Build high-performing OpenClaw agents end-to-end. Use when you want to design a new agent (persona + operating rules) and generate the required OpenClaw workspace files (SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md, optional MEMORY.md + memory/YYYY-MM-DD.md). Also use to iterate on an existing agent’s behavior, guardrails, autonomy model, heartbeat plan, and skill roster.

2026-03-100

docx

DoggyHU/pipipax_claw_backup

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

2026-03-100

evomap

DoggyHU/pipipax_claw_backup

Connect to the EvoMap collaborative evolution marketplace. Publish Gene+Capsule bundles, fetch promoted assets, claim bounty tasks, and earn credits via the GEP-A2A protocol. Use when the user mentions EvoMap, evolution assets, A2A protocol, capsule publishing, or agent marketplace.

2026-03-100

literature-review

DoggyHU/pipipax_claw_backup

文献综述自动化工具。当用户需要批量检索学术文献、提取文献信息、生成文献综述CSV时使用。触发词包括"文献综述"、"检索文献"、"批量提取文献信息"、"帮我查这些文献"等。该skill会自动登录华南农业大学VPN，访问知网等学术数据库，批量检索文献并提取结构化信息。

2026-03-100

literature-review-zotero

DoggyHU/pipipax_claw_backup

文献综述自动化 - Google Scholar + Zotero。使用Google Scholar检索学术文献，通过Zotero管理引用。适用于已有VPN或可直接访问Google的场景。

2026-03-100

puppeteer

DoggyHU/pipipax_claw_backup

Automate Chrome and Chromium with Puppeteer for scraping, testing, screenshots, and browser workflows.

2026-03-100

name	flaresolverr
description	Bypass Cloudflare protection — use when curl/summarize gets 403 or Cloudflare blocks
metadata	{"openclaw":{"emoji":"🛡️","requires":{"bins":["curl","jq"],"env":["FLARESOLVERR_URL"]},"primaryEnv":"FLARESOLVERR_URL"}}

FlareSolverr — Cloudflare Bypass

Use FlareSolverr to bypass Cloudflare protection when direct curl requests fail with 403 or Cloudflare challenge pages.

Setup

Run FlareSolverr (Docker recommended):

docker run -d --name flaresolverr -p 8191:8191 ghcr.io/flaresolverr/flaresolverr:latest

Set the environment variable:

export FLARESOLVERR_URL="http://localhost:8191"

Verify:

curl -s "$FLARESOLVERR_URL/health" | jq '.'
# Expected: {"status":"ok","version":"3.x.x"}

When to Use

Direct curl fails with 403 Forbidden
Cloudflare challenge page appears (JS challenge, captcha, "Checking your browser")
Bot detection blocks automated requests
Rate limiting or anti-scraping measures

Workflow

Try direct curl first (it's faster and simpler)
If blocked: Use FlareSolverr to get cookies/user-agent
Reuse session for subsequent requests (optional, for performance)

Basic Usage

Simple GET Request

curl -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "cmd": "request.get",
    "url": "https://example.com/protected-page",
    "maxTimeout": 60000
  }' | jq '.'

Response Structure

{
  "status": "ok",
  "message": "Challenge solved!",
  "solution": {
    "url": "https://example.com/protected-page",
    "status": 200,
    "headers": {},
    "response": "<html>...</html>",
    "cookies": [
      {
        "name": "cf_clearance",
        "value": "...",
        "domain": ".example.com"
      }
    ],
    "userAgent": "Mozilla/5.0 ..."
  },
  "startTimestamp": 1234567890,
  "endTimestamp": 1234567895,
  "version": "3.3.2"
}

Extract Page Content

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "cmd": "request.get",
    "url": "https://example.com/protected-page"
  }' | jq -r '.solution.response'

Extract Cookies

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "cmd": "request.get",
    "url": "https://example.com"
  }' | jq -r '.solution.cookies[] | "\(.name)=\(.value)"'

Session Management

Sessions allow reusing browser context (cookies, user-agent) for multiple requests, improving performance.

