claude

core-superpowers

Universal AI development workflow: spec-driven development (/spec), TDD, debugging, code review, verification, and workflow automation

1 on GitHubby Mark Tripoliv1.2.0UNLICENSEDupdated 5 months ago
/

Plugin core-superpowers from marketplace ai-jesus-team in Triippz/ai-jesus-team. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (38)

  • agent-teams

    Coordinate multi-agent work on large features with file ownership.

  • arch-reviewer

    Use when reviewing code for architecture compliance -- validates module boundaries, dependency direction, and detects structural anti-patterns.

  • brainstorming

    Use when exploring design ideas, constraints, and requirements before planning implementation.

  • code-review

    Use when reviewing completed code for architecture compliance, quality, and security.

  • code-reviewer

    Use when reviewing code quality -- checks SOLID principles, DRY/KISS/YAGNI, naming, complexity, and maintainability.

  • debugger

    Use when debugging errors, test failures, or unexpected behavior -- follows reproduce-isolate-hypothesize-verify-fix methodology.

  • debugging

    Use when investigating bugs, errors, or unexpected behavior with structured methodology.

  • design-patterns

    Use when selecting appropriate design patterns, detecting anti-patterns, or refactoring code to use better structural patterns.

  • dispatching-agents

    Run multiple independent tasks in parallel using agents.

  • executing-plans

    Use when implementing code against an existing plan with TDD enforcement.

  • finishing-branch

    Use when implementation is complete and you need to prepare the branch for merge or MR.

  • git-worktrees

    Create isolated git worktrees for feature work.

  • grafana-engineer

    Grafana, Prometheus, Loki, and OpenTelemetry observability specialist.

  • merge-request

    Use when you need to push a branch and create a GitLab merge request via glab CLI

  • orchestrator

    Use when you need to route work to domain agents, enforce workflow order, or coordinate multi-step development tasks.

  • plan-to-jira

    Convert an implementation plan from docs/plans/ into JIRA issues with a parent Story/Epic and subtasks per plan step

  • resolve-reviews

    Fetch unresolved GitLab MR review comments, research and triage each, implement fixes, reply to all threads with evidence-backed rationale, and resolve discussions

  • security-auditor

    Use when auditing code for security vulnerabilities -- checks OWASP top 10, hardcoded secrets, injection, and insecure patterns.

  • spec-challenger

    Adversarial spec reviewer that challenges assumptions with cited evidence.

  • spec-driven-development

    Multi-phase spec/PRD authoring with adversarial review and deterministic validation.

  • spec-validator

    Read-only structural validator for spec/plan/tasks. Deterministic READY/BLOCKED verdict.

  • tdd

    Use when writing tests before implementation -- enforces red-green-refactor discipline.

  • test-automator

    Use when identifying test coverage gaps, designing test strategy, or validating test quality for a codebase.

  • update-jira

    Update JIRA issues with implementation details, QA test steps, and code change summaries after work is complete

  • using-superpowers

    Session entry point — skill catalog, workflow, and agent roster.

  • verification

    Use when running tests, linters, and type checkers to verify code correctness.

  • writing-plans

    Use when creating a step-by-step implementation plan with clear deliverables and dependencies.

  • writing-skills

    Meta-skill for authoring new skills using TDD principles.

  • async-audit

    Audit async code for correctness, performance, and safety across Rust (Tokio), Dart/Flutter, Python (asyncio/Celery), Go (goroutines), and TypeScript (Deno/Node). Use when writing, reviewing, or debugging async code, or when user mentions race conditions, deadlocks, cancellation, or async patterns.

  • handoff

    Compacts the current session into a structured handoff document so a fresh agent can continue the work without context loss

  • improve-codebase-architecture

    Find deepening opportunities in a codebase — refactors that turn shallow modules into deep ones, improving testability and AI-navigability

  • interrogate-with-docs

    Adversarial interview with domain-language enforcement, ADR generation, and code-vs-intent cross-referencing

  • interrogate
  • orient
  • plan-to-github
  • prototype
  • terse
  • update-github

Slash commands (26)

  • /core-superpowers:AGENTS
  • /core-superpowers:CLAUDE
  • /core-superpowers:async-audit

    Audit async code for race conditions, deadlocks, resource leaks, and cancellation safety

