hiteshbandhu

@hiteshbandhu source repo

48 skills
0 followers
22 hours ago last updated

▌
UI UX · hiteshbandhu bundle
UI/UX and product review for web interfaces — opinionated principles, checklist-driven audits, polish passes on screenshots, and pre-ship UI gates. Uses Playwright to navigate, screenshot, and smoke-test interactions when a URL is available. Triggers on "review my UI", "polish this", "UX audit", "fix the hero", "make it look professional", "ui pass", "design review", attaches screenshot with UI feedback. Use when building or reviewing interfaces and product flows, not generic code review.

0
installs
▌
Raise Pr · hiteshbandhu bundle
Take a ready change from working tree to merged PR — branch, commit, push, open PR with a body drafted from the diff, watch CI, and squash-merge when green. General and portable: follows each repo's own commit/branch convention rather than imposing one. Never commits, pushes, or merges without explicit confirmation. Triggers on "raise a PR", "open a PR", "pr this", "push and pr", "ship this PR", "merge when green", "commit and open a pr".

0
installs
▌
PDF Report · hiteshbandhu bundle
Produce a client-ready PDF — proposal, audit, brief, one-pager — by authoring HTML/CSS and rendering with headless Chrome. Covers the print-CSS traps that silently clip content, inline SVG diagrams that survive print, hitting an exact page count, and the evidence discipline that keeps a client document defensible. Triggers on "make a PDF", "client proposal", "audit report", "one-pager", "deck for the client", "print this", "turn this into a document", "5 page report", "professional report". Use when the deliverable leaves your team — a document a client, board or admin reads. Not for READMEs, internal notes, or web pages that stay on screen.

0
installs
▌
Ship Check · hiteshbandhu bundle
Pre-ship gate before commit or push — runs lint, typecheck, tests, build, secret scan, and git diff review, then outputs a READY/BLOCKED verdict with a proposed commit message. Never commits without explicit user confirmation. Triggers on "ship check", "ready to commit", "pre-push check", "commit and push", "ship this", "can I push".

0
installs
▌
Create A Skill · hiteshbandhu bundle
Interview, stress-test, and author new skills for the skills-i-use repo — or improve existing ones. Asks hard questions, runs reviewer subagents, writes design briefs, generates SKILL.md and supporting files, validates conventions, and registers in README and OUTPUT.md. Triggers on "create a skill", "new skill", "add a skill", "improve this skill", "author a skill", "skill for X workflow", "build a skill".

0
installs
▌
Friction Audit · hiteshbandhu bundle
Audit a product flow for friction — every point where the system makes the user do work it could do itself — then design the automatic path for each. Classifies friction (ask-for-permission, re-do/re-send, manual recovery, re-discovery, dead-end, redundant confirmation), decides what should become automatic with a safety carve-out for destructive/irreversible/cross-user actions, and names the tradeoff. Triggers on "audit this flow", "where's the friction", "why does the user have to", "make this automatic", "remove the friction", "this has too much friction", "it should just happen", "reduce steps", "the user shouldn't need to". Use when reviewing a UX flow, agent loop, or feature for needless user effort — not for visual/styling review (use ui-ux for that).

0
installs
▌
Cto Weekly Review · hiteshbandhu bundle
Generate a deep CTO self-review report: working hours, productivity patterns, focus sessions, AI collaboration depth, cognitive load signals, sustainability health, and codebase velocity — not just commit counts. Triggers on "weekly review", "CTO report", "week summary", "what did I build", "productivity report", "show me my week", "engineer report", "weekly digest". Scans git across repos, AI agent session logs, shell history, file timestamps, and produces markdown + HTML reports. Always trigger this skill for any weekly or periodic review of engineering or product work.

0
installs
▌
Chat Failure Audit · hiteshbandhu bundle
Audit a real user transcript or agent session for failure modes — extract what went wrong, map each symptom to its root cause and the system layer that owns it, and rank by frequency × severity. Distinguishes symptom from cause (e.g. "it worked on the next turn" → root cause is activation not happening in-turn, not "the model is bad") and classifies each failure (capability gap, friction, state/lifetime bug, grounding/ confabulation, recovery gap, UX dead-end). Triggers on "analyse this chat", "what went wrong here", "audit this session", "why did the agent fail", "find the failure modes", "look at this transcript", "where did this break", "review this conversation". Use when you have a real session/log and want grounded failure analysis, not guesses.

0
installs
▌
Cross Model Review · hiteshbandhu bundle
Review a PR or working diff twice — once with the primary model, then again with a different vendor's model that is told nothing about the first pass — then verify the second model's claims against real code and reconcile both into one ranked review. Catches the class of bug a single model is systematically blind to. Triggers on "cross-model review", "second opinion on this PR", "review this with another model", "double-check this review", "have another model look at it", "blind review". Use when being wrong is expensive: unfamiliar code, an outside contributor's PR, or anything touching auth, money, migrations, or data loss.

