<EXTREMELY-IMPORTANT> If a skill clearly applies to the task at hand, you MUST invoke it before proceeding.

Invoke a skill when:

• The user explicitly requests it (by name or slash command)
• The task directly matches a skill's "When to Use" criteria
• A skill is marked "use PROACTIVELY" and the context matches

Do NOT invoke a skill when:

• The task is a simple question or lookup (no workflow needed)
• You're unsure and the skill description doesn't match the task
• Invoking it would add latency without value

When in doubt: check the skill's description. If it matches → invoke. If not → skip. </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. If a skill clearly matches the task, invoke it. If the match is ambiguous, use your judgment — false negatives (missing a useful skill) are worse than false positives (invoking an irrelevant one), but don't invoke everything blindly.

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

    "About to EnterPlanMode?" -> "Already brainstormed?";
    "Already brainstormed?" -> "Invoke brainstorming skill" [label="no"];
    "Already brainstormed?" -> "Might any skill apply?" [label="yes"];
    "Invoke brainstorming skill" -> "Might any skill apply?";

    "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 TodoWrite todo per item" [label="yes"];
    "Has checklist?" -> "Follow skill exactly" [label="no"];
    "Create TodoWrite todo per item" -> "Follow skill exactly";
}

Red Flags

These thoughts mean STOP—you're rationalizing:

Thought	Reality
"This doesn't need a skill"	If a skill's description matches your task, invoke it.
"I remember this skill"	Skills evolve. Read current version via Skill tool.
"The skill is overkill"	If it matches, invoke. You can adapt once loaded.
"I'll just do this one thing first"	Check for matching skills BEFORE starting work.
"I know what that means"	Knowing the concept ≠ having the latest skill guidance.

Skill Priority

When multiple skills could apply, use this order:

1. Process skills first (brainstorming, debugging) - these determine HOW to approach the task
2. Implementation skills second (frontend-design, mcp-builder) - these guide execution

"Let's build X" → brainstorming first, then implementation skills. "Fix this bug" → debugging first, then domain-specific skills.

Skill Types

Rigid (TDD, debugging): Follow exactly. Don't adapt away discipline.

Flexible (patterns): Adapt principles to context.

The skill itself tells you which.

User Instructions

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