superpowers

Plugin superpowers from marketplace cc-plugins in mthalman/cc-plugins. Commands read from the repo's manifest — 1 month ago.

Skills (38)

• arena

  Generate multiple structurally distinct interface or module designs in parallel, compare them against a task-specific rubric, select one coherent base, and graft the strongest compatible ideas from the alternatives. Use when the user wants to design an API, explore module shapes, compare competing i

• azure-pipeline-monitor

  Monitor an Azure DevOps (ADO) pipeline run to completion — the whole run or a single stage/job — using a blocking poller that estimates expected duration from past runs, adapts its polling cadence, holds control until a final outcome is reached, and returns a structured JSON result. Use this wheneve

• blast-radius

  Analyze what a proposed or completed code change could break outside the visible diff, identify the small set of safety assumptions the change depends on, and prove those assumptions with the strongest practical evidence. Use only when the user explicitly invokes blast-radius analysis, asks "what co

• bro

  Restate the immediately preceding assistant response in plain, concise human language without losing its facts, conclusions, caveats, commands, or exact identifiers. Use only when the user explicitly says "bro", asks to dumb down or simplify the last answer, or says the previous explanation was too

• claude-extension-type-identifier

  Use when determining what type of Claude Code extension (command, skill, or agent) a prompt or description should be classified as. This skill should be used when users ask "should this be a command, skill, or agent", when designing new extensions, or when there is ambiguity about the correct extens

• code-commenting

  Use proactively whenever writing or auditing inline code comments, doc comments, or docstrings. Explains why over what, preserves non-obvious contracts and rationale, removes narration and stale comments, evaluates suppressions, and prefers types, tests, naming, or structure when they can encode a c

• code-refactorer

  Expert code refactoring that strictly preserves existing behavior. Use when asked to refactor code, improve code structure, reduce duplication, extract methods/classes/modules, simplify complex conditionals, improve naming, apply design patterns, reduce complexity, clean up code, make code more main

• code-review-skill-creator

  Generate a repo-specific code-review skill (SKILL.md) for any GitHub repository by mining its PR history, issue history, and codebase, then synthesizing the findings into a reusable reviewer skill. Use whenever the user wants to "create a code review skill", "generate a review skill for my repo", "b

• code-review

  Use when analyzing code changes for correctness, performance, safety, and quality. Provides review criteria, severity classification, and output format for code reviews. Use standalone when reviewing any code changes, diffs, or patches. Triggers on "review my code", "check this for bugs", "audit thi

• copilot-pr-review

  Full GitHub Copilot PR review feedback loop — add Copilot as reviewer, poll for review, respond to comments, resolve threads, re-request review, and repeat until clean. Use when the user asks to 'run Copilot review', 'get Copilot feedback', 'request Copilot PR review', or when a PR needs automated c

• defend-the-diff

  Interrogate an existing code change through focused questions, evidence-backed answers, and independent judgment so the change is explainable, correct, justified, and defensible. Invoke explicitly when a user asks to defend a diff, justify code changes, run an explainability review, or challenge whe

• designing-ui-color

  Use when selecting colors for interfaces, evaluating color combinations, creating palettes, resolving stakeholder color conflicts, or when colors "feel wrong" but you can't articulate why - provides expert color theory, perceptual principles, and systematic palette creation beyond basic accessibilit

• designing-ui-typography

  Use when designing typography for web/app interfaces, selecting fonts, setting up type scales, addressing performance/accessibility concerns, or handling stakeholder conflicts over typography - provides expert-level guidance on font rendering, OpenType features, and performance trade-offs

• dispatching-parallel-agents

  Use when facing 2+ substantial tasks that can run without shared state or sequential dependencies, or when a high-value uncertain task justifies an explicitly bounded race. Covers partition, race, and mixed parallelism; self-contained briefs; isolated writes; and PASS, ISSUES, or BLOCKED result aggr

• documenting-workflows

  Use when the user wants to document a workflow, process, or procedure through an interview - asks questions one at a time to thoroughly capture steps, prerequisites, edge cases, and troubleshooting, then validates understanding before writing markdown

• draft-pr

  Draft a ready-to-paste pull request title and description from repository changes, commits, linked issue or work-item context, and the target GitHub repository's PR template when one exists. Use when the user asks to draft, write, improve, or regenerate a PR title, PR description or body, pull reque

• grill-me

  Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

• logo-design

  Use when designing logos, creating brand marks, or helping with visual identity work - provides expert logo design process including discovery, strategic positioning, validation testing, and delivery of production-ready designs using SVG

• markdown-toolkit

  Use when generating or validating GitHub Flavored Markdown structure and mechanics, including headings, links, tables, lists, code fences, anchors, templates, and markdownlint compliance. Use technical-writing instead for substantive document mode, information architecture, terminology, instructiona

