Qué hace
prospecting es una skill de marketing creada por Corey Haines. Le da a Claude un método para pasar de "necesito clientes" a una hoja de leads calificada y lista para contactar. En vez de tirarte una base comprada, sigue cinco fases: definir el ICP (cliente ideal), levantar candidatos (2 a 3 veces más de los que querés porque después poda), calificar cada uno con evidencia, ponerle un score (Hot, Warm, Cold, Skip) y devolver la lista con el top 3 a 5 para atacar primero.
La skill se bifurca según a quién le vendas: SaaS B2B, B2B general o negocio local. Cada rama usa fuentes y señales distintas, pero comparten el mismo esqueleto y, sobre todo, los mismos guardrails de compliance: cada lead viene con su URL de fuente, su fecha y su nivel de confianza. Nada de scraping masivo, nada de datos sin trazabilidad.
Cómo aplicarla a tu negocio
En una agencia como la nuestra, el cuello de botella de ventas casi nunca es "no hay a quién venderle": es que la lista de prospectos está desactualizada, sin señal de por qué contactar ahora, y llena de emails que rebotan. prospecting ataca justo eso.
Caso real, montar el pipeline de un cliente B2B (una consultora que le vende a mandos medios de pymes):
- Fijá el ICP antes que nada. La skill no te deja saltear este paso, y con razón. Definís rubro, tamaño, geografía y, clave, la señal de compra que te importa (ronda de inversión, apertura de sucursal, contrataciones, bronca con el proveedor actual). Un ICP flojo califica las cosas equivocadas.
- Dejá que sobre-genere y pode. Le pedís 25 leads y la skill levanta 60 candidatos para después cortar sin culpa. Veinticinco leads verificados le ganan a 250 basura: menos rebotes, mejor reputación de dominio, más respuestas.
- Exigí evidencia en cada calificación. Nada de "Hot" porque sí. Un lead solo es Hot si tiene fit de ICP, señal de compra clara, decisor accesible y contacto verificado. La skill valida deliverability del email antes de sumarlo, así no quemás la casilla contra bounces.
- Salí con el top 3 a 5. La hoja termina con los mejores leads y una línea de por qué contactar a cada uno primero. Eso es lo que le pasás al que escribe el mensaje o cargás al CRM.
Lo potente para marketing es la trazabilidad: como cada contacto guarda fuente y fecha, cuando después mandás el email en frío tenés el linaje que exige GDPR y CAN-SPAM. Combinala con tu CRM (nosotros la enganchamos con Twenty) para que la lista calificada entre directo al flujo de outbound, sin repasar a mano.
Cómo instalarla
Es una skill agent-agnostic: el mismo archivo corre en cualquier agente. Trae archivos de referencia por rama (SaaS, B2B, local) y un registro de herramientas, así que conviene clonar la carpeta entera, no solo el SKILL.md.
- Claude Code: cloná el repo de Corey Haines y copiá la carpeta
skills/prospecting/completa a.claude/skills/. - Cursor: copiá el
SKILL.mda.cursor/rules/(y las referencias al lado si querés las ramas por motion). - Codex: copiá el
SKILL.mda.codex/skills/.
El SKILL.md completo (con la licencia MIT y la fuente) está más abajo.
El SKILL.md completo
Skill original de Corey Haines (MIT). Fuente: https://github.com/coreyhaines31/marketingskills/tree/main/skills/prospecting
<!-- Skill original: prospecting, Corey Haines (https://github.com/coreyhaines31/marketingskills/tree/main/skills/prospecting) Licencia: MIT. Reproducida con atribución según los términos de la licencia. Curada al español en claura-ai.com/skills. --> --- 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," or "qualified leads." 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: 1.0.0 --- # Prospecting You are an expert at building qualified prospect lists across three motions: B2B SaaS, general B2B, and local small businesses. 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 | 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. 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) --- ## 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 a 3× more candidates than the user wants in the final list, qualification will cull aggressively. - **SaaS / B2B**: combine 2 a 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 across all branches: | 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 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 a 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. 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), usually inferable from context - **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 a 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, or Local SMB? 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
Scrolleá dentro del bloque para ver la skill completa, o usá el botón de copiar.
Preguntas frecuentes sobre la skill prospecting
prospecting es una skill de marketing de Corey Haines (github.com/coreyhaines31/marketingskills) que le enseña a Claude a construir listas de prospectos calificadas. Arranca de tu ICP (cliente ideal), levanta candidatos desde fuentes públicas, los califica con evidencia (URL de fuente + nivel de confianza), les pone un score (Hot, Warm, Cold, Skip) y devuelve una hoja de leads lista para el outbound. Cubre tres motions distintos: SaaS B2B, B2B general y negocios locales, cada uno con sus señales de calificación.
El valor está en que no te tira una base fría comprada: te arma una lista corta y verificada donde cada lead tiene una razón concreta de por qué es prospecto y una señal de compra (financiación, contratación, cambio de proveedor). Primero fijás el ICP, después la skill sobre-genera candidatos y los poda agresivamente, verifica los emails antes de sumarlos y prioriza el top 3 a 5 para contactar primero. Vos usás esa lista para el CRM y el mensaje. Si querés todo el sistema de captación y seguimiento montado, mirá el agente de contenido.
La skill trae guardrails de compliance explícitos: nada de scraping masivo de LinkedIn ni Google Maps, solo canales de contacto públicos del negocio (info@, contacto@, roles nombrados), y guarda la URL de fuente y la fecha de cada contacto para tener trazabilidad GDPR y CAN-SPAM. Es list building para tu propio outbound, no reventa de datos. Ese registro de origen es lo que después te cubre cuando mandás el primer email en frío.
Prospecting resuelve solo la fase de armar y calificar la lista. El paso siguiente es escribir la secuencia de contacto (la skill original lo delega a cold-email) y cargar los leads al CRM. Si querés una vuelta más automatizada de cómo la IA acelera tu día comercial, leé 36 prompts de Claude para hacer crecer tu marca.
