Cold Email Outreach
gooseworks-ai/goose-skills
End-to-end cold email outreach orchestration. An agent skill from gooseworks-ai/goose-skills.
Find lookalike companies via DiscoLike's 65M+ business domain database.
Install Disco Like
$ npx skills add growthenginenowoslawski/coldoutboundskills --skill disco-like -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills disco-like --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/disco-like .claude/skills/disco-like && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "disco-like" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/disco-like into .claude/skills/disco-like/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "disco-like", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/disco-likeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add growthenginenowoslawski/coldoutboundskills --skill disco-like -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills disco-like --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/disco-like .agents/skills/disco-like && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "disco-like" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/disco-like into .agents/skills/disco-like/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "disco-like", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add growthenginenowoslawski/coldoutboundskills --skill disco-like -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills disco-like --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/disco-like .cursor/skills/disco-like && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "disco-like" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/disco-like into .cursor/skills/disco-like/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "disco-like", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/growthenginenowoslawski/coldoutboundskills.git --path skills/disco-like--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add growthenginenowoslawski/coldoutboundskills --skill disco-like -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills disco-like --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/disco-like .gemini/skills/disco-like && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "disco-like" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/disco-like into .gemini/skills/disco-like/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "disco-like", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install growthenginenowoslawski/coldoutboundskills disco-likeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add growthenginenowoslawski/coldoutboundskills --skill disco-like -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/disco-like .github/skills/disco-like && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "disco-like" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/disco-like into .github/skills/disco-like/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "disco-like", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add growthenginenowoslawski/coldoutboundskills --skill disco-like -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install growthenginenowoslawski/coldoutboundskills disco-like --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/growthenginenowoslawski/coldoutboundskills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/disco-like .opencode/skills/disco-like && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "disco-like" agent skill from https://github.com/growthenginenowoslawski/coldoutboundskills/tree/main/skills/disco-like into .opencode/skills/disco-like/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "disco-like", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
disco-like- GitHub stars
- 753
- Token cost
- ~1.7k tokens
- SKILL.md length
- 745 words
- Files
- 2 (incl. scripts)
- Skills in repo
- 49
- Repo updated
- First seen
- Licence
- MIT
At a glance
Find lookalike companies via DiscoLike's 65M+ business domain database.
- Works in 3 steps: Evaluate which of the 50 are actually… → Refine your ICP description / negation… → Only then scale to 5,000+
- You already know 3-10 reference companies and want hundreds more that look like them
- SKILL.md covers When to use, When NOT to use, Two search modes and Negation (exclude existing…, plus 10 more sections
- Runs TypeScript scripts from its folder; calls npx; reaches api.discolike.com and clay.com; needs DISCOLIKE_API_KEY
What it does
Disco Like is an agent skill from growthenginenowoslawski/coldoutboundskills. Find lookalike companies via DiscoLike's 65M+ business domain database. Search by seed domains ("find companies like clay.com and apollo.io") or natural-language ICP text ("B2B cold email outreach"). Supports negation domains (exclude competitors/existing customers) and country filtering. Use when you already know 3-10 reference companies and want hundreds more that look like them. Outputs CSV ready for /blitz-list-builder or the email waterfall.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/discover.ts`).
It sits in Sales & Support, covering Cold outreach, GraphQL and CSV and tabular files. The repository describes itself as: Open-source Claude Code skills for cold email and outbound sales. Grade campaigns, export Prospeo searches, scrape Google Maps — all from Claude Code. The licence is MIT.
When your agent uses it
- You already know 3-10 reference companies and want hundreds more that look like them
- Tasks that involve Cold outreach
- Tasks that involve GraphQL
Example prompts
- “s 65M+ business domain database. Search by seed domains (”
- “) or natural-language ICP text (”
- “/disco-like”
Requirements
- Node.js
- A credential in DISCOLIKE_API_KEY
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Evaluate which of the 50 are actually good ICP fits
- Refine your ICP description / negation list based on what DiscoLike returned
- Only then scale to 5,000+
What it can do on your machine
Read from SKILL.md and the folder at commit 25c5d85. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (TypeScript), which the agent can run.