• over-engineering-review

  Use when evaluating code, a diff, API, or design for unnecessary complexity, speculative abstraction, premature extensibility, excessive indirection, needless configurability, or YAGNI violations. Produces an evidence-based, read-only assessment with simpler adequate alternatives while preserving ju

• post-github-review-comments

  Post code review findings as pending review comments on a GitHub pull request using the GitHub CLI. Use when the user asks to "post review comments", "add PR comments", "submit review comments", "post findings to PR", or when code review output needs to be turned into GitHub PR review comments. Also

• prompt-engineering

  Use when crafting prompts for AI models, reviewing existing prompts for quality, or designing system prompts for agents and tools - provides expert guidance on structure, clarity, common patterns, and model-specific optimizations to create effective, token-efficient prompts

• prompt-validator-generator

  Use when needing to create validators for LLM prompts in a specific domain - provides systematic process for analyzing domain expertise, classifying prompt types, and generating domain-specific validation frameworks that check for expert-level effectiveness, not just coverage

• show-me-your-work

  Keep a compact, reviewable decision trail for long-running, multi-phase, experimental, or unattended work. Use only when the user explicitly asks to show the work, keep a decision log, or produce an audit trail. Do not invoke automatically for routine or complex tasks.

• skill-reviewer

  Use when reviewing a newly authored or recently modified skill (a SKILL.md and its bundled files) for quality before it is merged or adopted. Checks frontmatter validity, description and trigger quality, structure, actionability, scope, progressive disclosure, and broken references, then reports fin

• svg-generator

  Use when generating SVG graphics from written descriptions including icons, data visualizations, illustrations, technical diagrams, or any visual content. Emphasizes visual accuracy through planning-first workflows, proper coordinate systems, and expert-level engineering reasoning including alternat

• systematic-debugging

  Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

• tdd

  Apply test-driven development to an approved software design by creating compile-valid interface or API stubs and executable tests before implementation begins. Use when the user provides a design, contract, API proposal, state model, or acceptance criteria and asks for TDD, test-driven development,

• technical-writing

  Use when authoring or substantively reviewing the content of technical documentation, READMEs, RFCs, design explanations, tutorials, how-to guides, reference material, or other engineering prose. Helps choose the document mode, organize information for the reader, write direct instructions, maintain

• threat-modeling

  Use when creating threat model documents for systems, services, or components - guides systematic user interview to gather comprehensive security information before documenting threats and mitigations using STRIDE methodology

• triage-issue

  Triage a bug or issue by exploring the codebase to find root cause, then create a GitHub issue with a TDD-based fix plan. Use when user reports a bug, wants to file an issue, mentions "triage", or wants to investigate and plan a fix for a problem.

• ubiquitous-language

  Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain mod

• unslop

  Remove recognizable AI-writing patterns from existing prose while preserving its meaning, evidence, uncertainty, and intended voice. Use only when the user explicitly asks to unslop, de-AI, humanize, or remove AI tells from text. Applies to documentation, messages, PR descriptions, reports, and othe

• using-git-worktrees

  Use when starting feature work that needs isolation from the current workspace, before executing implementation plans, or when auditing linked worktrees for active, unpublished, merged, or potentially removable work. Prefers host-native isolation, falls back to Git worktrees, and provides a conserva

• validation-scenarios

  Examine a proposed or completed change and design a proportional set of risk-based validation scenarios that provides reasonable assurance the change is correct. Use when the user asks for a validation plan, manual QA workflow, release checks, smoke scenarios, confidence-building checks, or "how sho

• web-audio-designer

  Use when creating audio from written descriptions - generates high-quality sound effects, musical tones, UI feedback sounds, ambient soundscapes, and game audio using Web Audio API for JavaScript. Triggered by requests like "create a button click sound", "generate a sci-fi whoosh", or "make an 8-bit

• why

  Investigate the historical motivation and constraints behind code, architecture, thresholds, regressions, or design choices. Use when the user asks why something was built this way, why one approach was chosen over another, where a number came from, what prior fixes failed, or whether the original r

• zoom-out

  Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Slash commands (3)

• /superpowers:address-pr-comments

  Systematically address GitHub or Azure DevOps PR review comments one at a time, with interactive guidance and resumable progress

• /superpowers:create-pr

  Full PR lifecycle — local code review and test loop, PR creation, Copilot review loop, CI verification, and merge conflict resolution

• /superpowers:pull-request-walkthrough

  Walk through a pull request interactively, explaining code changes to help you understand how everything works. Supports GitHub and Azure DevOps.

Subagents (1)

• code-reviewer

  Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: <example>Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing

Similar plugins