| name | using-superpowers |
| description | Use at the start of every Codex CLI conversation or new user request to enforce skill-first execution: check and read relevant skills before planning, clarifying, coding, or running tools |
If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST use that skill.
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.
Codex CLI Skill Access
Codex discovers skills from:
- Project-local:
./.agents/skills/
- User-level:
~/.agents/skills/
When a skill applies, open and follow that skill's SKILL.md instructions before taking implementation actions.
Using Skills
The Rule
Use relevant or requested skills BEFORE implementation actions. Even a 1% chance a skill might apply means you should read it first. If a skill turns out not to apply, move on.
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];
"Read relevant SKILL.md files" [shape=box];
"Announce: 'Using [skill] to [purpose]'" [shape=box];
"Has checklist?" [shape=diamond];
"Track checklist with update_plan" [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?" -> "Read relevant SKILL.md files" [label="yes, even 1%"];
"Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
"Read relevant SKILL.md files" -> "Announce: 'Using [skill] to [purpose]'";
"Announce: 'Using [skill] to [purpose]'" -> "Has checklist?";
"Has checklist?" -> "Track checklist with update_plan" [label="yes"];
"Has checklist?" -> "Follow skill exactly" [label="no"];
"Track checklist with update_plan" -> "Follow skill exactly";
}
Red Flags
These thoughts mean STOP—you're rationalizing:
| Thought | Reality |
|---|
| "This is just a simple question" | Questions are tasks. Check for skills. |
| "I need more context first" | Skill check comes BEFORE clarifying questions. |
| "Let me explore the codebase first" | Skills tell you HOW to explore. Check first. |
| "I can check git/files quickly" | Files lack conversation context. Check for skills. |
| "Let me gather information first" | Skills tell you HOW to gather information. |
| "This doesn't need a formal skill" | If a skill exists, use it. |
| "I remember this skill" | Skills evolve. Read current version. |
| "This doesn't count as a task" | Action = task. Check for skills. |
| "The skill is overkill" | Simple things become complex. Use it. |
| "I'll just do this one thing first" | Check BEFORE doing anything. |
| "This feels productive" | Undisciplined action wastes time. Skills prevent this. |
| "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. |
Skill Priority
When multiple skills could apply, use this order:
- Process skills first (brainstorming, debugging) - these determine HOW to approach the task
- 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.