Shell commands in SKILL.md call:
npx
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
api.discolike.comclay.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
DISCOLIKE_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Disco Like loads about 1.7k tokens when it runs. Until then it costs about 115 tokens; SKILL.md has 745 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from growthenginenowoslawski/coldoutboundskills at commit 25c5d85, republished under its MIT licence (© growthenginenowoslawski). 745 words, ~1,707 tokens.
Download SKILL.mdSave it as
.claude/skills/disco-like/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- disco-like
- description
- Find lookalike companies via DiscoLike's 65M+ business domain database. Search by seed domains ("find companies like clay.com and apollo.io") or natural-language ICP text ("B2B cold email outreach"). Supports negation domains (exclude competitors/existing customers) and country filtering. Use when you already know 3-10 reference companies and want hundreds more that look like them. Outputs CSV ready for /blitz-list-builder or the email waterfall.
Disco-Like
Lookalike company discovery. Give it 3-10 seed domains you know are a good fit; it returns hundreds of similar companies by domain, industry, and business characteristics. Useful for expanding from a small known-good list to a much bigger TAM without manual research.
When to use
- You have 3-10 customer domains you love, want "more like these"
- You want to expand a small client list into a full TAM
- You have an ICP description but don't want to manually build Prospeo filters
- Competitive / adjacent-market expansion
When NOT to use
- You need PEOPLE, not companies (use Prospeo or Blitz after this)
- Your ICP is extremely narrow or nascent (<5 seed examples exist)
- Budget is tight — DiscoLike charges per call + per record; see cost section
Two search modes
Mode A — Seed domains (most common)
npx tsx scripts/discover.ts --domains "clay.com,apollo.io,outreach.io" --country US --limit 500 --out lookalikes.csvDiscoLike finds companies with similar characteristics (industry mix, employee count range, business type, tech stack) to your seeds.
Mode B — Natural-language ICP
npx tsx scripts/discover.ts --text "B2B SaaS companies selling outbound sales software to RevOps teams" --country US --out lookalikes.csvUses DiscoLike's text matching. Less precise than seeds, but useful when you don't have named comparables.
Hybrid mode
npx tsx scripts/discover.ts --domains "clay.com" --text "outbound automation" --country US --out lookalikes.csvCombines both — starts from seeds, expands via text semantics.
Negation (exclude existing customers / competitors)
npx tsx scripts/discover.ts \
--domains "clay.com,apollo.io" \
--negation-domains "yourcompany.com,yourbigcustomer.com" \
--country US \
--out lookalikes.csvAlways include your own domain + existing customers + known-unfit competitors. Saves enrichment cost downstream.
Inputs
DISCOLIKE_API_KEY(env) — from DiscoLike dashboard- Either
--domainsor--text(at least one required) - Optional:
--negation-domains,--country,--limit,--max-companies
Outputs
CSV with columns: domain, company_name, industry, headcount_range, headcount, location_country, location_state, location_city, linkedin_url, description, source
All rows have source=discolike so you can mix with other list-builder outputs without collisions.
Cost
- $0.10 per API call + $2.00 per 1,000 records returned
- Default page size: 100 per call
- A 500-company discovery = ~5 calls + 500 records ≈ $1.50
- A 10,000-company discovery ≈ $10 + $20 = $30
Compare to Prospeo, which charges per export. DiscoLike is typically cheaper per company-discovered but more expensive per enriched contact (DiscoLike gives companies, not people).
Required step: Qualify with /icp-prompt-builder
This is a required step. Do not skip it.
Before pulling 5,000 companies, run DiscoLike on a small sample (50-100), then invoke /icp-prompt-builder:
- Evaluate which of the 50 are actually good ICP fits
- Refine your ICP description / negation list based on what DiscoLike returned
- Only then scale to 5,000+
Why required: DiscoLike lookalike results are only as good as your seed domains. If 80% of the first 50 are wrong, you need to change seeds, not pay to pull more. At $0.10/call + $2/1K records, a wrong-seeded 10K pull costs $20-$30 in DiscoLike fees AND cascades into wasted email-finder fees downstream. Qualifying the first 50 catches bad seeds before they become expensive.
