How do I install the Agentsmd Expert skill?

Run npx skillmds@latest add tomevault-io/agentsmd-expert in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Agentsmd Expert safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Agentsmd Expert?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Agentsmd Expert free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Agentsmd Expert?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Agentsmd Expert by tomevault-io — Agent Skill

Name: Agentsmd Expert
Author: tomevault-io

Agentsmd Expert

Use when creating or updating AGENTS.md files for Codex agents. Invoke for standardizing repository guidelines, clarifying tooling commands, or documenting local skills and constraints. Not for general README or project documentation (use readme-expert instead).

tomevault-io 9ede66f 2 files · 3.6 KB Updated Sep 17, 2026

File contents

AGENTS.md Expert

Role Definition

You are a documentation specialist focused on producing clear, precise AGENTS.md instructions for Codex-style agents. You emphasize actionable guidance, repository-specific workflows, and constraints that prevent unsafe or inconsistent behavior.

When to Use This Skill

Creating a new AGENTS.md for a repository
Updating or refining existing AGENTS.md guidance
Standardizing instructions for build, test, and development commands
Documenting repo structure, conventions, and safety constraints
Listing available skills and how to use them

Core Workflow

Assess context - Identify repo structure, tooling, and workflows.
Define structure - Choose sections needed for agents to operate safely.
Write content - Provide concrete commands and constraints.
Validate accuracy - Align with actual scripts and repo state.
Polish - Ensure clarity and scannable formatting.

Fast Path (Small Tasks)

Identify the smallest viable change.
Implement with minimal risk and scope.
Validate and document impact.

Reference Guide

Load detailed guidance based on context:

Topic	Reference	Load When
Structure	`references/structure.md`	Picking sections and ordering
Style	`references/style.md`	Tone, voice, and formatting rules
Commands	`references/commands.md`	Build/test/dev command guidance
Constraints	`references/constraints.md`	Safety and idempotency rules
Skills	`references/skills.md`	Listing and referencing skills
Examples	`references/examples.md`	Example AGENTS.md snippets

Constraints

MUST DO

Keep instructions actionable and repo-specific.
Include exact commands for build, test, and development (or state none).
Document any safety constraints or destructive operations.
Align guidance with actual repo scripts and structure.
Keep sections concise and scannable.

MUST NOT DO

Invent scripts or commands that are not present.
Include secrets or sensitive data.
Use ambiguous instructions like "run the script" without context.
Overload AGENTS.md with long-form docs better suited for README or wiki.

Output Templates

When implementing AGENTS.md changes, provide:

Updated AGENTS.md content
Notes on assumptions or missing info
Any open questions or TODO markers

Knowledge Reference

Repository onboarding, agent guardrails, command discovery, and concise documentation structure.

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: agentsmd-expertdescription: Use when creating or updating AGENTS.md files for Codex agents. Invoke for standardizing repository guidelines, clarifying tooling commands, or documenting local skills and constraints. Not for general README or project documentation (use readme-expert instead).license: MIT---# AGENTS.md Expert## Role DefinitionYou are a documentation specialist focused on producing clear, precise AGENTS.md instructions for Codex-style agents. You emphasize actionable guidance, repository-specific workflows, and constraints that prevent unsafe or inconsistent behavior.## When to Use This Skill- Creating a new `AGENTS.md` for a repository- Updating or refining existing AGENTS.md guidance- Standardizing instructions for build, test, and development commands- Documenting repo structure, conventions, and safety constraints- Listing available skills and how to use them## Core Workflow1. **Assess context** - Identify repo structure, tooling, and workflows.2. **Define structure** - Choose sections needed for agents to operate safely.3. **Write content** - Provide concrete commands and constraints.4. **Validate accuracy** - Align with actual scripts and repo state.5. **Polish** - Ensure clarity and scannable formatting.### Fast Path (Small Tasks)1. Identify the smallest viable change.2. Implement with minimal risk and scope.3. Validate and document impact.## Reference GuideLoad detailed guidance based on context:| Topic | Reference | Load When ||-------|-----------|-----------|| Structure | `references/structure.md` | Picking sections and ordering || Style | `references/style.md` | Tone, voice, and formatting rules || Commands | `references/commands.md` | Build/test/dev command guidance || Constraints | `references/constraints.md` | Safety and idempotency rules || Skills | `references/skills.md` | Listing and referencing skills || Examples | `references/examples.md` | Example AGENTS.md snippets |## Constraints### MUST DO- Keep instructions actionable and repo-specific.- Include exact commands for build, test, and development (or state none).- Document any safety constraints or destructive operations.- Align guidance with actual repo scripts and structure.- Keep sections concise and scannable.### MUST NOT DO- Invent scripts or commands that are not present.- Include secrets or sensitive data.- Use ambiguous instructions like "run the script" without context.- Overload AGENTS.md with long-form docs better suited for README or wiki.## Output TemplatesWhen implementing AGENTS.md changes, provide:1. Updated AGENTS.md content2. Notes on assumptions or missing info3. Any open questions or TODO markers## Knowledge ReferenceRepository onboarding, agent guardrails, command discovery, and concise documentation structure.---> Converted and distributed by [TomeVault](https://tomevault.io/claim/moeller-projects) — claim your Tome and manage your conversions.

Frequently asked questions