lookalike-customer-finder — Claude Code skill: how to install
Analyzes your top customer accounts to find matching target companies. It builds an ICP, scores prospects from 0 to 100, and tiers a 100-account list.
npx skills add OneWave-AI/claude-skills --skill lookalike-customer-finder -a claude-codeWhat lookalike-customer-finder does
The workflow starts from your best existing customers. If you do not provide any, the skill asks for 5 to 10 accounts. It evaluates shared traits across five profile dimensions defined in references/scoring-model.md. The agent then builds an Ideal Customer Profile and scans the market for companies fitting that profile by checking firmographic data and growth signals.
Every prospect receives a similarity score between 0 and 100. It groups 100 matching companies into three tiers: 10 priority accounts in Tier 1, 40 in Tier 2, and 50 in Tier 3. The final report follows references/output-template.md, delivering market insights alongside a targeted outreach plan.
Providing account domains upfront avoids an extra round of questions.
What it helps with
- identify lookalike B2B accounts based on existing top customers
- build an ideal customer profile from 5 to 10 key accounts
- score target companies on a 0 to 100 similarity scale
- tier 100 target accounts into priority groups for sales outreach
Example prompts for the agent
- Find lookalike companies based on our top customers: Stripe, Brex, and Ramp
- Generate a ranked target account list of 100 companies matching our ICP
- Score these target accounts using the lookalike-customer-finder model
How to install lookalike-customer-finder
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill lookalike-customer-finder -a claude-code2Manually: put the files in place
~/.claude/skills/lookalike-customer-finder/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/lookalike-customer-finder/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill lookalike-customer-finder -a codex2Manually: put the files in place
.agents/skills/lookalike-customer-finder/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill lookalike-customer-finder -a cursor2Manually: put the files in place
.cursor/skills/lookalike-customer-finder/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OneWave-AI/claude-skills lookalike-customer-finder2Manually: put the files in place
.github/skills/lookalike-customer-finder/SKILL.md1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill lookalike-customer-finder -a gemini-cli2Platform CLI
gemini skills install https://github.com/OneWave-AI/claude-skills --path lookalike-customer-finderManually: put the files in place
.devin/skills/lookalike-customer-finder/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill lookalike-customer-finder -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about lookalike-customer-finder
How do I install lookalike-customer-finder in Claude Code?
Run npx skills add OneWave-AI/claude-skills --skill lookalike-customer-finder -a claude-code in your terminal.
How does the skill tier target accounts?
It scores candidates from 0 to 100 and splits 100 companies into three tiers: top 10 in Tier 1, 40 in Tier 2, and 50 in Tier 3.
What input is required to start the analysis?
Provide a list of 5 to 10 of your best customer accounts. If omitted, the agent will prompt you for them before building the profile.
Source text
SKILL.md · MIT
--- name: lookalike-customer-finder description: Input your best customers and find 100+ companies that match the profile. Uses firmographic data, tech stack, growth signals, and similarity scoring to identify ideal prospects. Use when building target account lists or expanding to new markets. --- # Lookalike Customer Finder Analyze a company's best customers and find similar companies that match the same profile, producing a high-quality, ranked target account list. ## Contents - `references/scoring-model.md` - Profile dimensions, weighted scoring model, and score bands. - `references/output-template.md` - Full Markdown report structure (ICP, ranked lookalikes, market insights, targeting strategy, action plan). - `references/data-sources.md` - Recommended enrichment tools and data points to gather. - `references/examples.md` - Best practices, trigger phrases, and an example request. ## Workflow 1. Collect the best customers provided. If none are given, ask for the top 5-10 accounts. 2. Analyze common characteristics across them. See `references/scoring-model.md` for the five profile dimensions. 3. Build the Ideal Customer Profile (ICP) from those shared traits. 4. Search the market for companies matching the ICP. Pull firmographics, tech stack, growth signals, and contacts from the tools in `references/data-sources.md`. 5. Score each candidate 0-100 using the weighted scoring model in `references/scoring-model.md`. 6. Rank and tier the companies by score (Tier 1: top 10, Tier 2: next 40, Tier 3: next 50). 7. Produce the report following `references/output-template.md`, including market insights, a tiered targeting strategy, and a quick-start action plan. 8. Apply the best practices in `references/examples.md` throughout: favor quality over quantity, weight growth signals, and enrich contacts before recommending outreach.
© OneWave-AI · MIT · OneWave-AI/claude-skills
