agentleFS
pencil20388-engpencil20388-eng/adspower-skill/adspower/SKILL.md

adspower

Skill1 starsChanged 6 months agoMITView on GitHub

Automate AdsPower antidetect browser operations through its Local API. This skill handles profile creation, browser control, proxy management, cookie operations, and fingerprint verification. Base URL: http://local.adspower.net:50325 All requests require the Authorization header: Success response: {"code": 0, "msg": "success", "data": {...}} Error response: {"code": -1, "msg": "error description"} Profile creation is always limited to 1 req/sec. Add time.sleep(1.1) between batch opera

  • Reads credentials

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All requests require the Authorization header:

    line 17
  2. Distinctive:

    Always close browsers via API after automation to prevent resource leaks

    line 172
  3. Very specific:

    Use resp["data"]["ws"]["selenium"] for Selenium, resp["data"]["ws"]["puppeteer"] for Playwright

    line 173

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

AdsPower Local API Automation Skill

Automate AdsPower antidetect browser operations through its Local API. This skill handles profile creation, browser control, proxy management, cookie operations, and fingerprint verification.

Prerequisites

  • AdsPower installed and running locally (paid plan with API access)
  • API Key generated (AdsPower → Automation → API → Generate)
  • Python 3.8+ with requests installed

API Basics

Base URL: http://local.adspower.net:50325

All requests require the Authorization header:

Authorization: Bearer YOUR_API_KEY

Success response: {"code": 0, "msg": "success", "data": {...}} Error response: {"code": -1, "msg": "error description"}

Core Operations

1. Check API Status

curl -s -H "Authorization: Bearer $API_KEY" \
  "http://local.adspower.net:50325/api/v1/status"

2. Create a Profile

import requests

resp = requests.post(
    "http://local.adspower.net:50325/api/v1/user/create",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={
        "name": "profile_001",
        "group_id": "0",
        "fingerprint_config": {
            "automatic_timezone": "1",
            "language": ["en-US", "en"],
        },
    },
).json()
profile_id = resp["data"]["id"]

3. Open a Browser Profile

resp = requests.get(
    f"http://local.adspower.net:50325/api/v1/browser/start?user_id={profile_id}",
    headers={"Authorization": f"Bearer {API_KEY}"},
    timeout=30,  # 30s timeout for slow proxies
).json()

# Connection info for automation frameworks:
webdriver_path = resp["data"]["webdriver"]
selenium_address = resp["data"]["ws"]["selenium"]     # For Selenium
puppeteer_ws = resp["data"]["ws"]["puppeteer"]         # For Playwright

4. Close a Browser Profile

requests.get(
    f"http://local.adspower.net:50325/api/v1/browser/stop?user_id={profile_id}",
    headers={"Authorization": f"Bearer {API_KEY}"},
)

5. Connect Selenium

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service

service = Service(executable_path=webdriver_path)
options = Options()
options.add_experimental_option("debuggerAddress", selenium_address)
driver = webdriver.Chrome(service=service, options=options)
driver.get("https://www.browserscan.net/")

6. Connect Playwright

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    browser = p.chromium.connect_over_cdp(puppeteer_ws)
    context = browser.contexts[0]
    page = context.pages[0] if context.pages else context.new_page()
    page.goto("https://www.browserscan.net/")

7. Update Proxy

requests.post(
    "http://local.adspower.net:50325/api/v1/user/update",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={
        "user_id": profile_id,
        "user_proxy_config": {
            "proxy_soft": "other",
            "proxy_type": "http",       # http | https | socks5
            "proxy_host": "1.2.3.4",
            "proxy_port": "8080",       # Must be string
            "proxy_user": "username",
            "proxy_password": "password",
        },
    },
).json()

8. Query Profiles

resp = requests.get(
    "http://local.adspower.net:50325/api/v1/user/list",
    headers={"Authorization": f"Bearer {API_KEY}"},
    params={"page": 1, "page_size": 100, "group_name": "My Campaign"},
).json()
profiles = resp["data"]["list"]

9. Create a Group

resp = requests.post(
    "http://local.adspower.net:50325/api/v1/group/create",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={"group_name": "My Campaign"},
).json()
group_id = resp["data"]["group_id"]

Rate Limits

Profile countMax frequency
0–2002 req/sec
200–50005 req/sec
> 500010 req/sec

Profile creation is always limited to 1 req/sec. Add time.sleep(1.1) between batch operations.

Common Errors

ErrorCauseFix
Connection refusedAdsPower not runningStart AdsPower, check API status
Invalid API keyWrong or expired keyRegenerate in Automation → API
Error 100044Browser start timeoutCheck proxy, clear cache, increase timeout
Error 100001Browser failed to startRepair profile, update AdsPower
Too many requestsRate limit exceededAdd sleep between API calls
Profile not foundWrong user_idQuery /api/v1/user/list to get correct IDs

Important Notes

  • proxy_port must be a string, not an integer
  • user_id is the internal ID from creation, not the profile name or UI number
  • The API port (default 50325) can change between sessions — verify in AdsPower settings
  • Always close browsers via API after automation to prevent resource leaks
  • Use resp["data"]["ws"]["selenium"] for Selenium, resp["data"]["ws"]["puppeteer"] for Playwright

    Bundled Scripts

Profile Report Generator

Generate a CSV audit report of all profiles:

python3 ${CLAUDE_SKILL_DIR}/scripts/profile_report.py
python3 ${CLAUDE_SKILL_DIR}/scripts/profile_report.py --group "My Campaign"

Output includes: profile_id, name, group, proxy status, cookie status, creation time, last open time. Use this when the user asks to audit profiles, check proxy coverage, or generate a profile summary.

Resources

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.