Clay Docs logo

Clay Docs

Organization
clay-run
clay-docs

Use when the user asks a Clay product question — how a feature works, whether Clay supports or integrates with something, what plans include, security/compliance, or what's new — and the answer isn't operational guidance another skill owns. Answer from Clay's live public documentation, fetched and cited, never from memory.

Overview

Publisherclay-run
Repositoryagent-plugins
Skill nameclay-docs
Stars
145
Forks
24
Bundled files
Instructions only
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 clay-run on GitHub. Read the source before you install it.

Installation

Install the Clay Docs 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/clay-run/agent-plugins/tree/main/clay/skills/clay-docs
  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/clay-run/agent-plugins.git /tmp/agent-plugins
mkdir -p .claude/skills
cp -r /tmp/agent-plugins/clay/skills/clay-docs .claude/skills/clay-docs
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Clay Docs 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 Clay Docs 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 Clay Docs 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.

Clay product documentation

Clay's public documentation is the source of truth for product questions. Your training data about Clay is stale and incomplete: features ship weekly, integrations are added and renamed, and plans change. Answering a Clay product question from memory risks telling the user something that is no longer true, or denying something that now exists.

The rule: fetch a live doc page, answer from what it says, and cite its URL. If you cannot find the answer in the docs, say so plainly — "I couldn't find this documented". Never fill the gap by guessing.

Not this skill

  • Doing things (run a search, query a table, build a workflow) — use the area skill (searches, tables-cli, workflows, …). This skill answers questions, it does not operate Clay.
  • Live workspace state — credit balances, quotas, plan limits in effect for this workspace: use credits-quotas-plans. This skill covers what plans and pricing are publicly, not what this workspace has.
  • API and CLI reference — endpoints, schemas, flags: the public-api and cli skills point at https://developers.clay.com/llms.txt.
  • Something looks broken — use clay-feedback.

Docs map

Start from the most specific hub that matches the question:

Question is aboutFetch
How a feature works (find, enrich, transform, scraping, AI, export, signals)https://university.clay.com/docs — the product docs hub, organized by topic
Whether Clay integrates with a specific toolhttps://www.clay.com/integrations — the catalog; tool pages hang off it
Plans and pricinghttps://www.clay.com/pricing
Common product questionshttps://www.clay.com/faq
GTM tactics and playbooks built on Clayhttps://www.clay.com/claybooks
Prebuilt table templateshttps://www.clay.com/templates
What a GTM term meanshttps://www.clay.com/glossary
What shipped recentlyhttps://www.clay.com/changelog
Security, compliance, subprocessorshttps://trust.clay.com
Structured learning (courses, lessons, certifications)https://university.clay.com/courses
End-to-end use-case walkthroughshttps://university.clay.com/use-case-templates

Finding the right page

  1. Pick the closest hub from the map and fetch it with your web fetch tool. Hubs link to their leaf pages; follow the link that matches the question and fetch that. One caveat: the University docs hub leans toward per-integration reference pages, while conceptual "how does X work" content (waterfalls, credits, signal types) lives in lessons at university.clay.com/lessons/<slug> — when the hub surfaces only integration pages, go to the sitemap (step 3) instead of digging deeper.
  2. For an integration, fetch the catalog and follow its link for the tool. Tool pages live at /integrations/<category>/<slug> and the category is not guessable, so do not construct URLs by hand — and a 404 on a guessed URL does not mean unsupported.
  3. Find lessons through https://university.clay.com/sitemap.xml. It is large enough that a summarizing fetch tool can silently miss entries, so when you have a shell, grep a raw fetch instead: curl -sL <sitemap-url> | grep -i <keyword>. Skip /fr/ entries — they are French duplicates.
  4. When hub navigation dead-ends or a page you expected is missing, use web search scoped to the docs (site:university.clay.com or site:clay.com) to locate a page, then fetch it. Never answer from a search snippet alone.

If your environment has no web fetch tool, fetch with curl -sL <url> instead. If you cannot fetch at all, say you can't verify against the docs and link the user to the relevant hub URL rather than answering from memory.

Answering

  • Cite the page URL with every answer so the user can read the source.
  • Report what the page says, in its terms. Do not extrapolate a capability the page does not state, and do not present an inference as documented fact.
  • Pricing: state numbers only from a page fetched this session, and say plans change — link https://www.clay.com/pricing as the current source. The page's interactive tier sliders flatten badly into fetched markdown, so present dollar figures as "starts at" rather than exact.
  • University /docs/... pages are product reference; /lessons/... and claybooks are educational content that can lag or generalize. When they disagree, report both with their sources instead of picking one.
  • A capability you cannot find documented is "not documented", not "not supported" — unless a page says it is unsupported. Say what you checked, and don't volunteer a support handoff for a capability gap — the clay skill's escalation rules say when support enters.

Known unsupported

Clay does not offer X (formerly Twitter) data sourcing, scraping, or enrichment — no follower lists, profile data, posts, or mentions. Say so directly — this answer needs no fetch and no citation, and it overrides the fetch-first rule. Do not search the docs for a workaround.

Frequently asked questions

What does the Clay Docs AI skill do?

Use when the user asks a Clay product question — how a feature works, whether Clay supports or integrates with something, what plans include, security/compliance, or what's new — and the answer isn't operational guidance another skill owns. Answer from Clay's live public documentation, fetched and cited, never from memory.

Why use Clay Docs on TypingMind?

Because you install it once and use it with any model. Clay Docs 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 Clay Docs in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/clay-run/agent-plugins/tree/main/clay/skills/clay-docs. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Clay Docs?

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 Clay Docs?

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

Is the Clay Docs AI skill free?

It is published on GitHub by clay-run. Check the repository for licensing terms. 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 👇