メニュー
Defines and refines who the org sells to. Use for ICP discovery, segment refinement, new segment creation, persona definition, and tightening the rubric used by scoring and outreach.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use this skill when the user wants to submit, contribute, or publish a GTM skill to the GTM Skills library (github.com/swan-gtm/gtm-skills, gtmskills.com), or update one of their existing skills or their creator profile there.
Use this skill when [the concrete trigger — a signal fires, a moment in the deal, a recurring cadence]. Produces [the concrete output]. [One or two more sentences dense with the phrases someone would actually say when they need this.]
Use this skill when a deal closes won and you want to turn the win into pipeline immediately. It extracts the win profile, finds lookalike companies not yet in your CRM, researches the right persona contact at each, drafts outreach from the deal owner using an anonymized win reference, and queues a single batch review task — nothing sends without human approval.
Use this skill when scoring a paying customer (closed-won account) for expansion. It evaluates product usage depth, persona quality, and expansion headroom to produce an expansion tier with short actionable reasoning. Designed as a sub-skill of your lead-scoring methodology — the parent runs the ACV assessment first and this returns a tier to it.
Use this skill when a profile-view webhook (e.g. LeadShark) fires for a new view on a team member's LinkedIn profile. It resolves the viewer's identity and company, applies dedup, internal, relationship, and ICP gates, and routes qualified viewers into the MQL pipeline — treating a profile view exactly like a website visit. The CRM is never polluted: only fully resolved, ICP-matched viewers reach a CRM write.
Use this skill when a tracked influencer publishes a LinkedIn post focused on your product (sponsored, review, or organic mention) and you want to capture the engagers as leads. It verifies the post is genuinely about you, scrapes the full engager list, filters to ICP-fit companies and buyer personas, runs lead scoring, and posts per-lead alerts plus a reconciled digest. Detection and scoring only — no outreach.
| name | icp |
| title | ICP |
| description | Defines and refines who the org sells to. Use for ICP discovery, segment refinement, new segment creation, persona definition, and tightening the rubric used by scoring and outreach. |
| category | Prospecting |
Setup state. Configured Jun 8, 2026 via website/case-study evidence (Path B — no CRM connected). 3 segments: Cloud-Native B2B SaaS Engineering Teams (100–1,000 emp, B2B SaaS, AWS-first, post Series B), Fintech & Payments Infrastructure (50–500 emp, fintech/payments, cloud-native, compliance-driven), Digital Media, Streaming & Gaming (200–2,000 emp, high-traffic consumer platforms). 4 personas: SRE/Platform Engineer (Champion), VP/Director of Engineering (Economic Buyer), Head of DevOps/Infrastructure Lead (Champion/Evaluator), Engineering COO/CTO (Economic Buyer, Fintech segment). Next refinement: connect CRM to validate against real win/loss data.
Two day-to-day jobs:
First-time discovery lives in Setup — load it if the state check tells you to.
Pull the current segments, personas, target markets, value prop. Print them back to the user in one or two lines each so they remember what they're refining. Ask: "Anything specific that feels off, or should I scan recent deals broadly?"
Start narrow: closed-won and closed-lost deals from the last 6 months. Check the CRM if one is connected — pull the deal stage history, the associated company, the close date, the win/loss reason if populated. Page size 20.
If there are more than 60 closed deals in the period, switch to swan-execute-code: dump the deals query result to a file and aggregate there. Don't load 200 deal records into context.
If no CRM is connected, ask the user to name their last 5–10 closed-won and closed-lost deals — work from the named list. If they can't, refinement isn't possible yet; recommend they connect the CRM or come back when more deals have closed.
Search Swan's company records first. If size, industry, or stage is missing on more than 20% of records, flag the gap — don't enrich-everything to fill it. The analysis will be partial without that data; say so.
In swan-execute-code (or by hand if ≤ 20 deals), group wins vs losses by:
Print a short table per dimension. Don't paste raw deal data.
Compare patterns to the current ICP. Look for:
For each proposed change, write one line: "tighten size band to 50-300 (current: 50-1000). wins concentrate in 50-300, losses spike above 500."
Present 3–5 proposed changes. More than that means the ICP needs full discovery — route to Setup.
Ask the user which changes to apply. For each confirmed change:
swan-update-knowledge-segment on the existing segment.swan-create-icp-segment.swan-create-knowledge-persona or swan-update-knowledge-persona.swan-update-knowledge-value-prop.Confirm what was saved. Recommend running scoring on the next batch of unscored accounts to validate the refinement.
A great refine pass:
Failure modes to avoid:
Setup./icp.Add over time as the org's GTM motion sharpens:
SegmentDeepDive.md — when the org has 2+ segments with materially different motions, capture per-segment refinement playbooks (which dimensions matter most for that segment, which losses are noise).PersonaSharpening.md — when the persona work goes beyond title + responsibilities into career-stage signals, activity signals, and disqualifiers (the old ideal-buyer-profile territory).Drift.md — drift report flow once the org has 4+ quarters of history (folded in from icp-evolution if/when consolidated).SegmentBirth.md — process for spinning up a fresh segment when one wins cluster is materially different from the rest.