Skip to main content
skill CX Codex

finding-saas-company-leads-twitter — Claude Code skill

finding-saas-company-leads-twitter discovers SaaS companies and software startup leads on Twitter using Apify scrapers. Triggers on requests to build targeted lists for B2B sales or integrations.

Apache-2.0 926 installs ★ 1 updated 2026-05-13

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add apidojo-io/apidojo-skills --skill finding-saas-company-leads-twitter -a claude-code
Open on GitHub

What finding-saas-company-leads-twitter does

The skill searches Twitter for software product launches, funding signals, and niche hashtags. It runs a multi-step pipeline: finds active tweets using apidojo/tweet-scraper, pulls unique author handles, and enriches account details via apidojo/twitter-user-scraper.

Profiles pass through a classification filter to remove personal accounts. The skill calculates a lead_score based on SaaS bio keywords, website presence, recent activity within 30 days, and follower volume. Results are grouped into early, growing, and established tiers.

Without an APIFY_TOKEN set in your environment, actor execution will fail. Runs can execute through scripts/run_actor.js, the Apify MCP server, or plain REST calls.

What it helps with

  • compile a list of B2B SaaS companies by vertical from Twitter
  • spot early-stage software launches using product hashtags
  • filter out personal creator profiles from software company accounts
  • calculate lead scores from social engagement and website presence

Example prompts for the agent

  • Find early-stage project management SaaS companies on Twitter and output a CSV lead table
  • Identify active HR tech startups on X that announced funding or product launches recently

How to install finding-saas-company-leads-twitter

1Skills CLI (Vercel)

npx skills add apidojo-io/apidojo-skills --skill finding-saas-company-leads-twitter -a claude-code

2Manually: put the files in place

~/.claude/skills/finding-saas-company-leads-twitter/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/finding-saas-company-leads-twitter/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about finding-saas-company-leads-twitter

How to install finding-saas-company-leads-twitter in Claude Code?

Run npx skills add apidojo-io/apidojo-skills --skill finding-saas-company-leads-twitter -a claude-code. The file is placed at ~/.claude/skills/finding-saas-company-leads-twitter/SKILL.md.

What does finding-saas-company-leads-twitter do?

It coordinates Apify Twitter scrapers to discover software startups, fetch profile data, filter out non-SaaS accounts, and score leads for outreach.

What credentials are required to run this skill?

You must provide an APIFY_TOKEN environment variable. An Apify MCP server is optional but supported for direct tool calling.

Source text

SKILL.md · Apache-2.0
---
name: finding-saas-company-leads-twitter
description: >
  Finds SaaS companies and software startup leads from Twitter/X using apidojo's Twitter scrapers on Apify.
  Triggers when the user asks to: find SaaS companies on Twitter for partnership or sales outreach,
  build a list of software startups by vertical, find B2B SaaS founders or decision-makers on X,
  identify early-stage software companies by their Twitter activity, discover SaaS products in a
  specific niche from Twitter, find software vendors posting about product launches or fundraising,
  or compile a SaaS company contact list from social media.
  Returns company handle, founder name (from bio), follower count, product description, and recent tweets.
  Ideal for SaaS integration partners, investor outreach, B2B sales teams, and startup press.
license: Apache-2.0
metadata:
  author: apidojo
  version: "1.0"
  apify-actors: apidojo/twitter-user-scraper, apidojo/tweet-scraper
---

# Finding SaaS Company Leads on Twitter

Discovers SaaS companies and software product accounts via Twitter signals — product launches, feature announcements, founder activity, and niche-specific hashtags. Twitter is where early-stage B2B SaaS companies are most active before establishing a formal web presence.

