Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
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 brainstorming completes and a spec is approved — researches the current state of the art for all technologies and patterns in the spec before any implementation begins
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
Ultrapowers is a research-driven software development workflow for your coding agents. It extends Superpowers by Jesse Vincent with a research-first pipeline that ensures agents always work with current, verified knowledge before writing code.
Documentation · GitHub · Issues
It starts the same way Superpowers does — your agent doesn't just jump into code. It steps back and asks what you're really trying to do.
But then Ultrapowers goes further. After brainstorming, it researches the current state of the art for every technology and pattern involved. It audits your existing skills against what it finds, creates or updates skills to fill gaps, and only then moves into planning and implementation.
Every implementation step gets audited against the research findings and your plan. The result: agents that build on verified knowledge, not assumptions. Knowledge compounds across sessions — your agent gets smarter over time.
Another key difference: you stay in control. Ultrapowers does not auto-commit plans, does not auto-commit code, and does not auto-push. You decide when to commit and when to push. Plans are working documents, not git artifacts — commit them if you want to, or don't.
Ultrapowers is a fork of Superpowers by Jesse Vincent (obra) and the team at Prime Radiant. The original Superpowers workflow is brilliant — Ultrapowers builds on top of it. If Superpowers has helped you, consider sponsoring Jesse's work.
Register the marketplace first:
/plugin marketplace add ennio-datatide/ultrapowers
Then install:
/plugin install ultrapowers@ultrapowers
git clone https://github.com/ennio-datatide/ultrapowers.git
Start a new session and ask for something that should trigger a skill (for example, "help me plan this feature" or "let's debug this issue"). The agent should automatically invoke the relevant skill.
brainstorming — Your agent steps back and asks what you're really trying to do. Refines rough ideas through questions, explores alternatives, presents design in sections for validation.
deep-research — Researches the current state of the art for all technologies and patterns in the spec. Uses documentation, web search, and context to capture what's current — not what was true six months ago.
skills-audit — Audits all available skills against research findings. Classifies each as Covered, Stale, Missing, or External. Identifies exactly what needs to be created or updated.
skills-creation — Creates new or updates existing skills to fill gaps identified by the audit. Knowledge is captured for future sessions.
using-git-worktrees — Creates isolated workspace on new branch, runs project setup, verifies clean test baseline. Your main branch stays untouched.
writing-plans — Breaks work into bite-sized tasks (2-5 minutes each) with skill annotations on each step. Clear enough for any agent to follow.
subagent-driven-development or executing-plans — Dispatches fresh subagent per task with audited two-stage review (spec compliance first, then code quality).
test-driven-development — 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 — Reviews against plan with audit checks. Critical issues block progress. No rubber-stamping.
finishing-a-development-branch — Verifies all tests pass, presents options (merge/PR/keep/discard), cleans up worktree. You decide what happens next.
The agent checks for relevant skills before any task. Mandatory workflows, not suggestions.
"Build me a real-time notification system using WebSockets."
Ultrapowers brainstorms the design with you, researches current WebSocket best practices and libraries, audits your existing skills to find gaps, creates any missing skills, then plans and implements with TDD — all audited against the research. You review the code and commit when you're satisfied.
npx claudepluginhub ennio-datatide/ultrapowersDevelopment skills for Claude Code: language best practices, framework patterns, architecture, testing, and AI agent patterns
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.