Create Session

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{"cmd": "sessions.create"}' | jq -r '.session'

Use Session for Request

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "cmd": "request.get",
    "url": "https://example.com/page1",
    "session": "SESSION_ID"
  }' | jq -r '.solution.response'

List Active Sessions

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{"cmd": "sessions.list"}' | jq '.sessions'

Destroy Session

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "cmd": "sessions.destroy",
    "session": "SESSION_ID"
  }'

POST Requests

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "cmd": "request.post",
    "url": "https://example.com/api/endpoint",
    "postData": "key1=value1&key2=value2",
    "maxTimeout": 60000
  }' | jq '.'

For JSON POST data:

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "cmd": "request.post",
    "url": "https://example.com/api/endpoint",
    "postData": "{\"key\":\"value\"}",
    "headers": {
      "Content-Type": "application/json"
    }
  }' | jq '.'

Advanced Options

Custom User-Agent

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "cmd": "request.get",
    "url": "https://example.com",
    "userAgent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
  }' | jq '.'

Custom Headers

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "cmd": "request.get",
    "url": "https://example.com",
    "headers": {
      "Accept-Language": "en-US,en;q=0.9",
      "Referer": "https://google.com"
    }
  }' | jq '.'

Proxy Support

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "cmd": "request.get",
    "url": "https://example.com",
    "proxy": {
      "url": "http://proxy.example.com:8080"
    }
  }' | jq '.'

Download Binary Content

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "cmd": "request.get",
    "url": "https://example.com/file.pdf",
    "download": true
  }' | jq -r '.solution.response' | base64 -d > file.pdf

Error Handling

Common Errors

"status": "error": Request failed (check message field)
"status": "timeout": maxTimeout exceeded (increase timeout)
"status": "captcha": Manual captcha required (rare, usually auto-solved)

Check Status

curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{"cmd": "request.get", "url": "https://example.com"}' | \
  jq -r '.status'

Example Workflow

Bypass Cloudflare and Extract Data

# Step 1: Fetch page through FlareSolverr
RESPONSE=$(curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{
    "cmd": "request.get",
    "url": "https://example.com/protected-page"
  }')

# Step 2: Check if successful
STATUS=$(echo "$RESPONSE" | jq -r '.status')
if [ "$STATUS" != "ok" ]; then
  echo "Failed: $(echo "$RESPONSE" | jq -r '.message')"
  exit 1
fi

# Step 3: Extract and parse HTML
echo "$RESPONSE" | jq -r '.solution.response'

Multi-Page Session

# Create session
SESSION=$(curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d '{"cmd": "sessions.create"}' | jq -r '.session')

# Page 1
curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d "{\"cmd\": \"request.get\", \"url\": \"https://example.com/page1\", \"session\": \"$SESSION\"}" | \
  jq -r '.solution.response'

# Page 2 (reuses cookies from page 1)
curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d "{\"cmd\": \"request.get\", \"url\": \"https://example.com/page2\", \"session\": \"$SESSION\"}" | \
  jq -r '.solution.response'

# Cleanup
curl -s -X POST "$FLARESOLVERR_URL/v1" \
  -H "Content-Type: application/json" \
  -d "{\"cmd\": \"sessions.destroy\", \"session\": \"$SESSION\"}"

Health Check

curl -s "$FLARESOLVERR_URL/health" | jq '.'

Performance Tips

Use sessions for multiple requests to same domain (reuses cookies/context)
Increase maxTimeout for slow sites (default: 60000ms)
Fallback to direct curl when possible (FlareSolverr is slower due to browser overhead)
Destroy sessions when done to free resources

Limitations

Slower than direct curl (launches headless browser)
Resource intensive (limit concurrent requests)
May not solve all captchas (most Cloudflare challenges work)
HTML only in response (no client-side JS execution after fetch)

Best Practices

Always try direct curl first
Use sessions for multi-page workflows
Set appropriate maxTimeout (default 60s, increase for slow sites)
Clean up sessions when done
Handle errors gracefully (check status field)
Rate limit your requests (don't overwhelm FlareSolverr or target site)