Combined workflow skills for software engineering and knowledge work — disciplined task routing, TDD enforcement, safety hooks, systematic debugging, brainstorming, planning, and 28 expert workflows.
Use this agent to review completed implementation work against requirements, correctness, and production readiness.
Use this agent to adversarially attack completed implementation work — find concrete ways to break the code through specific inputs, state sequences, race conditions, assumption violations, and production context mismatches that checklist-based review would miss.
MUST USE when the user wants new features, behavior changes, new projects, documents, decisions, plans, or any work where no approved design exists yet. Produces an approved design before any implementation or production begins. Triggers on: "build this", "create", "write", "plan", "decide", "design", "I want to", "help me", "we need to". Routed by using-austinpowers, or invoke directly via /brainstorming.
Creates minimal, high-signal context files for any project. For software: CLAUDE.md and AGENTS.md based on empirical best practices. For knowledge-work: PROJECT.md or CONTEXT.md that gives collaborators (human or AI) the minimum context needed to contribute correctly. Invoke on /init command, "create CLAUDE.md", "set up project context", "write an onboarding doc", or when a project lacks a context file for new contributors. tools: Read, Glob, Grep, Bash, Edit
Use in long or noisy sessions to persist durable state across session boundaries via state.md. Also generates project-map.md when asked to map the project. Triggers on: user explicitly asks to "save state", "compress context", "map this project", "generate project map", "create project map", cross-session handoff needed, or repeated failures indicate context is getting stale.
Use BEFORE brainstorming when facing a complex architectural, technology, or design decision where the options are not yet well-defined or the problem itself may need reframing. Assembles named stakeholder perspectives that each speak once without debate, then surfaces where they converge and where real tension remains — without forcing a premature choice. Triggers on: "should we use X or Y", "not sure which approach", "evaluate these options", "what are the trade-offs between", "help me think through this decision", "architecture decision", "technology choice". Routed by using-austinpowers before brainstorming when the decision space is unclear.
MUST USE when updating, migrating, or auditing project dependencies: upgrading packages, fixing security vulnerabilities (CVEs), resolving breaking changes, migrating to new major versions, or auditing outdated dependencies. Enforces incremental updates with verification at each step. Distinct from systematic-debugging (which fixes application bugs) and refactoring (which restructures application code). Triggers on: "update dependencies", "upgrade packages", "npm update", "pip upgrade", "outdated", "vulnerability", "CVE", "security advisory", "breaking change", "migration guide", "dependency conflict", "peer dependency", "update to latest", "audit dependencies", "npm audit", "dependabot". Routed by using-austinpowers, or invoke directly via /dependency-management.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
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 power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
A combined workflow plugin for Claude Code that covers both software engineering and knowledge work. It merges superpowers-optimized (engineering workflows) with normalpowers (knowledge-work workflows) into one coherent plugin — yeah, baby.
austinpowers gives Claude Code a disciplined workflow for any type of task:
The plugin automatically routes tasks to the right workflow via the task-routing skill.
The plugin marketplace is bundled in this repo. Add it once, then install:
/plugin marketplace add DaltonWorsnup/austinpowers
/plugin install austinpowers@austinpowers
Or clone and install locally:
git clone https://github.com/DaltonWorsnup/austinpowers
/plugin install ./austinpowers
Every session starts with using-austinpowers loaded automatically via the SessionStart hook. The skill:
task-routing.For software tasks, the pipeline mirrors superpowers-optimized: brainstorm → plan → execute (subagent-driven) → verify → finish work unit.
For knowledge-work tasks, the pipeline mirrors normalpowers: brainstorm → write-plans → follow-your-plan → verify → finish work unit.
| Skill | Purpose |
|---|---|
using-austinpowers | Entry router for all tasks |
task-routing | Classifies tasks as software / knowledge-work / hybrid |
token-efficiency | Always-on: concise responses, parallel tool calls, context hygiene |
brainstorming | Design approval before any work begins |
writing-plans | Decompose approved designs into executable task plans |
verification-before-completion | Evidence required before any completion claim |
receiving-feedback | Handle review feedback or stakeholder pushback with rigor |
premise-check | Validate that the work is worth doing before designing |
deliberation | Surface competing perspectives before brainstorming |
context-management | Cross-session state: project-map, session-log, state.md |
error-recovery | Track known error→solution mappings |
writing-skills | Author new skills for your own domain |
self-consistency-reasoner | Multi-path majority-vote reasoning for high-stakes inference (internal) |
These skills were written for software engineering but apply equally to knowledge-work. subagent-driven-development and dispatching-parallel-agents handle parallel execution for any output type; finishing-a-work-unit covers publishing/merging/archiving for any deliverable; using-git-worktrees covers both branch isolation and document draft isolation; claude-md-creator creates context files for both software repos and knowledge-work projects.
| Skill | Purpose |
|---|---|
subagent-driven-development | Parallel subagents with staged compliance + quality review gates |
dispatching-parallel-agents | Independent concurrent tasks (code, research, analysis) |
finishing-a-work-unit | Merge / publish / archive / discard decisions for any deliverable |
using-git-worktrees | Isolated branch development (software) and draft isolation (knowledge-work) |
claude-md-creator | Initialize CLAUDE.md / AGENTS.md (software) or CONTEXT.md / PROJECT.md (knowledge-work) |
| Skill | Purpose |
|---|---|
executing-plans | Execute code plans with verification checkpoints |
test-driven-development | RED → GREEN → REFACTOR cycle |
systematic-debugging | Root cause investigation for code failures |
requesting-code-review | Multi-phase code review with security checklist |
refactoring | Behavior-locked incremental restructuring |
frontend-design | Production-grade UI with Tailwind v4, accessibility |
performance-investigation | Profile → identify → fix → re-measure |
dependency-management | Incremental dependency updates with verification |
| Skill | Purpose |
|---|---|
following-your-plan | Execute knowledge-work plans with explicit deviation tracking |
systematic-problem-solving | Root cause investigation for org/process problems |
npx claudepluginhub daltonworsnup/austinpowers --plugin austinpowersHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.