Skip to content
AI & Agents
Skill

/superpowers

Use when the user wants a disciplined software development workflow with design-first planning, implementation plans, TDD, systematic debugging, code review, or verification-before-completion, adapted from obra/superpowers.

BOOST
From plugin
nextclaw
26243 skills
Install
$ npx -y skills add peiiii/nextclaw --skill superpowers --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/superpowers

Context preview

The summary Claude sees to decide when to auto-load this skill.

Use when the user wants a disciplined software development workflow with design-first planning, implementation plans, TDD, systematic debugging, code review, or verification-before-completion, adapted from obra/superpowers.

SKILL.md

superpowers.SKILL.md
name: superpowers
description: Use when the user wants a disciplined software development workflow with design-first planning, implementation plans, TDD, systematic debugging, code review, or verification-before-completion, adapted from obra/superpowers.

Superpowers

Overview

Use this skill when the user wants a stronger engineering workflow inside NextClaw.

This marketplace skill adapts the upstream `obra/superpowers` project into a single installable NextClaw skill. Because NextClaw marketplace installs one skill directory at a time, this package provides:

  • one top-level workflow router,
  • bundled local reference files for the most useful upstream superpowers skills,
  • and clear rules for when to load which reference.

Be explicit about the boundary:

  • This skill owns workflow selection, expectation-setting, and reference routing.
  • The bundled reference files own the detailed superpowers methodology.
  • NextClaw, the current project rules, and the actual tool runtime own execution.

Do not present bundled superpowers guidance as a higher-priority authority than the user's instructions, the current project's `AGENTS.md`, or the host platform's rules.

What This Skill Covers

  • design-first brainstorming before implementation,
  • implementation plan writing for multi-step work,
  • test-driven development for feature and bugfix work,
  • root-cause-first debugging,
  • pre-merge or post-task code review prompts,
  • evidence-before-claims verification,
  • optional subagent-driven execution when the environment actually supports it.

What This Skill Does Not Cover

  • overriding user instructions or project rulebooks,
  • pretending NextClaw natively supports the upstream superpowers multi-directory auto-discovery model,
  • forcing subagent workflows when the current runtime does not support them,
  • claiming a workflow step happened when the needed evidence was not actually collected,
  • replacing domain-specific project skills that are more specific than this general workflow skill.

Install Boundary

Always distinguish these paths:

  • NextClaw marketplace install:

`nextclaw skills install superpowers`

  • Installed NextClaw skill assets:

`<workspace>/skills/superpowers/`

  • Upstream standalone installation outside NextClaw:

clone `https://github.com/obra/superpowers` and follow the upstream install docs

For NextClaw users, prefer the marketplace-installed assets already bundled under `skills/superpowers/`.

Do not ask the user to install the upstream repo separately unless they explicitly want the original Codex or Claude plugin setup outside NextClaw.

Deterministic First-Use Workflow

When this skill triggers, follow this order.

Step 0: Verify bundled references exist

Check:

test -f skills/superpowers/references/brainstorming.md
test -f skills/superpowers/references/systematic-debugging.md

If either file is missing, the skill is not correctly installed in the current workspace.

Step 1: Classify the user's need

Choose the smallest matching workflow:

  • feature or behavior design,
  • implementation planning,
  • implementation or bugfix execution,
  • debugging an existing problem,
  • review before merge or handoff,
  • verification before claiming completion,
  • plan execution with parallel agents.

Step 2: Load only the matching reference

Read only the smallest relevant reference instead of loading everything at once:

  • design or requirements refinement:

[references/brainstorming.md](references/brainstorming.md)

  • implementation plan writing:

[references/writing-plans.md](references/writing-plans.md)

  • implementation or bugfix execution:

[references/test-driven-development.md](references/test-driven-development.md)

  • debugging and root-cause analysis:

[references/systematic-debugging.md](references/systematic-debugging.md)

  • pre-merge or task-level review:

[references/requesting-code-review.md](references/requesting-code-review.md)

  • before saying work is done:

[references/verification-before-completion.md](references/verification-before-completion.md)

  • executing an approved plan with agent delegation:

[references/subagent-driven-development.md](references/subagent-driven-development.md)

Do not bulk-read all references unless the task truly spans multiple workflow stages.

Step 3: Reconcile with host rules before acting

Before following any bundled superpowers guidance, reconcile it with:

  • the user's explicit request,
  • the current repository's `AGENTS.md`,
  • the host runtime's tool and permission model,
  • and any more specific installed skill that directly matches the task.

If there is a conflict, follow the higher-priority local rule and use the bundled superpowers material as methodology, not authority.

Step 4: Execute with honest boundaries

  • Prefer the project's existing validation and review commands when they already exist.
  • If the current repository has stricter branching, testing, review, or release rules, follow those.
  • If the environment lacks multi-agent support, skip the subagent path and continue with the non-delegated workflow.
  • If the task is trivial, keep the workflow compact rather than theatrical, but still choose an explicit workflow.

Workflow Routing Guidance

New feature, refactor, or behavior change

Start with:

  • [references/brainstorming.md](references/brainstorming.md)

If the work becomes multi-step or cross-module, continue with:

  • [references/writing-plans.md](references/writing-plans.md)

During implementation, use:

  • [references/test-driven-development.md](references/test-driven-development.md)

Before declaring success, use:

  • [references/verification-before-completion.md](references/verification-before-completion.md)

Bug, failing test, or unexpected behavior

Start with:

  • [references/systematic-debugging.md](references/systematic-debugging.md)

Once root cause is understood and a fix is ready, use:

  • [references/test-driven-development.md](references/test-dr
Read more
Ships withnextclaw

Your long-term personal AI partner. NextClaw's mission is to be a good long-term partner to you. We are building toward a 1.0 that understands you, takes useful initiative, and continuously improves itself.

Get the whole plugin

Other skills on nextclaw.

github
Skill

github

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced…

@peiiii@peiiiiInstall Skill