使用方法
- 复制安装命令，在自己的智能体环境安装前先检查源码包。
- 从原始文档核对所需工具、凭据和支持的宿主。
- 说明输入材料与期望交付物，并对照来源检查输出。
npx skills add https://github.com/apidojo-io/apidojo-skills --skill finding-data-scientists-on-twitter开始前需了解
- 安装不包含模型订阅、API 额度或访问文件的权限。
- 仓库星数和安装量反映活跃情况，不等于独立质量或安全测试。
按源仓库内容呈现，保留标题、案例、代码、表格、链接以及原文引用的演示图片。
Finding Data Scientists And Ml Engineers on Twitter
Discovers data scientists and ML engineers on Twitter via skill keywords, portfolio/project signals, and open-to-work indicators. Twitter surfaces professionals who actively discuss their craft — a strong passive candidate signal.
Prerequisites
APIFY_TOKENenvironment 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: Search for role-specific tweets
- [ ] Step 2: Collect unique handles
- [ ] Step 3: Enrich profiles
- [ ] Step 4: Score candidate fit
- [ ] Step 5: Deliver candidate listStep 1: Search Queries
Recommended — run_actor.js (handles waiting, output, and file saving automatically):
# 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 jsonAPIFY_TOKENmust be set in environment or.envfile.
If Apify MCP is available:
Tool: apify:run-actor
Actor: "apidojo~tweet-scraper"
Input:
{
"searchTerms": ["data scientist", "ML engineer", "LLM engineer", "machine learning open to work"],
"maxItems": 300,
"tweetLanguage": "en"
}REST API fallback:
curl -X POST \
"https://api.apify.com/v2/acts/apidojo~tweet-scraper/runs?token=$APIFY_TOKEN" \
-H "Content-Type: application/json" \
-d '{"searchTerms": ["data scientist", "ML engineer", "LLM engineer", "machine learning open to work"], "maxItems": 300}'Collect unique author.username from results.
Step 2: Enrich Profiles
If Apify MCP is available:
Tool: apify:run-actor
Actor: "apidojo~twitter-user-scraper"
Input: {"usernames": ["[username1]", "[username2]", "..."]}REST API fallback:
curl -X POST \
"https://api.apify.com/v2/acts/apidojo~twitter-user-scraper/runs?token=$APIFY_TOKEN" \
-H "Content-Type: application/json" \
-d '{"usernames": ["handle1", "handle2"]}'Step 3: Filter and Score
Skill confirmation: bio contains keywords: "data science", "machine learning", "ML", "NLP", "LLM", "AI", "neural network", "PyTorch", "TensorFlow", "scikit-learn"
research_signal = bio contains 'PhD', 'researcher', or links to papers/Google Scholar
Candidate score:
candidate_score = (skill_confirmed ? 1 : 0) * 0.35
+ (open_to_work_signal ? 1 : 0) * 0.30
+ (followerCount in 200..20000 ? 1 : 0.6) * 0.20
+ (tweeted_in_last_30_days ? 1 : 0) * 0.15Activity: active (< 30 days) | passive (30–90 days) | dormant (> 90 days)
Step 4: Edge Cases
- Company/brand accounts in results: Filter where
followerCount > 50KAND bio contains no personal pronouns; these are likely brand accounts - < 20 candidates found: Broaden skill term; remove location or seniority filter; try adjacent skills
- Bot detection: Flag
followerCount / followingCount < 0.05ANDtweetsCount < 20as potential bot - Location not matching: Bio location is free text — use fuzzy match; accept partial city/country names
Output Format
# Data Scientists And Ml Engineers Candidates: [ML_SPECIALTY]
Profiles found: [N] | Open-to-work: [N] | Active: [N] | Date: [DATE]
## Priority: Open-to-Work Candidates
| Name | @Handle | Specialty | Location | Followers | Last Active | Score |
|------|---------|----------|---------|-----------|------------|-------|
## Passive Candidates
| Name | @Handle | Specialty | Location | Followers | Score |
|------|---------|----------|---------|-----------|-------|
## Bio Highlights (Top 5)
1. @[handle]: "[bio excerpt]"Troubleshooting
All results are agencies/companies not individuals: Add personal pronouns filter or search "I am a [role]", "I do [skill]". Role too generic returns too many results: Add location OR seniority qualifier. No open-to-work signals: Most candidates don't signal publicly — treat passive candidates as warm leads with personalized outreach referencing their recent content.
