Runs enterprise AI architecture playbooks from AI Architects @ AI Engineer — AI architect role, agent platforms, voice agents, agent auth (CIAM), trusted inference, team structure, monetization, and product survival. Use when designing org-wide AI systems, agent platforms, or CIO-ready inference; or when the user says "AI architect", "enterprise agents", "CIAM for agents", "AI that pays", "build-operate divide".
Runs workflows to author, route, and scale agent skills — SKILL.md structure, description-driven discovery, progressive disclosure, and team distribution. Use when the user writes Cursor/Claude/Codex skills, replaces bloated rules files, or says "author skill", "skill.md", "skills at scale", "agent routing".
Runs checklists and workflows for designing, hardening, and operating agent harnesses — guardrails, verify steps, tool loops, durable sessions, eval, quotas, coding/deep-research/voice harnesses. Use when the user builds agent runtimes, asks what a harness is, scopes agent vs workflow, or says "agent harness", "guardrails", "verify step", "FOMAT", "durable session".
Runs workflows for AIEWF 2024 RAG talks — layout-aware ingest, GraphRAG, eval-driven tuning, Pydantic structured IO, MongoDB vectors, EMT memory, construction vertical agents, personal-assistant data graphs. Use when the user says "RAG", "GraphRAG", "chunking PDF", "Pydantic RAG", or AIEWF retrieval playlist.
Builds and ships generative image/video products—FLUX, ComfyUI workflows, Veo, fal platforms, Luma-scale launches, and API-first creator UX. Use when working on diffusion pipelines, Comfy graphs, video models, generative media infra, or viral consumer media launches.
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, plugins, and tools that I use in my day-to-day workflow as a developer.
Built by @hiteshbandhu — open for anyone to use, fork, or build on.
npx skillsInstall skills into Cursor (and 50+ other agents) using the Agent Skills CLI (skills.sh):
# List installable skills from this repo
npx skills add hiteshbandhu/skills-i-use --list
# Install one skill into the current project
npx skills add hiteshbandhu/skills-i-use --skill ship-check
# Install globally (available across all projects)
npx skills add hiteshbandhu/skills-i-use --skill ship-check -g
# Target Cursor explicitly
npx skills add hiteshbandhu/skills-i-use --skill ship-check -a cursor
# Search the public skills directory
npx skills find ship check
The CLI discovers 39 skills — five core skills under skills/ plus 34 in the ai-engineer-talks bundle (via .claude-plugin/marketplace.json):
# List all skills (core + ai-engineer-talks, grouped in output)
npx skills add hiteshbandhu/skills-i-use --list
# Install an AI engineer talks skill
npx skills add hiteshbandhu/skills-i-use --skill build-rag-search-stacks -a cursor
| Skill | Install |
|---|---|
architecture-review | npx skills add hiteshbandhu/skills-i-use --skill architecture-review |
create-a-skill | npx skills add hiteshbandhu/skills-i-use --skill create-a-skill |
cto-weekly-review | npx skills add hiteshbandhu/skills-i-use --skill cto-weekly-review |
ship-check | npx skills add hiteshbandhu/skills-i-use --skill ship-check |
ui-ux | npx skills add hiteshbandhu/skills-i-use --skill ui-ux |
Full index of the ai-engineer-talks bundle: skills/ai-engineer-talks/README.md.
After install, invoke a skill with @skill-name in chat or /skill-name in Agent mode.
| Folder | What it contains |
|---|---|
skills/ | Reusable skill definitions and workflow prompts for AI agents |
plugins/ | Integrations, MCP servers, and tool extensions (coming soon) |
examples/ | Working configs and usage walkthroughs (coming soon) |
Skill definitions that extend AI agents with specialised workflows. Each skill writes
output to ./skill-outputs/{skill-name}/ in your project (configurable via
SKILL_OUTPUT_DIR). See skills/OUTPUT.md.
| Skill | What it does |
|---|---|
architecture-review | Structured ADR process — subagent persona debate, markdown ADR, optional HTML, decision registry. |
cto-weekly-review | Deep weekly engineering report — parallel data collectors, markdown + HTML, links ADRs from architecture-review. Includes scripts. |
ship-check | Pre-ship gate — lint, typecheck, tests, build, diff review, commit message draft. Never commits without confirmation. Includes scripts. |
ui-ux | Product-aware UI/UX review and polish — Playwright verification, principles, checklist audits. |
create-a-skill | Author or improve repo skills — hard questions, reviewer subagents, validate, register. Includes scripts. |
Three skills ship shell scripts under scripts/. Always read a script before running it — review paths, env vars, and side effects. Do not run blindly.
| Skill | Scripts | What they touch |
|---|---|---|
cto-weekly-review | collect-git.sh, collect-ai-sessions.sh, collect-context.sh | Git repos, AI session logs, shell history, file timestamps, optional gh |
ship-check | ship-check.sh | Project lint/typecheck/test/build commands, git status/diff |
create-a-skill | validate-skill.sh | Skill folder structure and conventions (read-only checks) |
Each scripted skill documents its scripts in its README. When an agent proposes running one, double-check the command first.
34 skills from ingest-into-skills — full index in skills/ai-engineer-talks/README.md.
Topics include RAG, evals, agents, harnesses, OpenAI/DeepMind/Microsoft, AIEWF 2024 tracks, Summit 2023, Europe 2026 keynotes, security, legal AI, OpenClaw, PM/leadership, inference, robotics, generative media, skills/MCP, and more.
From ingest-into-skills; create-a-skill hygiene before sync.
npx claudepluginhub hiteshbandhu/skills-i-use --plugin ai-engineer-talksCore workflow skills — architecture review, ship checks, UI/UX, CTO reports, and skill authoring
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.