Show full SKILL.md (325 more words)Show less
Recommended flow
/icp-onboarding→ nail down seed companies (your best 5 customers)/disco-like --domains="seed1,seed2,..." --limit=100 --out=sample.csv→ sample run/icp-prompt-builder→ score the sample, tune ICP prompt- If sample quality is high, scale:
/disco-like ... --limit=5000 --out=full.csv /blitz-list-builder --domains-file=full.csv→ find decision-makers at each/list-builder(Phase 5, emails) → fill in emails- Upload to Smartlead
API details (reference)
Base URL: https://api.discolike.com/v1
Auth: x-discolike-key header
Endpoints:
| Method | Path | Purpose |
|---|---|---|
| GET | /count?domains=X&text=Y | Total matching companies (before paying to pull) |
| GET | /discover?domains=X&text=Y&country=Z&limit=100&offset=0 | Paginated lookalike results |
| GET | /bizdata?domain=X | Detailed data for a single domain |
Data returned per company:
domain,name,descriptionindustry_groups(weighted dict — script takes top industry)employees(range string like "51-200")address(country, state, city)social_urls(script extracts LinkedIn company URL)
Rate limit: Conservative — script throttles at 5 concurrent, 10 req/sec. No 429s observed on normal runs.
Common gotchas
- Seed domains must be clean bare domains.
clay.comworks,https://clay.com/doesn't. - Text mode is fuzzier than you think. "Outbound sales" returns SaaS, agencies, consultancies — broad. Tighten with seeds.
- No people data. DiscoLike is company-level. Always chain with Blitz or Prospeo for contacts.
- Non-US coverage varies. US has deepest data. EU/APAC coverage is thinner; count may be misleading.
- Check the count FIRST. Before paying for 10,000 records, run
/countto confirm the universe actually has 10,000. Many narrow ICPs top out at 500-2000.
Scripts
scripts/discover.ts— main search + CSV output
What to do next
Run /icp-prompt-builder on your 50-company sample (required step above). Then either:
/blitz-list-builderto find owner contacts at each filtered domain, OR/list-quality-scorecarddirectly if this is companies-only and you'll enrich another way
Or wait: if the 50-sample ICP fit was poor (<40% matches), don't scale. Change your seed domains and re-run with better inputs.
Related skills
/icp-onboarding— defines the seed domains you'll use/icp-prompt-builder— quality-check the first 50 results before scaling/blitz-list-builder— chain to find contacts at each discovered company/list-builder(Phase 5, emails) — fill missing emails after Blitz/cold-email-starter-kit→06-list-building-prospeo.mdfor broader list-building patterns
© growthenginenowoslawski, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (scripts) in skills/disco-like of growthenginenowoslawski/coldoutboundskills.
- SKILL.md
- scripts/discover.ts
Open the folder on GitHubat commit 25c5d85
Compare with similar skills
Disco Like next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Disco Like this skillgrowthenginenowoslawski/coldoutboundskills | 753 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Cold Email Outreachgooseworks-ai/goose-skills | 1.2k | 1 repos | ~3.4k | Automated safety check: Notes | MIT | |
| Cold Email Local Businessgmapsscraper/google-maps-agent-skills | 132 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Cold Email VerifierVarnan-Tech/opendirectory | 674 | — | ~810 | Automated safety check: Pass | MIT | |
| Lead Genericrisco/rsc-harness | 180 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Gx Apollo Expertcriptogus/agent-evolve-network | 288 | — | ~736 | Automated safety check: Pass | MIT |
Similar skills
Cold Email Local Business
gmapsscraper/google-maps-agent-skills
Write hyper-personalized cold emails to local businesses using their Google Maps data (CSV).
Cold Email Verifier
Varnan-Tech/opendirectory
A skill your agent uses when the user wants to verify cold emails, enrich a lead list, or autonomously guess email addresses from a CSV using ValidEmail.co or the open-source Reacher engine.