  • /core-superpowers:brainstorm

    Explore a design idea collaboratively before implementation

  • /core-superpowers:debug

    Debug a problem using structured reproduce-isolate-hypothesize-verify-fix

  • /core-superpowers:execute-plan

    Execute an implementation plan step-by-step with TDD enforcement

  • /core-superpowers:finish

    Auto-update docs and prepare branch for merge or PR

  • /core-superpowers:handoff

    Compact the current session into a handoff document so a fresh agent can continue without context loss

  • /core-superpowers:improve-codebase-architecture

    Find deepening opportunities — refactors that turn shallow modules into deep ones, improving testability and AI-navigability

  • /core-superpowers:interrogate-with-docs

    Stress-test a plan with glossary enforcement, ADR generation, and code-vs-intent cross-referencing

  • /core-superpowers:interrogate

    Stress-test a plan or design through adversarial dialogue, one branch at a time

  • /core-superpowers:mr

    Push branch and create a GitLab merge request via glab CLI

  • /core-superpowers:orient

    Map modules, callers, and dependencies for a codebase area using domain vocabulary

  • /core-superpowers:plan-to-github

    Convert an implementation plan into GitHub Issues with parent and child issues

  • /core-superpowers:plan-to-jira

    Convert an implementation plan into JIRA issues with subtasks

  • /core-superpowers:prototype

    Build throwaway code to answer a design question — logic explorer or UI variation sampler

  • /core-superpowers:readme
  • /core-superpowers:resolve-reviews

    Fetch unresolved GitLab MR review comments, evaluate each, and implement fixes

  • /core-superpowers:review

    Run architecture, code quality, and security review

  • /core-superpowers:spec

    Author a granular, unambiguous spec/PRD using spec-driven development (multi-phase, validation-gated)

  • /core-superpowers:tdd

    Write failing tests first using test-driven development

  • /core-superpowers:terse

    Activate ultra-compressed communication mode (~75% fewer tokens, full accuracy)

  • /core-superpowers:update-github

    Update GitHub Issues with implementation details and QA test steps

  • /core-superpowers:update-jira

    Update JIRA issues with implementation details and QA test steps

  • /core-superpowers:verify

    Run tests, linter, and type checker to verify readiness

  • /core-superpowers:write-plan

    Create a step-by-step implementation plan from a design

Subagents (14)

  • AGENTS
  • CLAUDE
  • arch-reviewer

    Architecture compliance reviewer that validates module boundaries and dependency direction

  • code-reviewer

    Code quality reviewer that checks SOLID principles, readability, and maintainability

  • debugger

    Structured debugging agent that follows reproduce-isolate-hypothesize-verify-fix methodology

  • design-patterns

    Design patterns expert that helps select appropriate patterns and detects anti-patterns

  • grafana-engineer

    Grafana, Prometheus, Loki, and OpenTelemetry observability specialist. Builds dashboards, configures alerts, designs OTel pipelines, and ingests logs. Reads latest docs via context7 MCP at runtime.

  • orchestrator

    Universal workflow orchestrator that detects project type and routes to domain-specific agents

  • protobuf-expert

    Protocol Buffers expert that reviews .proto files for correctness, style compliance, and evolution safety

  • readme
  • security-auditor

    Security reviewer that checks for OWASP top 10 vulnerabilities and hardcoded secrets

  • spec-challenger

    Adversarial spec reviewer that challenges assumptions with cited evidence. Anti-sycophancy by mandate. Counterweight to optimistic-by-default LLM behaviour.

  • spec-validator

    Read-only structural validator for spec/plan/tasks. Coverage matrix, constitution gates, path validity, checklist pass rate. Deterministic.

  • test-automator

    Test strategy agent that identifies coverage gaps and validates test quality

Hooks (13)

  • SessionStart

    ${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/block-main-branch-commit-push.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/commit-msg-check.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/block-unsafe-bash.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/block-destructive-git.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/require-explicit-staging.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/block-unsafe-sql.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/protect-files.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/detect-secrets.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/protect-infrastructure.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/detect-secrets.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/warn-large-diff.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/detect-ai-test-shortcuts.sh

View source on GitHub

More from Triippz/ai-jesus-team

All 2 plugins →

NUVCard SaaS development: Deno, Hono, HTMX, TypeScript

hooks

1

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows

18 skills

MiniMax-AI/skills 13,828

worktrunk

claudecodex

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.

2 skills · hooks

max-sixty/worktrunk 12,481

Maintain core-superpowers?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins2 plugins