## Prerequisites

- `APIFY_TOKEN` environment variable set
- Optional: Apify MCP server installed

## Inputs

| Parameter | Type | Required | Default | Notes |
|-----------|------|----------|---------|-------|
| `startUrls` | array | Optional | `[]` | Twitter profile or tweet URLs |
| `twitterHandles` | array | Optional | `[]` | Twitter usernames (without @) |
| `twitterUserIds` | array | Optional | `[]` | Twitter user IDs |
| `getFollowers` | boolean | Optional | `false` | Extract follower lists |
| `getFollowing` | boolean | Optional | `false` | Extract following lists |
| `getRetweeters` | boolean | Optional | `false` | Extract retweeters of a tweet URL |
| `includeUnavailableUsers` | boolean | Optional | `false` | Include unavailable/suspended users |
| `maxItems` | number | Optional | Unlimited | Maximum users to return |
| `customMapFunction` | string | Optional | — | JavaScript function to transform each output object |

## Workflow

```
Progress:
- [ ] Step 1: Build keyword and hashtag search list for vertical
- [ ] Step 2: Run tweet-scraper to find active companies
- [ ] Step 3: Extract unique company handles
- [ ] Step 4: Enrich via twitter-user-scraper
- [ ] Step 5: Score and classify by stage
- [ ] Step 6: Deliver lead list
```

### Step 1: Search Keywords

Build from vertical. Example for "project management SaaS":
```
Keywords: ["project management software", "PM tool", "#pmtools", "task management SaaS",
           "launched a product", "we built", "try our tool", "project management app"]
```

Standard SaaS signal phrases (always include):
```
["just launched", "we built", "our product", "sign up free", "#buildinpublic",
 "new feature", "we're hiring", "Series A", "product update", "[vertical] tool"]
```

### Step 2: Run tweet-scraper


**Recommended — run_actor.js (handles waiting, output, and file saving automatically):**
```bash
# Quick answer (prints table to chat)
node scripts/run_actor.js \
  --actor "apidojo~twitter-user-scraper" \
  --input '{"param": "value"}'

# Save as CSV
node scripts/run_actor.js \
  --actor "apidojo~twitter-user-scraper" \
  --input '{"param": "value"}' \
  --output YYYY-MM-DD_results.csv --format csv

# Save as JSON
node scripts/run_actor.js \
  --actor "apidojo~twitter-user-scraper" \
  --input '{"param": "value"}' \
  --output YYYY-MM-DD_results.json --format json
```
> `APIFY_TOKEN` must be set in environment or `.env` file.

**If Apify MCP is available:**
```
Tool: apify:run-actor
Actor: "apidojo~tweet-scraper"
Input:
{
  "searchTerms": ["[VERTICAL] software", "[VERTICAL] SaaS", "[VERTICAL] tool launch", "we built [VERTICAL]"],
  "maxItems": 300,
  "tweetLanguage": "en"
}
```

**REST API fallback:**
```bash
curl -X POST   "https://api.apify.com/v2/acts/apidojo~tweet-scraper/runs?token=$APIFY_TOKEN"   -H "Content-Type: application/json"   -d '{
    "searchTerms": ["HR tech SaaS", "HR software launch", "we built HR tool"],
    "maxItems": 300
  }'
```

Collect unique `author.username` values.

### Step 3: Enrich Profiles

**If Apify MCP is available:**
```
Tool: apify:run-actor
Actor: "apidojo~twitter-user-scraper"
Input:
{
  "usernames": ["[username1]", "[username2]", "...up to 100 usernames"]
}
```

**REST API fallback:**
```bash
curl -X POST   "https://api.apify.com/v2/acts/apidojo~twitter-user-scraper/runs?token=$APIFY_TOKEN"   -H "Content-Type: application/json"   -d '{"usernames": ["handle1", "handle2"]}'
```

### Step 4: Filter and Classify

**Is a SaaS company?** Keep if bio contains:
- Product keywords: "software", "SaaS", "platform", "app", "tool", "API", "dashboard"
- Launch signals: "try", "sign up", "free trial", "beta"
- Funding signals: "backed by", "YC", "Techstars", "seed", "Series A/B"

