Skip to content

JasonColapietro/suede-creator-skills / skills/suede-prospecting

suede-prospecting

Verified

Build a source-backed, scored prospect list across SaaS, B2B, local business, or early demand signals. Use when asked to "find our first design partners", define an ICP, enrich leads, run gap plays or warm-path network mining, or document disqualification evidence. Includes source dates, confidence, licensed-data checks, and a qualification handoff. NOT FOR: sending outreach (use suede-cold-email), CRM routing (use suede-revops), or competitor profiles (use suede-competitor-profiling).

Suede Prospecting Skills

Compatibility

Works from supplied URLs, exports, or source text; live sourcing needs an authorized browser or research connector. The bundled scripts/collect.mjs (Node 22+, no API keys) pulls free public account signals; no paid enrichment service is bundled.

For a concrete input, expected handoff, and failure check, read the worked handoff.

Suede Prospecting turns an approved ICP into a source-backed, scored lead sheet across B2B SaaS, general B2B, local business, and early demand-signal motions. Every candidate carries qualification evidence, disqualification logic, and a compliance-aware handoff before outreach begins.

IRON LAW: every row carries a source URL and the date it was captured,
or it does not ship. No exceptions, no "verify later," no placeholder rows.

That single rule is what makes the downstream GDPR / CAN-SPAM lineage real. A row without it is not a low-confidence lead: it is not a lead.

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:

BranchSell toWhat "qualified" looks likePossible sources after access and terms checks
SaaSOther SaaS companies / digital businessesICP fit + tech stack match + growth signals (funding, hiring, product velocity)Public company sites, directories, developer sources, or licensed data available to the user
B2BNon-SaaS B2B (services, manufacturers, enterprises, mid-market)Industry + size + geographic fit + buying signals (trigger events, vendor changes)Public company records, industry directories, or licensed business data available to the user
Local SMBLocal small businesses (shops, gyms, restaurants, clinics, salons, services)Active business + website status + proximity + decision-maker accessPublic business sites and manually reviewed listings allowed by their terms
Demand-signalEarly-stage: first customers, design partners, or beta usersA cited public pain, demand, or timing signal, not just firmographic fitPublic forums, reviews, issues, posts, jobs, and launch records reachable with current authorized tools or manual review

Before using any named platform or vendor, discover what is currently callable, authenticated, authorized, and permitted by its terms. If no research connector or browser is available, give the user a manual source checklist and work from URLs, exports, screenshots, or source text they provide.

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:


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)

Start at 2-3x the requested output count, adjusted down for thin source access or review capacity. Expand only when the observed disqualification rate shows another batch is needed, and cap expansion at 3 rounds. At the cap, stop sourcing: report the disqualification rate you observed and hand back a narrower ICP proposal rather than grinding through more sources.

  • SaaS / B2B: cross-check material claims across available first-party, public, or licensed sources. Named vendors are candidates only after access, freshness, terms, and cost checks.
  • Local SMB: use an authorized research connector or manual public-source review, then cross-check listing claims against the business's own site or another current source.

A smaller evidence-complete list is preferable to padding the output with unverified candidates. Don't start qualification until every candidate has its source URL captured.

Warm paths before bought lists. Mine the relationships the user already has before sourcing cold. A warm introduction gets read when the twentieth cold email of the day doesn't, and AI-written outreach widens that gap.

  1. Export the network. LinkedIn connections (Settings, Data privacy, Get a copy of your data), calendar attendees, and inbox contacts. This is the user's own data export, not scraping. LinkedIn's export includes emails only for connections who allow it.
  2. Enrich and score every contact against the ICP like any other list.
  3. Match against target accounts to find first- and second-degree paths into the companies the user wants.
  4. Start with the calendar. Recent meetings show who is in a buying moment now.
  5. Find one connector per vertical: someone trusted by buyers who ignore cold outreach. Pay them the way you would pay for a qualified meeting, and disclose the arrangement.
  6. Double opt-in intros only. Ask the connector, then the target, before anyone is introduced. A human approves every intro, and no contact is asked to take intros for two vendors in the same week. Trust is the asset; spend it slowly.

Warm-path method adapted from Cody Schneider's podcast with Chris of Super Connector (October 2026).

For gap plays (a signal plus a gap you can verify from outside, such as ads running with no visible tracking), see the "Gap Plays" section of references/saas-prospecting.md.

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.

Free account signals first. Before spending enrichment credits, run the bundled collector per account (references/collector.md):

  1. dns <domain>: email senders and verified tools (technographics).
  2. jobs <board-slug>: open roles by function and marketing channel, a strong buying trigger.
  3. Shortlist only: stack <domain> (pixels and tools with first-seen month), subdomains <domain> (new launches), adoption --npm/--pypi/--github (developer-tool accounts), and ads (ad-library links: are they spending on paid?).

Each value is a dated public observation and one source toward confidence: stamp it with its command, source, and pull date. When output says blocked by <host>, record the signal as not collected. A missing pixel or board is not disqualification evidence by itself. The collector studies companies only; never use it to gather personal data.

