Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By edwinhu
Development, data science, writing, and workshop presentation workflows with TDD enforcement, output-first verification, agent team parallelization, and GSD-style deviation rules, test gap validation, and session handoff.
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
Use for EDA, data profiling, and dataset exploration
Systematic hypothesis-driven debugging agent. User = reporter, Claude = investigator. Don't ask what's causing the bug — investigate it yourself. Spawned by dev-debug workflow for each investigation cycle.
This skill should be used when reviewing AI-generated text, checking for AI writing patterns, detecting undisclosed AI content, or before finalizing any written content.
Canonical doctrine for scored iterative improvement, and the generic fallback for ad-hoc 'iteratively improve / audit and fix / grade and improve / hill-climb quality / score and fix' requests that don't map to a domain workflow.
This skill should be used when the user asks to 'audit footnotes', 'check Bluebook formatting', 'audit citations', 'run footnote audit', 'check my footnotes', 'bluebook audit', or needs systematic Bluebook compliance checking of a law review manuscript.
This skill should be used when the user asks to “cite a case”, “format a citation”, “check Bluebook format”, “cite a statute”, “use id. or supra”, “format footnotes”, “cite a law review article”, or needs Bluebook 21st Edition citation guidance.
Verify academic citations against source PDFs using Gemini File Search API. Use when 'check citations', 'verify cites', 'cite-check', 'run citation review', 'are my citations grounded', 'does source X support claim Y', 'what does source X say about Y', or validating that pandoc citations in markdown drafts are supported by their source documents.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Share bugs, ideas, or general feedback.
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
Share bugs, ideas, or general feedback.
A curated collection of development, data science, writing, workshop, legal, and research workflows for Claude Code.
# 1. Install the plugin
/plugin marketplace add edwinhu/workflows
# 2. (Optional) Install CLI dependencies for knowledge management, email, and calendar
bash ~/.claude/plugins/cache/edwinhu-plugins/workflows/*/bin/install-deps.sh
The core workflows (/dev, /ds, /writing, /workshop, document formats) work without any CLI dependencies. The install script is only needed for skills that use external tools.
This downloads pre-built binaries for your platform (macOS arm64, Linux x64, Windows x64) from GitHub Releases:
| Tool | Purpose | Used by |
|---|---|---|
| nlm | NotebookLM CLI | librarian agent, /nlm |
| readwise-custom | Readwise RAG/chat/upload | librarian agent, /readwise-chat |
| scholar | Google Scholar search | librarian agent, /google-scholar |
| consensus | Academic paper search | librarian agent, /consensus |
| morgen | Calendar & tasks | Direct Bash, or session in ~/areas/assistant/ |
| superhuman | email-handling skill (via Bash) |
Requires gh (GitHub CLI). Tools already on your $PATH are skipped.
These are the skills you invoke directly with /name:
Four primary workflows, each with a fresh-start entry and a midpoint re-entry:
| Start Fresh | Midpoint Re-entry | Domain |
|---|---|---|
/dev | /dev-debug | 7-phase feature development with TDD enforcement |
/ds | /ds-fix | 6-phase data science with output-first verification and DQ validation |
/writing | /writing-revise | 6-phase writing with claim validation and deviation rules |
/workshop | /workshop-revise | 4-phase workshop presentations from research papers |
| Skill | Purpose |
|---|---|
/docx | Word document creation, editing, tracked changes |
/pdf | PDF extraction, creation, form filling |
/pptx | Presentation creation and editing |
/xlsx | Spreadsheet creation and analysis |
Office format skills sourced from anthropics/skills via git submodule.
| Skill | Purpose |
|---|---|
/skill-creator | Skill creation with superpowers enforcement patterns |
/workflow-creator | Design structured multi-phase LLM workflows |
/headline-card | LWT-style headline cards for Typst presentations |
These skills have user-invocable: false — Claude loads them automatically when relevant. You don't call them directly.
bluebook, bluebook-audit, docx-footnotes, source-verify
wrds, lseg-data, gemini-batch
nlm, google-scholar, readwise, readwise-chat, readwise-search, readwise-docs, readwise-prune
consensus, research
marimo, jupytext, notebook-debug
look-at, visual-verify, visual-mockup, data-context, continuous-learning, pattern-capture, ai-anti-patterns, dev-tools, ds-tools, dev-worktree, obsidian-organize, pptx-render, audit-fix-loop, plugin-creator
Dev: dev-clarify, dev-explore, dev-design, dev-delegate, dev-implement, dev-tdd, dev-review, dev-verify, dev-handoff, dev-spec-reviewer, dev-plan-reviewer, dev-test, dev-test-* (cross-turn iteration uses Claude Code's built-in /goal)
DS: ds-plan, ds-delegate, ds-implement, ds-review, ds-validate, ds-verify, ds-handoff, ds-spec-reviewer, ds-plan-reviewer
Writing: writing-setup, writing-outline, writing-outline-reviewer, writing-precis-reviewer, writing-draft, writing-econ, writing-general, writing-legal, writing-review, writing-validate, writing-handoff
Workshop: (no internal phase skills — workshop and workshop-revise are both user-facing entry points)
Specialized subagents auto-discovered by Claude Code from agents/:
npx claudepluginhub edwinhu/workflows --plugin workflowsCore workflow engine - Execute workflow-as-markdown definitions with validation-driven completion
Agentic workflow mechanics: CLAUDE.md instruction quality and structured context handoff
Agentic engineering done right — 57 structured workflows, 17 specialist agent personas, persistent memory across sessions, integrated learning partner, and impeccable UI design system. Works with Claude Code, Windsurf, Cursor, Gemini CLI, OpenCode, and Codex.
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
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.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.