with one click
using-superpowers
// Use when starting any conversation - establishes how to find and use Codemini skills before acting
// Use when starting any conversation - establishes how to find and use Codemini skills before acting
Generate a CodeWiki project requirements report in Markdown format from an existing codebase. Same report scope as the HTML CodeWiki—presented as `.md` for plain-text reading, Git diffs, and Markdown previewers.
Generate a CodeWiki project requirements report in interactive HTML format from an existing codebase. Same report scope as the Markdown CodeWiki—browser-openable with search, filters, collapsible API cards, and inline SVG/CSS diagrams.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
| name | using-superpowers |
| description | Use when starting any conversation - establishes how to find and use Codemini skills before acting |
Codemini skills guide workflow, but user instructions always take precedence:
AGENTS.md, direct requests, project docs) - highest priorityIf AGENTS.md says "do not use TDD" and a skill says to use TDD, follow AGENTS.md. The user is in control.
Use Codemini's skill tool for indexed skills, or invoke a skill as a slash command such as /systematic-debugging. The full SKILL.md is loaded on demand; do not read skill files manually unless you are editing the skill itself.
Codemini ships a compact built-in skill set focused on day-to-day development:
| Skill | Use when |
|---|---|
brainstorming | Requirements or approach are still ambiguous. |
test-driven-development | Implementing a feature or bugfix with meaningful behavior. |
systematic-debugging | Investigating a bug, failing test, or unexpected behavior. |
verification-before-completion | Before claiming work is complete or fixed. |
requesting-code-review | Before merging or when a plan/change needs pressure testing. |
receiving-code-review | When acting on review feedback. |
using-git-worktrees | When isolated feature work would reduce risk. |
Invoke relevant or requested skills before taking action. If a skill may apply, load it with Codemini's skill tool or invoke it as a slash command, then follow the current instructions from that skill. If it turns out not to fit, say so briefly and continue with the better workflow.
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" [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" [label="yes"];
"Might any skill apply?" -> "Respond (including clarifications)" [label="definitely not"];
"Invoke skill" -> "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";
}
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. |
When multiple skills could apply, use this order:
"Let's build X" → brainstorming first, then implementation skills. "Fix this bug" → debugging first, then domain-specific skills.
Rigid (TDD, debugging): Follow exactly. Don't adapt away discipline.
Flexible (patterns): Adapt principles to context.
The skill itself tells you which.
Instructions say WHAT, not HOW. "Add X" or "Fix Y" doesn't mean skip workflows.