IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.

This is not negotiable. This is not optional. You cannot rationalize your way out of this. </EXTREMELY-IMPORTANT>

How to Access Skills

In Claude Code: Use the Skill tool. When you invoke a skill, its content is loaded and presented to you—follow it directly. Never use the Read tool on skill files.

In other environments: Check your platform's documentation for how skills are loaded.

Using Skills

The Rule

Invoke relevant or requested skills BEFORE any response or action. Even a 1% chance a skill might apply means that you should invoke the skill to check. If an invoked skill turns out to be wrong for the situation, you don't need to use it.

digraph skill_flow {
    "User message received" [shape=doublecircle];
    "Might any skill apply?" [shape=diamond];
    "Invoke Skill tool" [shape=box];
    "Announce: 'Using [skill] to [purpose]'" [shape=box];
    "Has checklist?" [shape=diamond];
    "Create task per checklist item" [shape=box];
    "Follow skill exactly" [shape=box];
    "Respond (including clarifications)" [shape=doublecircle];

    "User message received" -> "Might any skill apply?";
    "Might any skill apply?" -> "Invoke Skill tool" [label="yes, even 1%"];
    "Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
    "Invoke Skill tool" -> "Announce: 'Using [skill] to [purpose]'";
    "Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
    "Has checklist?" -> "Create task per checklist item" [label="yes"];
    "Has checklist?" -> "Follow skill exactly" [label="no"];
    "Create task per checklist item" -> "Follow skill exactly";
}

Lifecycle Map — work → skill

Find the work, invoke the skill. Dispatch tier matters:

• (auto) — dual/library skills you invoke directly with the Skill tool, or that other skills call.
• (user runs) — user-only leaves (disable-model-invocation: true). You cannot invoke or dispatch these; they are invisible to you at call time. When one fits, recommend the slash command and let the user run it. They are heavyweight or high-blast-radius (swarms, full PRD generation, autonomous loops, outward-facing deploy) on purpose.

Define / Discover

Plan / Architect

Build

Verify / Review / Debug

Ship

Meta / Project

Red Flags

These thoughts mean STOP—you're rationalizing:

Skill Priority

When multiple skills could apply, use this order:

1. Process skills first (design-product, design-architecture) - these determine HOW to approach the task
2. Implementation skills second (tasks, test-driven-development) - these guide execution

"Let's build X" -> design-product first, then implementation skills.

Skill Types

Rigid: follow exactly, don't adapt away discipline

Flexible: adapt principles to context.

The skill itself tells you which type it is.

Monorepo Awareness

When working in a monorepo (.groundwork.yml exists):

• Always check project context before reading/writing specs
• If {{project_name}} is empty, prompt the user to select a project
• All {{specs_dir}}/ paths resolve to the selected project's specs directory
• Use /groundwork:select-project to switch between projects
• Use /groundwork:setup-repo to configure the repo structure

User Instructions

Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.