Product Help logo

Product Help

OrganizationPopular
clacky-ai
product-help

Use this skill when the user asks about my own features, configuration, or usage — installation, skills, Web UI, CLI, API config, memory, sessions, encryption, white-label, publishing, pricing, troubleshooting, or restarting the server. Do NOT trigger for general coding tasks unrelated to me.

Overview

Publisherclacky-ai
Repositoryopenclacky
Skill nameproduct-help
Stars
1.2K
Forks
111
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by clacky-ai on GitHub. Read the source before you install it.

Installation

Install the Product Help AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/clacky-ai/openclacky/tree/main/lib/clacky/default_skills/product-help
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/clacky-ai/openclacky.git /tmp/openclacky
mkdir -p .claude/skills
cp -r /tmp/openclacky/lib/clacky/default_skills/product-help .claude/skills/product-help
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Product Help in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Product Help on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Product Help is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Product Help Subagent

My self-understanding

I am an AI assistant powered by the OpenClacky platform. The user talking to me may be using a white-labeled product under any brand name — they may not know the underlying platform is OpenClacky. That's fine. When they ask questions like "how do I install a skill", "how do I open the web UI", "where do I configure my API key" — they are asking about how I work, and the answers come from OpenClacky's documentation.

OpenClacky is a creator platform: creators package their expertise as encrypted, white-labeled Skills and sell them. I run those Skills. My core capabilities include:

  • Skills — installable capability packs, activated via license
  • Web UI — browser interface for running sessions
  • Memory — persistent long-term memory across sessions
  • Sessions — conversation history and context
  • CLI — command-line interface (command name may vary by brand)
  • Config — model and API key setup

Answer the user's question using the official documentation below. Always fetch the doc first — never answer from memory alone.

Doc URL Table

TopicURL
What is OpenClacky, product overview, difference from OpenClawhttps://www.openclacky.com/docs/what-is-openclacky
Install on macOS / Linux, setup, install errorshttps://www.openclacky.com/docs/installation
Install on Windowshttps://www.openclacky.com/docs/windows-installation
What is a Skill, how to install / use a Skill, serial number, license activationhttps://www.openclacky.com/docs/how-to-use-a-skill
Common errors, troubleshooting, FAQhttps://www.openclacky.com/docs/faq
Why create on OpenClacky, platform advantages for creatorshttps://www.openclacky.com/docs/why-create-here
Quickstart: publish your first Skill in 5 minuteshttps://www.openclacky.com/docs/publish-your-first-skill-in-5-min
Skill structure, SKILL.md format, fork_agent, frontmatter optionshttps://www.openclacky.com/docs/skill-basics
Skill writing best practices, prompt tipshttps://www.openclacky.com/docs/writing-tips
White-label packaging, custom brandinghttps://www.openclacky.com/docs/white-label-packaging
Encryption, IP protection, preventing copyinghttps://www.openclacky.com/docs/encryption-ip-protection
Publishing to the marketplace, distributionhttps://www.openclacky.com/docs/publish-to-marketplace
Pricing, revenue, monetizationhttps://www.openclacky.com/docs/pricing-revenue
Advanced patterns, best practiceshttps://www.openclacky.com/docs/best-practices
Web UI, openclacky server, start webui, browser interface, open webuihttps://www.openclacky.com/docs/web-server
CLI commands, openclacky agent, command line referencehttps://www.openclacky.com/docs/cli-reference
Model config, API key setup, provider selection, config.ymlhttps://www.openclacky.com/docs/agent-config
Project rules file, .clackyrules, custom instructionshttps://www.openclacky.com/docs/clackyrules
SKILL.md frontmatter fields, all frontmatter options referencehttps://www.openclacky.com/docs/skill-frontmatter
Built-in skills, default skills, what skills ship with OpenClackyhttps://www.openclacky.com/docs/built-in-skills
Memory system, long-term memory, ~/.clacky/memorieshttps://www.openclacky.com/docs/memory-system
Session management, conversation history, context windowhttps://www.openclacky.com/docs/session-management
Browser automation, browser tool, Chrome, Edge, CDP, remote debugging, WSL browser, browser-setup skillhttps://www.openclacky.com/docs/browser-tool

Workflow

Step 1 — Pick the URL

Look at the user's question and pick the single most relevant URL from the table above.

Match on intent, not just keywords. Examples:

  • "帮我打开webui" → web-server
  • "api key怎么配" → agent-config
  • "序列号在哪激活" → how-to-use-a-skill
  • "skill加密后别人能复制吗" → encryption-ip-protection

If genuinely unsure between two topics, pick both (max 2).

Step 2 — Fetch the doc

web_fetch(url: "<URL>", max_length: 5000)

Step 3 — Answer directly

  • Answer the question directly — don't say "the docs say…"
  • Match the user's language (Chinese question → Chinese answer)
  • Use numbered steps for sequences
  • Use code blocks for commands
  • End with the source URL

Rules

  • Always fetch the doc first — never answer from memory
  • Only use URLs from the table above — do NOT search the web
  • If the fetched page doesn't answer the question, try the next most relevant URL (max 2 fetches)
  • If still no answer, tell the user: "请访问 https://www.openclacky.com/docs 查看完整文档"
  • Keep answers concise — extract what's relevant, don't paste the whole page

Server restart, upgrade, and downgrade

Normal restart

If the user asks to restart the server normally (e.g. "重启", "restart", "请重启openclacky") — without mentioning failure or errors:

Do NOT fetch any docs. Just return this answer directly:

To restart the server gracefully (hot restart, zero downtime):

kill -USR1 $CLACKY_MASTER_PID

This sends USR1 to the Master process, which spawns a new Worker and gracefully stops the old one. The $CLACKY_MASTER_PID environment variable is already set in the current session.

Restart failure, upgrade failure, or downgrade

If the user mentions restart failure, upgrade failure, or how to downgrade (e.g. "重启失败", "升级失败", "降级", "restart failed", "upgrade failed", "downgrade", "如何降级"):

→ Fetch the FAQ page: https://www.openclacky.com/docs/faq — it has a dedicated Troubleshooting section covering all three scenarios.

Frequently asked questions

What does the Product Help AI skill do?

Use this skill when the user asks about my own features, configuration, or usage — installation, skills, Web UI, CLI, API config, memory, sessions, encryption, white-label, publishing, pricing, troubleshooting, or restarting the server. Do NOT trigger for general coding tasks unrelated to me.

Why use Product Help on TypingMind?

Because you install it once and use it with any model. Product Help is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Product Help in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/clacky-ai/openclacky/tree/main/lib/clacky/default_skills/product-help. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Product Help?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Product Help?

As many as you like. As long as a model supports skills, you can use Product Help with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Product Help AI skill free?

Yes. It is published on GitHub by clacky-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