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, discover whether an authorized validator is callable and read its current result semantics before use. If none is available, label the address unverified, keep it out of send-ready exports, and provide a user-operated validation checklist. Never claim that validation guarantees delivery. Don't move to scoring until every candidate carries a confidence level.

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.

ScoreDefinition
HotICP fit (passes the full Phase 1 ICP checklist) + clear buying signal + decision-maker accessible + verified contact
WarmICP fit + softer or older signal + contact verifiable
ColdLoose ICP fit OR no clear signal OR contact unverified
SkipDisqualifier hit (out of ICP, closed business, duplicate, irrelevant, low confidence)

Branch-specific signals refine the scoring: see each reference file. Let the evidence determine the number in each label; never force a Hot/Warm/Cold quota. No row leaves this phase labeled Hot without both a buying signal and a verified contact: downgrade it to Warm instead.

Phase 5: Output the lead sheet

(SaaS / B2B / Local SMB. The Demand-signal branch ships an evidence report instead: see 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, add "Priority review candidates" when the evidence supports one or more: a bounded set ranked by current signal strength, with one sentence on what was verified and what still needs review.

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

The sheet is not deliverable until it also carries the search parameters used and the open questions left unresolved.


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, Clay, HubSpot Breeze Intelligence) 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.


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: use the requested count or propose a bounded pilot justified by source coverage and review capacity
  • Geography (essential for Local SMB; useful for B2B; less critical for SaaS)
  • Tools the user has access to: discover current callable tools and authenticated accounts; never assume a vendor connector or browser exists
  • Output format: chat table (default) or CSV
  • Buying signal preference: what triggers should they prioritize? (funding rounds, hiring, recent move, etc.)

Tool Selection

Treat every named product below as a candidate, not an available capability. These are selection examples, not guaranteed integrations: discover what is currently callable and verify the user's authenticated access, license, source terms, data freshness, export rights, and cost before using one. Full breakdown in references/data-sources.md.

If the user has access to...Use it forVerify Before Use
ApolloB2B / SaaS firmographic + contact discoveryFreshness, export terms, email validation
ClayMulti-source enrichment, waterfall lookups, custom scoringCredit cost, providers, field provenance
HubSpot Breeze Intelligence (formerly Clearbit)Company enrichment inside HubSpotHubSpot tier, credits, coverage
ZoomInfoEnterprise B2B contact + intent dataLicense, export rights, signal freshness
Hunter or SnovEmail pattern discovery and verificationVerification status and lawful basis
TruelistEmail deliverability validation before outreachResult meanings and current API limits
LinkedIn Sales NavigatorDecision-maker mapping (manual, no scraping)Platform terms; no bulk extraction
Bundled collect.mjs (free)DNS tools, stack history, hiring, launches, ad linksPull date; homepage-only stack; collector gaps
BuiltWith / WappalyzerTech stack qualification (SaaS branch)Detection accuracy and staleness
CrunchbaseFunding signals (SaaS branch)Record recency and license tier
GitHubStargazers / forks, public developer-intent signalsAPI terms, rate limits, company mapping
Google Maps + browserLocal SMB discoveryTerms; assisted review only, no bulk extract
OutreachSales engagement after approvalSequence permissions and suppression rules
RB2BVisitor identificationPrivacy basis and company-vs-person grain
Firecrawl / BrowserbaseSingle prospect websites: never platformsTarget terms, scope, and session access

If the user has no enrichment or browser tools: provide exact public-source queries and a qualification worksheet, then work from URLs, exports, or screenshots the user supplies.


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:

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:

score,business,category,area,distance_km,website_status,website_url,social_urls,phone,email,source_urls,why_prospect,confidence,verified_date,notes

Include after the table

  • Priority review candidates: a bounded evidence-ranked set with one-sentence 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
  • Email status comes from a currently authorized validator with documented result semantics, or is explicitly unverified; failed results stay in a separate invalid bucket
  • 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)
  • Every collector value carries its source and pull date; blocked signals read not collected
  • Final count matches user's request, or you've explained why it's smaller (quality bar)

Any unchecked box means the sheet is not deliverable. Name the failing box and what is missing, rather than shipping the sheet with a caveat attached.


Common Mistakes

  1. Treating data sources as authoritative without cross-checks. Apollo and ZoomInfo are out of date often; verify before scoring as "Hot."
  2. Mixing branches. Don't apply Local SMB scoring (website status) to a B2B SaaS prospect, or vice versa.
  3. Ignoring quiet hours / time zone when scheduling the downstream outreach (handoff to suede-cold-email).
  4. Forgetting to retain consent / lineage records. Required for GDPR DSARs and CAN-SPAM audits.

Boundaries

  • Do not send outreach, import contacts, buy data, mutate a CRM, or enroll a person in a sequence.
  • Do not invent contact details or qualification evidence, evade source terms, collect unnecessary personal data, or label a lead verified without a cited current source.
  • Do not decide legal compliance or claim deliverability. Apply the applicable consent, privacy, and suppression rules before any downstream contact.

Routing

  • Use suede-product-marketing to define the ICP and positioning context.
  • Use suede-cold-email after a qualified list is approved for outreach copy.
  • Use suede-revops for approved CRM routing and lifecycle handoff.
  • Use suede-sales-enablement for collateral used in active sales work.
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall