Superpowers is a complete software development methodology for your coding agents, built on top of a set of composable skills and initial instructions that make sure your agent uses them.
It starts from the moment you fire up your coding agent. As soon as it sees that you're building something, it doesn't just jump into trying to write code. Instead, it steps back and asks you what you're really trying to do.
Once it's teased a spec out of the conversation, it shows it to you in chunks short enough to actually read and digest.
After you've signed off on the design, your agent puts together an implementation plan that's clear enough for an enthusiastic junior engineer with poor taste, no judgement, no project context, and an aversion to testing to follow. It emphasizes true red/green TDD, YAGNI (You Aren't Gonna Need It), and DRY.
Next up, once you say "go", it launches a subagent-driven-development process, having agents work through each engineering task, inspecting and reviewing their work, and continuing forward. It's not uncommon for Kimi to be able to work autonomously for a couple hours at a time without deviating from the plan you put together.
There's a bunch more to it, but that's the core of the system. And because the skills trigger automatically, you don't need to do anything special. Your coding agent just has Superpowers.
These skills are already in .agents/skills/ and will be auto-discovered when working in this directory.
To use across all projects:
mkdir -p ~/.config/agents/skills
cp -r .agents/skills/* ~/.config/agents/skills/Or use --skills-dir when starting Kimi:
kimi --skills-dir /path/to/superpowers-kimi/.agents/skills-
brainstorming - Activates before writing code. Refines rough ideas through questions, explores alternatives, presents design in sections for validation. Includes an optional visual companion for browser-based mockups and diagrams. Saves design document.
-
using-git-worktrees - Activates after design approval. Creates isolated workspace on new branch, runs project setup, verifies clean test baseline.
-
writing-plans - Activates with approved design. Breaks work into bite-sized tasks (2-5 minutes each). Every task has exact file paths, complete code, verification steps.
-
subagent-driven-development or executing-plans - Activates with plan. Dispatches fresh subagent per task with two-stage review (spec compliance, then code quality), or executes in batches with human checkpoints.
-
test-driven-development - Activates during implementation. Enforces RED-GREEN-REFACTOR: write failing test, watch it fail, write minimal code, watch it pass, commit. Deletes code written before tests.
-
requesting-code-review - Activates between tasks. Reviews against plan, reports issues by severity. Critical issues block progress.
-
finishing-a-development-branch - Activates when tasks complete. Verifies tests, presents options (merge/PR/keep/discard), cleans up worktree.
The agent checks for relevant skills before any task. Mandatory workflows, not suggestions.
Testing
- test-driven-development - RED-GREEN-REFACTOR cycle
Debugging
- systematic-debugging - 4-phase root cause process
- verification-before-completion - Ensure it's actually fixed
Collaboration
- brainstorming - Socratic design refinement
- writing-plans - Detailed implementation plans
- executing-plans - Batch execution with checkpoints
- dispatching-parallel-agents - Concurrent subagent workflows
- requesting-code-review - Pre-review checklist
- receiving-code-review - Responding to feedback
- using-git-worktrees - Parallel development branches
- finishing-a-development-branch - Merge/PR decision workflow
- subagent-driven-development - Fast iteration with two-stage review
Tools & References
- visual-companion - Browser-based server for mockups, diagrams, and visual A/B testing during brainstorming
- spec-document-reviewer - Validate design specs before planning
- plan-document-reviewer - Validate implementation plans before execution
- code-reviewer - Structured production-readiness reviews
Meta
- writing-skills - Create new skills following best practices
- using-superpowers - Introduction to the skills system
When running in yolo/non-interactive mode (AskUserQuestion unavailable), Superpowers skills do not silently skip user-choice gates. Instead, the agent outputs a visible decision block before proceeding:
--- ASSUMPTIONS ---
--- APPROACHES CONSIDERED ---
--- RECOMMENDATION ---
--- NEXT STEP ---
This ensures you can review every decision the agent made on your behalf and override it in your next message.
Kimi CLI has a native Plan Mode (EnterPlanMode/ExitPlanMode). In yolo mode both are auto-approved, and ExitPlanMode ignores any options parameter — your approach choices won't be shown. Superpowers skills take precedence over Plan Mode workflow. We recommend using superpowers:brainstorming for design and superpowers:writing-plans for planning instead of mixing native Plan Mode with Superpowers.
- Test-Driven Development - Write tests first, always
- Systematic over ad-hoc - Process over guessing
- Complexity reduction - Simplicity as primary goal
- Evidence over claims - Verify before declaring success
MIT License
Superpowers is built by Jesse Vincent and the rest of the folks at Prime Radiant.
This is a Kimi Code CLI adaptation of the original Superpowers framework.
- Discord: Join us for community support
- Original repository: https://github.com/obra/superpowers
- Release announcements: Sign up