By leehanchung
Personal agent skills for writing, coaching, and technical strategy. Includes ML paper writing, copy editing, executive coaching, O'Reilly Radar analysis, Manning book authoring, and data/AI strategy frameworks.
Reviews ML/AI research papers for clarity, rigor, and conference readiness. Use when reviewing a draft paper before submission.
Advises on data/AI/ML technical strategy, engineering principles, and organizational design. Use when thinking through strategy documents, roadmaps, or org-level technical decisions.
Coaches on writing quality across all content types — papers, books, blog posts, strategy docs. Use when the user wants feedback on their writing rather than a direct edit.
Use when copy editing, proofreading, polishing, or removing AI-sounding prose.
Use when creating Data/AI strategy, principles, roadmaps, MLOps plans, or executive docs.
Use when coaching technical leaders on conflict, burnout, cofounders, CTO transitions, or growth.
Use when writing Manning-style technical chapters, Chapter 1s, examples, callouts, or summaries.
Use when drafting ML/AI papers, verifying citations, framing evidence, using LaTeX, or preparing submissions.
Uses power tools
Uses Bash, Write, or Edit tools
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.
Personal agent plugin monorepo — one set of skills, three platforms.
Works as a native plugin on Claude Code, OpenAI Codex, and Cursor without any build step. Each platform reads its own manifest and discovers the shared plugins/hstack/skills/ directory.
| Skill | Description |
|---|---|
copy-editing | Professional copy editing, grammar, style guide, AI writing pattern detection, and verbosity diagnosis |
data-ai-tech-strategy | Tech strategy and engineering principles for Data/AI/ML organizations |
executive-coaching | Executive coaching frameworks: GROW model, NVC, active listening, burnout prevention, co-founder dynamics, CTO transition |
manning-tech-book-writing | Manning Publications style, chapter structure, and writing standards |
ml-paper-writing | Publication-ready ML/AI research papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM — full writing process, citation verification, LaTeX, conference checklists |
tech-writing | Strategic tech blog posts and industry analysis — short-form (800-1,500 words) and long-form (2,000-4,000 words) with concision rules and AI pattern avoidance |
hstack/
├── .claude-plugin/
│ └── marketplace.json # Claude Code marketplace catalog
├── .cursor-plugin/
│ └── plugin.json # Cursor manifest
├── .agents/plugins/
│ └── marketplace.json # OpenAI Codex marketplace catalog
├── plugins/hstack/ # Shared plugin payload
│ ├── .claude-plugin/
│ │ └── plugin.json # Claude Code manifest
│ ├── .codex-plugin/
│ │ └── plugin.json # OpenAI Codex manifest
│ ├── skills/ # Shared skills
│ │ └── <skill-name>/
│ │ ├── SKILL.md # Entry point with frontmatter
│ │ └── references/ # Supporting materials
│ ├── agents/ # Custom agent definitions
│ └── commands/ # Slash commands
├── rules/ # Cursor .mdc rules (auto-attach by file type)
│ └── <skill-name>.mdc
├── LICENSE
└── README.md
| Platform | Manifest | Skills | Extras |
|---|---|---|---|
| Claude Code | .claude-plugin/marketplace.json -> plugins/hstack/.claude-plugin/plugin.json | plugins/hstack/skills/*/SKILL.md | plugins/hstack/agents/, plugins/hstack/commands/ |
| OpenAI Codex | .agents/plugins/marketplace.json -> plugins/hstack/.codex-plugin/plugin.json | plugins/hstack/skills/*/SKILL.md | interface branding |
| Cursor | .cursor-plugin/plugin.json | plugins/hstack/skills/*/SKILL.md | rules/*.mdc with glob triggers |
All three platforms use the same SKILL.md frontmatter format:
---
name: skill-name
description: When and how to use this skill
allowed-tools: "Read,Write,Edit,Bash,Glob,Grep,WebSearch,WebFetch"
---
name + description — required by all platformsallowed-tools — used by Codex to scope tool access; ignored by Claude and Cursorclaude plugin marketplace add leehanchung/hstack
claude plugin install hstack
# Skills appear as /hstack:skill-name
For local testing from a checkout:
claude plugin marketplace add /path/to/hstack --scope local
claude plugin install hstack --scope local
For one-off session testing without installing:
claude --plugin-dir /path/to/hstack/plugins/hstack
codex plugin marketplace add leehanchung/hstack
For local testing from a checkout:
codex plugin marketplace add /path/to/hstack
In the Codex app, add the GitHub marketplace source leehanchung/hstack, then enable the HStack plugin. Codex reads .agents/plugins/marketplace.json, resolves ./plugins/hstack, and loads plugins/hstack/.codex-plugin/plugin.json.
Symlink or copy into your Cursor plugins directory. Rules in rules/ auto-attach to matching file types (e.g., .tex files trigger ml-paper-writing).
plugins/hstack/skills/<skill-name>/SKILL.md with frontmatterplugins/hstack/skills/<skill-name>/references/rules/<skill-name>.mdc for Cursor glob-based auto-attachmentMIT
npx claudepluginhub leehanchung/hstack --plugin hstackAdvisory PR code review scoped to the SMILE-factory monorepo. Approve-or-comment only (never request-changes), submits one formal review via `gh pr review --body-file`.
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.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
TypeScript/JavaScript full-stack development with NestJS, React, and React Native