# Create Project Instructions

> Create project-context AGENTS.md files using phased discovery, required operational sections, and session-state modeling.

- Skill: `msiccdev/create-project-instructions` (Agent Skill, multi-file: 8 files)
- Install (CLI): `npx skillmds@latest add msiccdev/create-project-instructions`
- Raw SKILL.md: https://api.skillmd.com/api/skills/msiccdev/create-project-instructions/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Product & Planning
- Author: MSiccDev (https://skillmd.com/u/msiccdev)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/msiccdev/create-project-instructions

---


# 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.

## How to Invoke

Load or attach this file's contents into your AI session to activate the workflow (paste, upload, or reference with `#file:skills/create-project-instructions/SKILL.md` in VS Code Copilot Chat). In Claude Projects, add it to project knowledge. See [Invoking Skills](../../README.md#invoking-skills) in the README for full platform guidance.

## 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
1. Run phased discovery using `references/discovery-phases.md`.
2. Apply required output schema from `references/output-schema.md`.
3. Build command and role structures using:
   - `references/command-template.md`
   - `references/role-template.md`
4. Apply artifact/summary contract from `references/output-format.md`.
5. Stamp `<!-- spec_version: 1.5.0 -->` as an HTML comment at the top of the generated `AGENTS.md`.
6. 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.