What is an AGENTS.md file?

An AGENTS.md is a project-context document containing sections, roles, session state, and command references used to guide AI agents.

Can I customize templates?

Yes; you can adapt role and command templates and the baseline structure to fit the project.

How is validation performed?

Validation uses the quality checklist to ensure completeness, consistency, and that the output remains provider-neutral.

create-project-instructions

npx machina-cli add skill MSiccDev/ai-context-kit/create-project-instructions --openclaw

Files (1)

SKILL.md

2.4 KB

Create Project Context AGENTS

Purpose

Generate project-context AGENTS.md files with required sections, role definitions, command namespace controls, and validation-ready structure.

When To Use

Use this skill when the task is to create or regenerate project-context AGENTS.md.
Use this skill when project context must include role/phase/style defaults.
Do not use this skill for user-context instruction generation.

Required Inputs

Project name, description, and current phase.
Tech stack, architecture, and repository structure.
Roles, default session state, and command namespace.
Objectives, testing strategy, and documentation standards.

Workflow

Run phased discovery using references/discovery-phases.md.
Apply required output schema from references/output-schema.md.
Build command and role structures using:
- references/command-template.md
- references/role-template.md
Apply artifact/summary contract from references/output-format.md.
Validate completeness using references/quality-checklist.md before final output.

Output Expectations

One complete AGENTS.md file with all required project-context sections.
Session-state and command-reference elements are fully populated.
Core project-context required-section completeness is enforced through AGENTS structure.
Role definitions and examples are project-specific and actionable.
Output remains provider-neutral.
Output contract and summary format follow references/output-format.md.

Resources

Discovery workflow: references/discovery-phases.md
Output schema: references/output-schema.md
Command template: references/command-template.md
Role templates: references/role-template.md
Output contract: references/output-format.md
Quality checklist: references/quality-checklist.md
Structure baseline: ../../templates/AGENTS_template.md
Example reference: ../../AGENTS.md

Constraints And Safety

Keep recommendations tied to project scope.
Avoid placeholders in final command examples unless explicitly unresolved.
Use relative paths for references.
Do not introduce provider-specific assumptions.

Source

git clone https://github.com/MSiccDev/ai-context-kit/blob/development/skills/create-project-instructions/SKILL.mdView on GitHub

Overview

Generates complete project-context AGENTS.md files with required sections, role definitions, and a validated structure. It follows phased discovery and templated schemas to ensure consistent, provider-neutral outputs that support onboarding and governance.

How This Skill Works

The skill guides users through phased discovery, applies the mandated output schema, and builds robust command and role references. The result is a single AGENTS.md that is ready for validation and aligns with documentation standards.

When to Use It

Create or regenerate a project-context AGENTS.md.
Ensure the document includes role, phase, and style defaults in the context.
Produce a validation-ready structure with session-state and command references.
Prepare AGENTS.md for new or evolving project scopes.
Audit or update AGENTS.md before handover or release.

Quick Start

Step 1: Gather project name, description, current phase, tech stack, architecture, repository structure, and inputs for roles, session state, and commands.
Step 2: Run phased discovery using references/discovery-phases.md and apply the output schema and templates to build the AGENTS.md core.
Step 3: Validate with the quality checklist and finalize the AGENTS.md for delivery.

Best Practices

Start from the AGENTS_template baseline and tailor to the project.
Fill all required sections, plus concrete role definitions and examples.
Keep file paths and references relative to the repository.
Validate against references/quality-checklist.md before finalizing.
Avoid placeholders in final commands unless unresolved.

Example Use Cases

Regenerate AGENTS.md for a greenfield project.
Update AGENTS.md after a tech stack change.
Create AGENTS.md for a monorepo with multiple teams.
Onboard a new team by exporting the current AGENTS.md.
Audit existing AGENTS.md for completeness and compliance.

Frequently Asked Questions

Add this skill to your agents