Agents

Purpose

This file defines how to use agent-style workflows in this project so tasks are clear, scoped, and repeatable.

Audience And Tone Rules

Assume the reader is new to AI and needs detailed, step-by-step guidance.

Be specific and explicit. Avoid shorthand.
Explain terms in plain language.
Provide an example whenever possible.
Prefer checklists, short steps, and concrete outcomes.
Assume the reader is an expert engineer but a beginner at AI.

Sync Expectation

Keep this file aligned with PRD and README when workflows, scope, or structure change.

When to Use Agents

Multi-step changes across files.
Refactors with clear acceptance criteria.
Audits or documentation updates.

Common Agent Use Cases

Create or expand documentation sections.
Plan a refactor before making edits.
Summarize and assess risks across files.

How to Use Agents

Define the outcome in one sentence.
List inputs (files, context, constraints).
Ask for a plan, then approve before edits.
Ask for focused changes and verification steps.

Skills Sync

This repo uses a skills manifest to standardize skills across developers.

Review skills.yaml for required skills.
Run ./scripts/sync-skills.sh to sync skills locally.
Restart your editor if needed.

Suggested Agent Request Template

Goal: (one sentence)
Inputs: (files, context, constraints)
Output: (expected deliverable)
Verification: (tests or checks)

Example

Goal: Add a troubleshooting section to the AI docs. Inputs: docs/ai/troubleshooting.md, docs/planning/AI-Docs-Plan.md Output: Updated troubleshooting section with 5 common issues. Verification: Manual review.

1.6 KiB Raw Blame History