Agent Instructions logo

Agent Instructions

OrganizationPopular
EpicenterHQ
agent-instructions

Write and maintain repository guidance across AGENTS.md, CLAUDE.md, and .agents/skills. Use when creating or editing skills, deciding where instructions belong, or diagnosing instruction sprawl and skill selection. Do not use merely because another skill is being executed.

Overview

PublisherEpicenterHQ
Repositoryepicenter
Skill nameagent-instructions
Stars
4.8K
Forks
386
Bundled files
17
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.

  • 17 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by EpicenterHQ on GitHub. Read the source before you install it.

Installation

Install the Agent Instructions 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/EpicenterHQ/epicenter/tree/main/.agents/skills/agent-instructions
  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/EpicenterHQ/epicenter.git /tmp/epicenter
mkdir -p .claude/skills
cp -r /tmp/epicenter/.agents/skills/agent-instructions .claude/skills/agent-instructions
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Agent Instructions 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 Agent Instructions 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 Agent Instructions 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.

Agent Instructions

Preserve useful judgment in guidance a future agent can find and apply. A skill earns its place through knowledge, preferences, or recurring failures the agent would otherwise miss. More instructions are not evidence of progress.

Find the instruction's owner

Use dialectic when the purpose or desired behavior is unsettled: articulate the proposed model alongside a sample of the behavior it would produce. Use reactions to both to develop the instructions. Settled edits do not require another discovery conversation.

Ground the guidance in actual work, source material, or the user's corrections. Extract the judgment behind an accepted interaction, not its topic, layout, or turn count. Remove instructions that push against that judgment before adding compensating rules. An example is evidence for a principle, not a template for every future response.

Update the existing owner when the intent is the same. Create a separate skill when it offers a coherent capability someone would reach for independently. Merge or delete guidance whose distinction creates more work than it saves; legitimate composition does not require every phrase to have exactly one owner.

Keep cross-task constraints in AGENTS.md, specialized judgment in skills, and architecture or decision history in the relevant README or ADR. References carry conditional detail; scripts carry repeated fragile mechanics. One-off advice and rules already owned elsewhere need not become another instruction.

Write for judgment

State the premise and connect instructions to their reasons so the agent can apply them to cases you did not anticipate. Give criteria and boundaries; prescribe a sequence only when the order affects correctness. Keep enough context to prevent the recurring mistake without dictating unrelated work.

Describe the capability and the user intent that should select it in the frontmatter description. Add exclusions for plausible near misses, and revisit the description when the capability changes. The body supplies the judgment and workflow rather than repeating a list of trigger phrases.

Keep the core readable on its own. Link to a reference with a concrete reason to read it, and retain examples only when they reveal something the principle cannot carry alone. Remove obsolete references and duplicated rules as part of the same edit; moving every paragraph elsewhere is not simplification.

Repository conventions

Project skills live in .agents/skills/<name>/SKILL.md with lowercase hyphenated names and YAML frontmatter containing name and description. Preserve optional metadata or host settings unless the requested change makes them unnecessary; do not add host scaffolding to portable skills by default.

For skills intended for Claude as well, create a relative sibling link from the repository root, and update or remove it with the skill:

bash
ln -s ../../.agents/skills/<name> .claude/skills/<name>

Codex-only skills deliberately have no Claude link. CLAUDE.md files are shims importing the sibling AGENTS.md. Durable personal guidance belongs in the tracked dotfiles repository, not a host-managed system-skill installation.

When importing guidance, inspect its scripts, dependencies, external actions, and assumptions before using them. Adapt to local conventions and state the tools or credentials the workflow needs; instructions cannot grant access.

Check what changed

Choose checks that answer a concrete uncertainty. Check affected links after moving references; check frontmatter and intended-host discovery after changing skill names, locations, or discovery metadata. A prose correction does not by itself require an installation CLI or an audit of the whole library.

Review the motivating request and a materially different use to see whether the judgment transfers, including when direct action is appropriate. When behavior is uncertain or regresses, compare actual work with the previous version, or without the skill for a new capability. Report what was observed separately from what the wording is intended to improve.

Read evaluation when investigating selection or behavior, comparing versions, or asked for evidence of improvement. Read composition diagnostics when checking broken links, duplicated guidance, or competing skill descriptions. Neither is a required pass for every edit.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Agent Instructions AI skill do?

Write and maintain repository guidance across AGENTS.md, CLAUDE.md, and .agents/skills. Use when creating or editing skills, deciding where instructions belong, or diagnosing instruction sprawl and skill selection. Do not use merely because another skill is being executed.

Why use Agent Instructions on TypingMind?

Because you install it once and use it with any model. Agent Instructions 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 Agent Instructions in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/EpicenterHQ/epicenter/tree/main/.agents/skills/agent-instructions. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Agent Instructions?

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 Agent Instructions?

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

Is the Agent Instructions AI skill free?

It is published on GitHub by EpicenterHQ. 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 👇