS) |
| 125 | - **Tools the user has access to** — Apollo? Clay? ZoomInfo? Hunter? Truelist? Defaults to what's free + browser |
| 126 | - **Output format** — chat table (default) or CSV |
| 127 | - **Buying signal preference** — what triggers should they prioritize? (funding rounds, hiring, recent move, etc.) |
| 128 | |
| 129 | --- |
| 130 | |
| 131 | ## Tool Selection Quick Picks |
| 132 | |
| 133 | Full breakdown in [references/data-sources.md](references/data-sources.md). Quick picks: |
| 134 | |
| 135 | | If the user has access to... | Use it for | |
| 136 | |------------------------------|------------| |
| 137 | | **Apollo** | B2B / SaaS firmographic + contact discovery | |
| 138 | | **Clay** | Multi-source enrichment, waterfall lookups, custom scoring | |
| 139 | | **Clearbit** | Email-to-company and company enrichment | |
| 140 | | **ZoomInfo** | Enterprise B2B contact + intent data | |
| 141 | | **Hunter or Snov** | Email pattern guessing and verification | |
| 142 | | **Truelist** | Email deliverability validation (before adding to outreach list) | |
| 143 | | **LinkedIn Sales Navigator** | Decision-maker mapping (manual, no scraping) | |
| 144 | | **BuiltWith / Wappalyzer** | Tech stack qualification (SaaS branch) | |
| 145 | | **Crunchbase** | Funding signals (SaaS branch) | |
| 146 | | **GitHub** | Stargazers / forks of competitor or adjacent repos (dev-tool SaaS branch) | |
| 147 | | **Google Maps + browser** | Local SMB discovery | |
| 148 | | **Firecrawl / Browserbase** | Programmatic extraction from individual prospect websites — never from platforms | |
| 149 | |
| 150 | **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. |
| 151 | |
| 152 | --- |
| 153 | |
| 154 | ## Output Formats |
| 155 | |
| 156 | ### Default — chat table |
| 157 | |
| 158 | For SaaS / B2B (≤25 rows): |
| 159 | |
| 160 | ``` |
| 161 | | Score | Company | Industry | Size | Signal | Contact | Email status | Source | Confidence | |
| 162 | | --- | --- | --- | --- | --- | --- | --- | --- | --- | |
| 163 | ``` |
| 164 | |
| 165 | For Local SMB (≤15 rows) — port from the local-prospector reference: |
| 166 | |
| 167 | ``` |
| 168 | | Score | Business | Category | Area | Website status | Website/Social | Phone | Why it's a prospect | Confidence | |
| 169 | | --- | --- | --- | --- | --- | --- | --- | --- | --- | |
| 170 | ``` |
| 171 | |
| 172 | ### CSV — when >25 rows or user requests a file |
| 173 | |
| 174 | SaaS / B2B columns: |
| 175 | |
| 176 | ```csv |
| 177 | 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 |
| 178 | ``` |
| 179 | |
| 180 | Local SMB columns: |
| 181 | |
| 182 | ```csv |
| 183 | score,business,category,area,distance_km,website_status,website_url,social_urls,phone,email,source_urls,why_prospect,confidence,verified_date,notes |
| 184 | ``` |
| 185 | |
| 186 | ### Always include after the table |
| 187 | |
| 188 | - **Top outreach targets**: top 3–5 hot leads with one-sentence outreach rationale each |
| 189 | - **Search parameters**: branch, ICP, location/radius, target count, date generated |
| 190 | - **Open questions**: anything you couldn't verify and the user should look at |
| 191 | |
| 192 | --- |
| 193 | |
| 194 | ## Quality Checks (before finalizing) |
| 195 | |
| 196 | - [ ] Remove duplicates (by domain for SaaS/B2B, by business + address for Local SMB) |
| 197 | - [ ] Every "Hot" lead has a verified contact + at least one source URL |
| 198 | - [ ] No lead has an email that failed Truelist (or your validator) verification — move to a separate "invalid" bucket and flag for the user |
| 199 | - [ ] No lead labeled "Hot" lacks a clear buying signal |
| 200 | - [ ] Confidence levels honest — "High" requires 2 independent sources, not just two of your own searches |
| 201 | - [ ] No leads sourced from prohibited scraping (LinkedIn at scale, Google Maps bulk extract, etc.) |
| 202 | - [ ] Source URL + date captured for every contact (GDPR / CAN-SPAM lineage) |
| 203 | - [ ] Final count matches user's request, or you've explained why it's smaller (quality bar) |
| 204 | |
| 205 | --- |
| 206 | |
| 207 | ## Common Mistakes |
| 208 | |
| 209 | 1. **Starting discovery without an ICP**. Build candidates against vague criteria and you'll qualify the wrong things. |
| 210 | 2. **Treating data sources as authoritative without cross-checks**. Apollo and ZoomInfo are out of date often; verify before scoring as "Hot." |
| 211 | 3. **Adding contacts without email verification**. Cold email reputation tanks fast with bounces — always validate. |
| 212 | 4. **Bulk scraping LinkedIn or Google Maps**. Real risk: account suspension + ToS violation. Browser as an assisted tool only. |
