Menu
MrScraper unblocker and AI scraping tools for blocked pages and structured extraction.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Deploy KERNEL_INTUITION_Cp on any AI architecture with calibrated thresholds. Use when user wants to "activate Cp", "setup creative intuition", "deploy kernel on [AI]", "enable intuition mode", or mentions activating computational intuition on a specific model. Also trigger for "configure Cp for [architecture]" or "calibrate creative thresholds". This skill handles the full activation workflow including architecture profiling, threshold calibration, kernel generation, and monitoring setup.
Three-Layer Thinking Chain Architecture — Personality-Driven Agent Self-Evolution Framework
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.
Delegate coding tasks to Codex, Claude Code, Cursor Agent, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode/Cursor Agent: pty:true required.
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
| name | mrscraper |
| description | MrScraper unblocker and AI scraping tools for blocked pages and structured extraction. |
| metadata | {"openclaw":{"emoji":"🕸️","requires":{"config":["plugins.entries.mrscraper.enabled"]}}} |
| Need | Tool | When |
|---|---|---|
| Blocked or JS-heavy page fetch | web_fetch | MrScraper can power web_fetch when selected as the fetch provider |
| Rendered HTML plus extracted text | mrscraper_fetch_html | Need unblocker controls like geoCode or blockResources |
| AI-powered structured extraction | mrscraper_scrape | Need schema-free extraction from plain-language instructions |
| Reuse an AI scraper | mrscraper_rerun_ai_scraper | Apply an existing AI scraper to a new page or crawl target |
| Batch AI reruns | mrscraper_bulk_rerun_ai_scraper | Reuse one AI scraper across many URLs |
| Reuse a manual scraper | mrscraper_rerun_manual_scraper | Apply a dashboard manual scraper to a new URL |
| Batch manual reruns | mrscraper_bulk_rerun_manual_scraper | Reuse one manual scraper across many URLs |
| Browse prior runs | mrscraper_get_all_results | List stored results with sorting, paging, and filters |
| Inspect one prior run | mrscraper_get_result_by_id | Fetch one detailed result by result ID |
When mrscraper is the selected web_fetch provider, OpenClaw routes normal
web_fetch calls through MrScraper's unblocker.
| Parameter | Description |
|---|---|
url | HTTP or HTTPS URL to fetch |
extractMode | markdown or text |
maxChars | Maximum returned characters |
Use this when you need unblocker-specific controls or want both rendered HTML and extracted text back in one tool result.
| Parameter | Description |
|---|---|
url | HTTP or HTTPS URL to fetch |
extractMode | markdown or text |
maxChars | Maximum returned characters |
timeoutSeconds | Request timeout |
geoCode | Optional country routing code like US or SG |
blockResources | Block images/fonts/resources for faster loads |
Use this when you want MrScraper to create an AI scraper run from natural-language instructions.
| Parameter | Description |
| ----------------- | ---------------------------------------------- | --- | --- |
| url | Target page or site |
| message | What to extract |
| agent | general, listing, or map |
| proxyCountry | Optional ISO country code |
| maxDepth | map agent only |
| maxPages | map agent only |
| limit | map agent only |
| includePatterns | map agent only; regex patterns joined with | | |
| excludePatterns | map agent only; regex patterns joined with | | |
Reuse an existing AI scraper on a new URL.
| Parameter | Description |
| ----------------- | ---------------------------------------------- | --- | --- |
| scraperId | Existing AI scraper ID |
| url | Target page or site |
| maxDepth | map agent only |
| maxPages | map agent only |
| limit | map agent only |
| includePatterns | map agent only; regex patterns joined with | | |
| excludePatterns | map agent only; regex patterns joined with | | |
Reuse an existing AI scraper across multiple URLs.
| Parameter | Description |
|---|---|
scraperId | Existing AI scraper ID |
urls | One or more target URLs |
Reuse an existing manual scraper on a new URL.
| Parameter | Description |
|---|---|
scraperId | Existing manual scraper ID |
url | Target page or site |
Reuse an existing manual scraper across multiple URLs.
| Parameter | Description |
|---|---|
scraperId | Existing manual scraper ID |
urls | One or more target URLs |
Browse previous MrScraper runs with optional paging and filtering.
| Parameter | Description |
|---|---|
sortField | Sort column such as updatedAt |
sortOrder | ASC or DESC |
pageSize | Number of results per page |
page | Page number starting at 1 |
search | Optional text search |
dateRangeColumn | Optional date field to filter by |
startAt | Optional ISO start timestamp |
endAt | Optional ISO end timestamp |
Fetch one detailed result object by result ID.
| Parameter | Description |
|---|---|
resultId | Result ID to fetch |
web_fetch or mrscraper_fetch_html when you mainly need page contents.mrscraper_scrape when you need structured extracted data instead of raw page text.map agent only when the task really needs multi-page crawling.