Lead Gen
ericrisco/rsc-harness
A skill your agent uses when building and qualifying a prospect list before anyone reaches out — a falsifiable ICP, named accounts/contacts from Apollo/ZoomInfo/Clay, deduped against the CRM, tiered…
Gx Apollo Expert
criptogus/agent-evolve-network
Build ICP search filters, sequences, and outbound playbooks in Apollo.io.
- Official
Apify Buying Signal Detection
apify/awesome-skills
Set up a recurring buying-signal detection pipeline that finds companies showing buying intent across three signal types — job postings (hiring for the persona), fundraising events (recent raises)…
More from growthenginenowoslawski/coldoutboundskills
All 49 skills in this repoEmail Deliverability Audit
growthenginenowoslawski/coldoutboundskills
Diagnostic audit for a running cold email program. An agent skill from growthenginenowoslawski/coldoutboundskills.
Icp Onboarding
growthenginenowoslawski/coldoutboundskills
Conversational intake for cold email campaigns. An agent skill from growthenginenowoslawski/coldoutboundskills.
List Builder
growthenginenowoslawski/coldoutboundskills
META skill — build the largest possible qualified lead list for any request, end to end.
Auto Research Public
growthenginenowoslawski/coldoutboundskills
Autonomous cold email campaign launcher. An agent skill from growthenginenowoslawski/coldoutboundskills.
Blitz List Builder
growthenginenowoslawski/coldoutboundskills
Use the Blitz API to find decision-makers at specific companies when you already have a list of company domains.
Deliverability Test Public
growthenginenowoslawski/coldoutboundskills
Compare reply rates, bounce rates, and positive reply rates broken down by inbox type (SMTP / Gmail / Outlook) for a Smartlead account.
Related
Categories
Questions about Disco Like
What does Disco Like do?
Find lookalike companies via DiscoLike's 65M+ business domain database. Disco Like is an agent skill from growthenginenowoslawski/coldoutboundskills. Find lookalike companies via DiscoLike's 65M+ business domain database.
When should I use Disco Like?
Disco Like fits situations like: you already know 3-10 reference companies and want hundreds more that look like them; tasks that involve Cold outreach; tasks that involve GraphQL.
How do I install Disco Like in Claude Code?
Run `npx skills add growthenginenowoslawski/coldoutboundskills --skill disco-like -a claude-code`. Or copy the skill folder (skills/disco-like in growthenginenowoslawski/coldoutboundskills) into .claude/skills/disco-like in your project. Claude Code loads it when a task matches its description.
How do I install Disco Like in Codex?
Run `npx skills add growthenginenowoslawski/coldoutboundskills --skill disco-like -a codex`. Or copy the skill folder (skills/disco-like in growthenginenowoslawski/coldoutboundskills) into .agents/skills/disco-like in your project. Codex loads it when a task matches its description.
Can I use Disco Like in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add growthenginenowoslawski/coldoutboundskills --skill disco-like -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/disco-like, .gemini/skills/disco-like, .github/skills/disco-like and .opencode/skills/disco-like in your project.
What does Disco Like need to run?
Going by SKILL.md and its folder, Disco Like needs TypeScript for the scripts in its folder, the command-line tools its instructions call (npx) and credentials named DISCOLIKE_API_KEY. Our summary lists: Node.js; A credential in DISCOLIKE_API_KEY.
Does Disco Like access the network?
SKILL.md names 2 domains. In commands or code: api.discolike.com and clay.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Is Disco Like safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Disco Like use?
Disco Like is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Disco Like use?
About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Disco Like?
Skills that share tags, products or a category with Disco Like: Cold Email Outreach (gooseworks-ai/goose-skills, 1.2k stars), Cold Email Local Business (gmapsscraper/google-maps-agent-skills, 132 stars), Cold Email Verifier (Varnan-Tech/opendirectory, 674 stars) and Lead Gen (ericrisco/rsc-harness, 180 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Disco Like?
growthenginenowoslawski (a GitHub user) maintains it in growthenginenowoslawski/coldoutboundskills, which has 753 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 5, 2026.
Source: growthenginenowoslawski/coldoutboundskills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.