openclaw-specialist

Answers OpenClaw questions and enforces project file placement and naming conventions.

Updated Mar 30, 2026
One-click install
npx skills add https://github.com/guizonatto/myopen-claw --skill openclaw-specialist-guizonatto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openclaw-specialist
Source: https://github.com/guizonatto/myopen-claw/tree/main/.claude/skills/openclaw-specialist
Command: npx skills add https://github.com/guizonatto/myopen-claw --skill openclaw-specialist-guizonatto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Developers working on this OpenClaw-based assistant project need accurate answers about the OpenClaw gateway (channels, tools, automation, security, nodes, configuration) and consistent rules for where new Python files belong, avoiding misplaced business logic and inconsistent naming. ## Core Features & Use Cases - OpenClaw Documentation Reference: Directs the assistant to read docs/openclaw_reference.md for any OpenClaw question, with instructions to refresh it by re-crawling https://docs.openclaw.ai/. - File Placement Rules: Enforces a strict architecture — data collection in skills/, external integrations in tools/, orchestration in pipes/, scheduling in crons/, event triggers in triggers/, conditional logic in agents/, and shared utilities in openclaw/. - Naming & Security Conventions: Mandates naming patterns like {dominio}_{acao}.py and {canal}_notify.py, forbids hardcoded credentials, and requires new environment variables to be added to .env.example. - Use Case: When asked to create a Telegram notification script, the assistant places it in tools/telegram_notify.py, reads credentials via os.environ.get(), and updates .env.example. ## Quick Start Ask where a new Python script for scraping LinkedIn and sending results to Telegram should be created in this project.

Frequently Asked Questions about openclaw-specialist

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I answer questions about OpenClaw configuration and channels?

Read the docs/openclaw_reference.md file, which contains the full crawled OpenClaw documentation covering architecture, channels, tools, automation, security, nodes, and configuration. To refresh it, re-crawl https://docs.openclaw.ai/ and overwrite the file.

Where should I create a new Python file in an OpenClaw project?

Placement depends on purpose: data collection goes in skills/, external integrations in tools/, orchestration in pipes/, scheduled jobs in crons/, event-driven activation in triggers/, conditional logic in agents/, and shared utilities in openclaw/.

What naming convention should OpenClaw project scripts follow?

Each directory has a required pattern: skills use {dominio}_{acao}.py, tools use {canal}_notify.py or {canal}_scraper.py, pipes use {processo}_pipe.py, crons use {processo}_cron.py, triggers use {canal}_trigger.py, and agents use {nome}_agent.py.

Can I hardcode API tokens in OpenClaw project scripts?

No, hardcoding credentials, tokens, or IDs is forbidden. Always read them via os.environ.get(), and any new environment variable must also be added to the .env.example file.

Why should orchestration logic not live in crons or triggers?

Crons handle only time-based scheduling and triggers handle only external event activation. Putting orchestration there mixes responsibilities; multi-step coordination belongs in pipes/ or agents/ for maintainability.