icp-definition

ICP Definition

Produce a tiered, scored, evidence-backed Ideal Customer Profile that drives every downstream GTM decision — written tightly enough that a new SDR can apply it on day one without judgment calls.

Framework(s) used: 100-pt scorecard (Pain 25 / Trigger 20 / WTP 20 / Reach 15 / TTV 10 / Strategic 10), role-map (Buyer/Champion/User/Blocker), anti-ICP boundary — tightly opinionated framework — do not swap; if user wants a different scorecard, trigger Clarification Protocol. If multiple frameworks apply, trigger Clarification Protocol so the user picks.

Clarification Protocol

When you encounter any of the following, STOP and ask the user — do NOT make a silent assumption, and do NOT flatly refuse:

• Ambiguous or missing input
• A fork in approach (multiple valid frameworks, segments, scopes, or sources)
• A rule that would block progress
• An assumption that materially shapes the output
• Unverified data that a downstream step depends on

Present 2–4 concrete options with trade-offs and your recommendation.

Format:

Decision needed: <what's being decided> Options:

• A) <option> — trade-off
• B) <option> — trade-off
• C) <option> — trade-off My recommendation: <X> because <reason>. Confirm or pick a different option before I continue.

Refusing to proceed is NEVER the final answer. Every "block" must come with an override option. If the user picks an override, honor it on the first request — do not re-prompt the same block multiple times in one run.

Scope

This skill ONLY produces tiered Ideal Customer Profile with scorecard, role-map, and anti-ICP boundary. Do not expand into adjacent topics. If the user's request implies adjacent scope, trigger Clarification Protocol with options to (A) stay in scope, (B) note the adjacent need as a follow-up, (C) hand off to a different skill.

Verification Requirements

Before producing the final output, every factual claim about external entities (markets, competitors, people, companies, technologies, pricing, benchmarks) MUST be verified via web search.

• Use a quick lookup for single-fact checks (one company, one stat).
• Use a deep search for landscape/trend questions (multi-source synthesis).
• Tag every verified claim inline as [H/M/L][Sn].
• End the report with a ## Sources section.
• Unverified claims belong in ## Assumptions to Validate, NOT in the main analysis.

Sources are mandatory. If you cannot cite a source for a factual claim, do not state it as fact — move it to Assumptions to Validate or trigger Clarification Protocol.

When to Use

• User asks to define or refine their ICP
• User wants qualification rules or sales-marketing alignment on target customer
• Pre-outbound grounding before lead sourcing
• Anti-ICP definition — "who should we say no to"
• Persona work — buyer + champion + user + blocker mapping
• User says "what makes a lead qualified" or "when should an SDR disqualify"

Legend — Tier cutoffs & Confidence Score

• Tiers: Tier 1 ≥75 / Tier 2 55–74 / Tier 3 40–54 / Anti-ICP <40
• [H] High — ≥2 independent primary sources within 6 months (firmographic claims)
• [M] Medium — single primary source OR multiple secondary sources agree
• [L] Low — inferred / single secondary source / >12 months old

Quick Reference

Concept	Value
Scorecard weights	Pain 25 / Trigger 20 / WTP 20 / Reach 15 / TTV 10 / Strategic 10 = 100
Tier cutoffs	Tier 1 ≥75, Tier 2 55–74, Tier 3 40–54, Anti-ICP <40
Roles required	Buyer (Economic) / Champion / User (End) / Blocker — fill all four
Pain-Trigger-Outcome	chronic problem → workaround + cost → acute event → measurable success state
Trigger types	Type: need (pain acute) vs Type: buy (budget/process opens). Both required.
Anti-ICP lenses	Firmographic / Pain / Buyer / Trigger
SDR qualify time	2 minutes using handoff doc

Procedure

1. Anchor in evidence. Pull last 10–20 won deals. Capture company, size, role, pain, trigger, ACV. If 0 customers → mark "hypothesis-only", confidence cap Low.
2. Define buyer firmographic. Industry (specific), size range, stage, geography, tech-stack signals, operating model. Test: produces 500–5,000 candidate accounts. Before locking segment boundaries, trigger Clarification Protocol if the user has provided multiple plausible segment definitions or if the won-deal evidence is split.
3. Fill four roles. Buyer / Champion / User / Blocker — title patterns, what they care about, what kills the deal, where to find them. See ${HERMES_SKILL_DIR}/references/role-map.md.
4. Build Pain-Trigger-Outcome chain. In buyer language. Include Workaround Analysis: what they do today, cost (time/money/risk/accuracy/reputation), 90-day dream state. See ${HERMES_SKILL_DIR}/references/pain-trigger-outcome.md.
5. Build trigger library. 5–10 specific triggers, each tagged Strength + Type: need or buy + named detection source. At least one buy-trigger required.
6. Run 100-point scorecard. Apply to ≥9 accounts (3 best-fit, 3 mid, 3 anti-ICP). If scores cluster, re-tune weights. See ${HERMES_SKILL_DIR}/references/scorecard-rubric.md.
7. Define Anti-ICP. 4 boundaries (firmographic / pain / buyer / trigger), each with rule + rationale.
8. Generate Tier 1/2/3 examples. 3 named accounts per tier with score breakdown.
9. Produce ICP one-pager + SDR handoff. Single document, 2-minute usable. See ${HERMES_SKILL_DIR}/references/sdr-handoff-template.md.

Pitfalls

• Aspirational ICP — describing the customer you wish you had vs. the one you actually win
• One-role ICP — missing champion or blocker causes stalled deals
• Pain without trigger — buyer hurts but isn't acting; pain alone doesn't fund a deal
• Skipping Anti-ICP — sales wastes capacity chasing fit-but-misqualified accounts
• Generic firmographic — "B2B SaaS" is not a firmographic; be specific
• Static ICP — re-run every 6 months minimum, faster if motion changes
• Logo lust — "we want BigCo" is wishful thinking, not ICP work

Verification

1. SDR can qualify a lead in 2 minutes using the handoff doc
2. Marketing can write outbound sequences using Pain-Trigger-Outcome directly
3. Anti-ICP is specific enough that 3 disqualifiers can be stated without thinking
4. 100-pt scorecard differentiates won from lost deals when applied retroactively

Output Format

• Sections required: ICP Profile (Firmographics, Technographics, Pains, Triggers, Buying Committee, Disqualifiers), Anti-ICP, Sources, Assumptions to Validate
• Tables / fields: Buying Committee table = Role | Title patterns | What they care about | What kills the deal | Where to find them; Trigger library table = Trigger | Type need/buy | Strength [H/M/L] | Detection source [Sn]
• Length target: 800–1,500 words (includes 1-page SDR handoff)
• File type: markdown
• Mandatory closing sections: Verification Notes, Sources, Assumptions to Validate, Next Step