**Stage classification from followerCount:**
```
early: followerCount < 1,000
growing: 1,000–10,000
established: > 10,000
```

**Company score:**
```
lead_score = (is_saas_signal ? 1 : 0) * 0.40
           + (has_website ? 1 : 0) * 0.25
           + (tweeted_in_last_30_days ? 1 : 0) * 0.20
           + min(followerCount / 5000, 1) * 0.15
```

### Step 5: Edge Cases

- **Personal accounts return instead of company**: Filter — prefer accounts where `name` != `username` and bio describes a product; deprioritize accounts with personal pronouns in bio ("I build...")
- **< 20 companies found**: Widen vertical keywords; try hashtags `#buildinpublic`, `#indiehacker`, `#saas` directly
- **Duplicate company** (founder + company account both found): Keep company account; link to founder handle as contact

## Output Format

```
# SaaS Company Leads: [VERTICAL]
Companies found: [N] | Early: [N] | Growing: [N] | Established: [N] | Date: [DATE]

## Growing-Stage Companies (Best Outreach Window)
| Company | Handle | Product | Stage | Followers | Website | Score |
|---------|--------|---------|-------|-----------|---------|-------|
| [name] | @[handle] | [1-line description from bio] | Growing | [N] | [url] | [0.XX] |

## Early-Stage (High Receptivity)
| Company | Handle | Product | Followers | Last Active |
|---------|--------|---------|-----------|------------|

## Established (Formal Sales Cycle)
| Company | Handle | Product | Followers | Website |
|---------|--------|---------|-----------|---------|
```

## Troubleshooting

**Results are mostly personal accounts:** Add `"software" OR "app" OR "platform"` to search and filter aggressively by bio keywords.
**Vertical too broad (returns 500+ companies):** Narrow to a sub-vertical (e.g., "project management" → "async project management for remote teams").
**Companies inactive (last tweet > 60 days):** Flag as potentially dormant; cross-reference product website for active status.

© apidojo · Apache-2.0 · apidojo-io/apidojo-skills

Similar skills

All skills for Browser and scraping →

From the same set100

The whole set →
monitoring-brand-mentions-on-twitter monitoring-brand-mentions-on-twitter collects public brand mentions on Twitter/X via Apify, sorts them by sentiment, and builds an engagement report. CX Codex +1 928installs scraping-instagram-location-posts scraping-instagram-location-posts extracts Instagram posts tagged at venues or geographic places via Apify. Helpful for gathering UGC content and attendee feedback. CX Codex +1 928installs finding-instagram-ugc-creators-for-brands finding-instagram-ugc-creators-for-brands is a Claude Code skill that finds Instagram creators for brand UGC campaigns. It searches niche hashtags and scores profile fit. CX Codex +1 927installs finding-marketing-professionals-on-twitter finding-marketing-professionals-on-twitter finds marketing and growth people on Twitter with Apify scrapers: collects handles from role-related tweets, enriches the profiles, returns a scored shortlist. CX Codex +1 926installs analyzing-competitor-youtube-content-strategy analyzing-competitor-youtube-content-strategy audits a competitor’s YouTube strategy by topic, format, publishing cadence, views, and engagement. Use it to compare two channels or find content gaps. CX Codex +1 926installs scraping-youtube-comments scraping-youtube-comments pulls comments, likes, and reply counts from YouTube videos using Apify. Useful for audience feedback and sentiment analysis. CX Codex +1 925installs finding-data-scientists-on-twitter finding-data-scientists-on-twitter searches Twitter for data scientists and ML engineers who may fit a hiring pipeline, then enriches profiles with skills and work-interest signals. CX Codex +1 925installs monitoring-trending-topics-twitter-by-niche monitoring-trending-topics-twitter-by-niche is a Claude Code skill that tracks trends and conversations in a niche through apidojo's Twitter Search scraper and measures tweet velocity. CX Codex +1 924installs

Project sponsors

Companies that keep this analytics open