Agent Native

shape-your-agent

This skill guides users through an interactive session to craft a system prompt that defines an AI agent's personality, tone, boundaries, and refusal policies.

by SanityOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (sanity-io)

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
License
No license stated
Pin
296c8aapinned Oct 9, 2026
Context cost
about 2,100 tokenswhen the skill loads
GitHub stars
7on sanity-io/context
Scripts
None found

What it does

“Interactive session to craft a system prompt for an AI agent powered by the Sanity Context MCP server. Use this skill when users want to define agent personality, set tone/voice, establish boundaries and guardrails, configure refusal behaviors, or control how their agent communicates. Trigger when users mention their agent sounds wrong, needs to refuse certain requests, has the wrong tone, or they want to set communication rules and policies.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill guides users through an interactive session to craft a system prompt that defines an AI agent's personality, tone, boundaries, and refusal policies. It provides a structured conversational workflow with example frameworks and testing methods to create concise, focused prompts that work alongside the Sanity Context MCP server.

When to use it

  • Users want to customize agent personality, tone, or communication style
  • Need to define what the agent should refuse or redirect requests
  • Setting guardrails for specific topics like pricing or competitor mentions
  • Configuring fallback behavior when the agent lacks information

When not to

  • Users cannot modify the agent's system prompt in their setup
  • Addressing content schema or data query patterns (use Instructions field instead)
  • Agent needs GROQ syntax or response formatting guidance (handled by MCP)

Install

No license stated: install from the publisher's repository, and ask the author before you reuse or share it.

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add sanity-io/context --skill shape-your-agent

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install sanity-io/context shape-your-agent@296c8aa5dcb39735eef9e410975615258c4bbf2d

Installs the commit we checked (296c8aa).

Copy by hand

Download the folder at 296c8aa and put it in .claude/skills/shape-your-agent for Claude Code and in .agents/skills/shape-your-agent for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 296c8aa

Claude Code plugin

/plugin install sanity@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "shape-your-agent" by Sanity.

Source, pinned to commit 296c8aa5dcb39735eef9e410975615258c4bbf2d:
https://github.com/sanity-io/context/tree/296c8aa5dcb39735eef9e410975615258c4bbf2d/skills/shape-your-agent

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/shape-your-agent/ for Claude Code and .agents/skills/shape-your-agent/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Its license is restricted or not stated. Show me the license terms from the repository before you copy anything.

Listing and checks: https://www.agentnative.dev/skills/sanity/shape-your-agent

SKILL.md at the pin

The license of this skill does not let us show its files here.

View SKILL.md on GitHub at 296c8aa

Files

1 file, 8.8 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 296c8aa
All 24 skills from Sanity

More from Sanity

  • sanity-live-cache-components

    Integrates Sanity Live with Next.js Cache Components in next-sanity v13+ apps, setting up shared cached data fetching through sanityFetch, live content…

    Claude Code, Codex, Cursor +4 · about 4K tokens · pinned 6 days ago

  • content-experimentation-best-practices

    This skill provides guidance for designing and running content experiments using A/B and multivariate testing.

    Claude Code, Codex, Cursor +4 · about 360 tokens · pinned 6 days ago

  • content-modeling-best-practices

    Guides agents through structured content modeling principles for headless CMSes like Sanity, covering schema design, content reuse strategies, and field…

    Claude Code, Codex, Cursor +4 · about 340 tokens · pinned 6 days ago

  • portable-text-conversion

    Converts HTML and Markdown content into Portable Text blocks for Sanity using markdownToPortableText, htmlToBlocks, or manual construction.

    Claude Code, Codex, Cursor +4 · about 510 tokens · pinned 6 days ago

  • portable-text-serialization

    This skill enables rendering Portable Text content across multiple frameworks and output formats using the @portabletext library family.

    Claude Code, Codex, Cursor +4 · about 940 tokens · pinned 6 days ago

  • sanity-best-practices

    This skill provides best practices for Sanity headless CMS development across schema design, GROQ queries, framework integrations (Next.js, Nuxt, Astro…

    Claude Code, Codex, Cursor +4 · about 1.1K tokens · pinned 6 days ago

All AI and agents skills

Related in AI and agents

  • -21risk-automation

    This skill automates 21risk operations by connecting to the 21risk toolkit through Composio's Rube MCP server.

    by ComposioOfficial publisher

    Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 6 days ago

  • -2chat-automation

    This skill automates 2chat tasks by integrating with Composio's 2chat toolkit through Rube MCP.

    by ComposioOfficial publisher

    Agents not labelled yet · about 680 tokens · pinned 6 days ago

  • ably-automation

    This skill automates Ably messaging platform tasks by connecting to Composio's Ably toolkit through Rube MCP.

    by ComposioOfficial publisher

    Agents not labelled yet · about 680 tokens · pinned 6 days ago

  • abstract-automation

    This skill enables agents to automate Abstract design platform operations through Composio's Abstract toolkit via Rube MCP.

    by ComposioOfficial publisher

    Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 6 days ago

  • abuselpdb-automation

    This skill automates Abuselpdb operations through Composio's toolkit via Rube MCP, enabling the agent to search for IP/domain abuse reports and manage threat…

    by ComposioOfficial publisher

    Agents not labelled yet · about 700 tokens · pinned 6 days ago

  • abyssale-automation

    This skill enables agents to automate Abyssale tasks through Composio's toolkit via Rube MCP.

    by ComposioOfficial publisher

    Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 6 days ago

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use