| 213 | 5. **Mixing branches**. Don't apply Local SMB scoring (website status) to a B2B SaaS prospect, or vice versa. |
| 214 | 6. **"Hot" labels without buying signals**. ICP fit alone is not enough — the signal is what makes the timing right. |
| 215 | 7. **No source URLs**. Every claim should be traceable to a public source. Future outreach depends on this lineage. |
| 216 | 8. **Ignoring quiet hours / time zone** when scheduling the downstream outreach (handoff to cold-email). |
| 217 | 9. **Forgetting to retain consent / lineage records**. Required for GDPR DSARs and CAN-SPAM audits. |
| 218 | |
| 219 | --- |
| 220 | |
| 221 | ## Task-Specific Questions |
| 222 | |
| 223 | 1. Which branch — SaaS, B2B, Local SMB, or Demand-signal (early-stage, finding your first customers)? |
| 224 | 2. What's your ICP? (Or: should I pull from your product-marketing context?) |
| 225 | 3. How many qualified leads do you want? |
| 226 | 4. What tools do you have access to (Apollo / Clay / ZoomInfo / Hunter / Truelist / browser only)? |
| 227 | 5. What's the triggering buying signal you care most about? |
| 228 | 6. Geography or radius (Local SMB / B2B)? |
| 229 | 7. Chat table or CSV? |
| 230 | |
| 231 | --- |
| 232 | |
| 233 | ## Tool Integrations |
| 234 | |
| 235 | For implementation, see the [tools registry](../../tools/REGISTRY.md). Key prospecting tools: |
| 236 | |
| 237 | | Tool | Best For | MCP | Guide | |
| 238 | |------|----------|:---:|-------| |
| 239 | | **Apollo** | B2B / SaaS firmographic + contact discovery | - | [apollo.md](../../tools/integrations/apollo.md) | |
| 240 | | **Clay** | Multi-source enrichment + waterfall | ✓ | [clay.md](../../tools/integrations/clay.md) | |
| 241 | | **Clearbit** | Email-to-company enrichment | - | [clearbit.md](../../tools/integrations/clearbit.md) | |
| 242 | | **ZoomInfo** | Enterprise B2B contact + intent | ✓ | [zoominfo.md](../../tools/integrations/zoominfo.md) | |
| 243 | | **Hunter** | Email pattern + verification | - | [hunter.md](../../tools/integrations/hunter.md) | |
| 244 | | **Snov** | Email finder + verifier | - | [snov.md](../../tools/integrations/snov.md) | |
| 245 | | **Truelist** | Email deliverability validation | - | [truelist.md](../../tools/integrations/truelist.md) | |
| 246 | | **Outreach** | Sales engagement (post-list) | ✓ | [outreach.md](../../tools/integrations/outreach.md) | |
| 247 | | **RB2B** | Visitor identification (warm intent) | - | [rb2b.md](../../tools/integrations/rb2b.md) | |
| 248 | | **GitHub** | Stargazers/forks/watchers as developer-intent signal | - | [github.md](../../tools/integrations/github.md) | |
| 249 | | **Firecrawl** | Single-target site extraction (prospect's own website) | ✓ | [firecrawl.md](../../tools/integrations/firecrawl.md) | |
| 250 | | **Browserbase** | Real-browser site research when rendering or interaction needed | ✓ | [browserbase.md](../../tools/integrations/browserbase.md) | |
| 251 | |
| 252 | --- |
| 253 | |
| 254 | ## Related Skills |
| 255 | |
| 256 | - **cold-email**: For writing outbound sequences against the qualified list (the natural next step after prospecting) |
| 257 | - **customer-research**: For understanding why current customers buy — informs the ICP definition |
| 258 | - **competitor-profiling**: For deeper research on individual accounts (different from list-building qualification) |
| 259 | - **revops**: For lead routing, lifecycle, and CRM handoff after prospecting |
| 260 | - **sales-enablement**: For battle cards and one-pagers used in the outreach |
| 261 | - **directory-submissions**: For inbound discovery surfaces (the prospects might find you back) |
| 262 | - **product-marketing**: For the ICP definition that anchors every prospecting engagement |
| 263 |
Reviews
Installed this one?Write the first review and take the Trailblazer badge.
Alternatives
Subagent Driven DevelopmentUse when executing implementation plans with independent tasks in the current session◐◐◐◐◐●36/40Python Code Style & DocumentationPython code style, linting, formatting, naming conventions, and documentation standards. Use when writing new code, reviewing style, configuring linters, writing docstrings, or establishing project standards.◐····●35/40Competitor Price Analysis 💲Competitor pricing strategy analysis and market positioning. Price mapping, pricing gaps identification, elasticity signals evaluation, and strategic pricing optimization. Use when the user asks about competitor pricing, price analysis, pricing strategy, or co◐····●34/40Competitor Price Tracker 📊Set up competitor price tracking and monitoring workflows. Track price changes, detect promotions, analyze pricing patterns, and get alerts for competitive price movements.◐····●34/40