By asktinnguyen
100+ skills, 44 commands, and 6 workflows for AI-powered development. Multi-agent orchestration, code review, video production, browser automation, Unreal tooling, and more.
Run comprehensive agent-native architecture review with scored principles
Brand profiles - list, edit, or create new
Create engaging changelogs for recent merges to main branch
Share improvements - issues, PRs, skills, templates
Create or edit Claude Code skills with expert guidance on structure and best practices
You are **Jeff**, an AI coding coach based on Jeffrey Emanuel's (@doodlestein) methodology for AI-assisted software development.
- **Name:** Jeff
Ready-to-use agents you can install on any OpenClaw instance.
**Planning is not overhead.** It's the actual work. The 30,000-word plan *is* the product. Code is just the compilation step.
You are **Jeff**, an AI coding coach based on Jeffrey Emanuel's (@doodlestein) methodology for AI-assisted software development.
Uses power tools
Uses Bash, Write, or Edit tools
Runs pre-commands
Contains inline bash commands via ! syntax
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.
A curated collection of skills, commands, and workflows for Claude Code.
/plugin marketplace add https://github.com/AskTinNguyen/vesper-team-skills
/plugin install vesper-team-skills
That's it. All skills and commands are now available in your Claude Code sessions.
This repo now also vendors the full addyosmani/agent-skills lifecycle pack and keeps it available as first-class skills inside vesper-team-skills.
Imported upstream skills:
using-agent-skillsspec-driven-developmentplanning-and-task-breakdownincremental-implementationtest-driven-developmentcode-review-and-qualitydebugging-and-error-recoverycontext-engineeringapi-and-interface-designfrontend-ui-engineeringsecurity-and-hardeningperformance-optimizationcode-simplificationgit-workflow-and-versioningci-cd-and-automationdocumentation-and-adrsshipping-and-launchdeprecation-and-migrationbrowser-testing-with-devtoolsidea-refineRefresh from upstream:
./scripts/import-agent-skills --source ~/agent-skills/skills
This refreshes the imported skill directories in this repo and re-links them into common local skill roots:
~/.vesper/skills~/.claude/skills~/.codex/skillsUpstream provenance and license are kept in third_party/agent-skills/.
| Skill | Description |
|---|---|
| dispatch | Coordinate complex features with parallel subagent execution |
| agent-supervisor | Monitor task lists, detect gaps, and track agent status without doing implementation |
| github-sync | Synchronize GitHub PRs and issues into the Claude Code task list |
| ralph-loop | Trigger and manage Ralph Loop autonomous coding workflows |
| Skill | Description |
|---|---|
| code-review-expert | Expert code review with a senior engineer lens — SOLID violations, security risks |
| code-simplifier | Simplify and refine code for clarity and maintainability |
| code-quality-hook | PostToolUse hook that checks code quality after Edit/Write operations |
| tdd-failing-tests-loop | Drive contract-first refactors with strict failing-tests-first TDD |
| reducing-entropy | Minimize total codebase size — biases toward deletion |
| verify-and-ship | Verify agent work output, commit, push, and create PRs |
| scheduled-codebase-review | Periodic deep reviews of the entire codebase using multi-agent analysis |
| Skill | Description |
|---|---|
| ship-notes | Generate release notes from recent git activity |
| last7days | Review the last 7 days of activity in a git repository |
| agent-changelog | Compile an agent-optimized changelog from git history |
| compound-docs | Capture solved problems as categorized documentation |
| feature-specification | Write comprehensive feature specifications for product and engineering |
| Skill | Description |
|---|---|
| claude-md-improver | Audit and improve CLAUDE.md files in repositories |
| claudemd-reviewer | Review and analyze CLAUDE.md hierarchy in repositories |
| create-agent-skills | Expert guidance for creating and refining Claude Code skills |
| skill-creator | Guide for creating effective skills |
| skill-enricher | Cross-reference a skill with its source repo to fill gaps |
| skill-qa-release-guardian | Automated release QA with UI testing, regression verification, and bug reporting |
| claude-code-hooks | Implement pre-hooks and post-hooks for Claude Code |
| Skill | Description |
|---|---|
| remotion | Create programmatic videos using React with Remotion |
| launchpad-remotion | Reusable components and brand assets for the trycua/launchpad Remotion monorepo |
| ffmpeg | Video and audio processing — format conversion, resizing, compression |
| playwright-recording | Record browser interactions as video using Playwright |
| gemini-imagegen | Generate and edit images using the Gemini API |
npx claudepluginhub asktinnguyen/vesper-team-skills --plugin vesper-team-skillsComprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Harness-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
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.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Complete developer toolkit for Claude Code