0
installs
▌
Verify Like A User · hiteshbandhu bundle
Build and check UI the way a person meets it — measure the rendered page instead of trusting the source, break it on purpose at several widths and along the paths people actually take, fix the root cause, and re-measure before calling it done. Carries a catalogue of UI failures that survive code review (clipped borders, dropped size classes, dead ends on short screens, stale caches, redirects that never move the URL) with symptom → cause → fix. Triggers on "verify this UI", "does this look right", "check it at other widths", "it looks bad, fix it", "break the product", "make these pages consistent", "why is this clipped / overflowing / huge / not clickable", "audit every page in this section", and any screenshot sent with "fix this".

0
installs
▌
Architecture Review · hiteshbandhu bundle
Run a structured architecture decision process using subagent personas that debate the decision, then produce a signed ADR (markdown + optional HTML) and update a decision registry. Triggers on "should I use X or Y", "architecture decision", "ADR", "help me decide between", "which approach", "debate this", "tech decision". Use whenever the user is making a technical or architectural choice and needs structured thinking, not just a list of tradeoffs.

0
installs
▌
Spec Grounded Design · hiteshbandhu bundle
Before implementing against any protocol, SDK, or external API, ground the design in reality — pull the actual spec, probe the live endpoint to capture how it really behaves, reconcile spec-vs-reality (reality wins), and extract a design contract of verified facts, edge cases, and invariants to build against. Encodes "read the protocol" + "test live before assuming the spec is correct," because reverse-engineered or stale docs lag the real API. Triggers on "integrate with X", "design against this API", "read the protocol first", "before we build this integration", "is the spec right", "how does this API actually behave", "ground this in the docs", "verify before coding". Use before writing integration code against an external system, not for internal logic.

0
installs
▌
State Lifetime Decision · hiteshbandhu bundle
Decide the right home for a new piece of state — its scope (turn, step, chat/thread, user-session, user, org, global) and its durability (ephemeral, TTL'd, durable, log) — as an explicit product-and-systems decision rather than a default. Forces the cross-cutting checks that get missed: per-user/tenant isolation, staleness and invalidation, growth/bloat bounds, and the cache implication. Triggers on "where should this live", "how long should we keep this", "should this persist", "what's the scope of this state", "cache or db or redis", "per chat or per user", "ttl for this", "session vs chat scope", "should we remember this". Use when adding or changing stored/remembered state in an app or agent — before picking a store.

0
installs
▌
Run LLM Evals · hiteshbandhu bundle
Runs checklists and workflows for designing, operating, and improving LLM evals — domain harnesses, agent/voice evals, LLM judges, metrics workshops, product flywheels, dynamic search eval, enterprise conversation intelligence. Use when the user says "evals", "LLM judge", "eval harness", "regression on prompts", "agent eval", "eval dataset", or needs to ship with measurement before prod.

0
installs
▌
Ship AI As Pm · hiteshbandhu bundle
Runs PM workflows from World's Fair talks — AI PM role, knife-fight strategy, ship-to-user focus, uncertain capabilities, expert systems, domain experts, agent coordination platforms, post-engineer orgs, taste-led UX. Use when the user is an AI PM, founder, or shipping AI product strategy.

0
installs
▌
Scroll Engineering · hiteshbandhu bundle
Audit a streaming chat UI against the 15-point scroll engineering checklist — every principle about reader intent, viewport control, layout stability, and accessibility. Classifies each point as passing, failing, or not applicable, then ranks the top fixes by user impact. Triggers on "audit my scroll behavior", "check auto-scroll", "streaming chat UX review", "scroll engineering", "jump to latest", "reader intent", "chat viewport issues", "streaming layout shifts". Use when reviewing or building a streaming chat interface — not for general UI review (use ui-ux for that). Credit: principles by @shadcn (https://x.com/shadcn/status/2070394918720221522).

0
installs
▌
Secure AI Agents · hiteshbandhu bundle
Security workflows for AI agents: OAuth/MCP identity, enterprise CIAM, tool/API red teaming, code sandboxes, GenAI fuzzing, Azure PyRIT scans, prompt injection drills, web AI bot policy, confidential inference patterns. Use when hardening agents, MCP servers, coding agents, or public apps against agent abuse.

0
installs
▌
Build Robotics AI · hiteshbandhu bundle
Runs workflows for robotics/autonomy talks — lab co-scientist loops, Optimus systems latency, kitchen supervised autonomy, Waymo EMMA, GR00T N1 humanoid FM, open $9k humanoids. Use when the user builds robots, humanoids, AV planning, or lab automation agents.

0
installs
▌
Build With Openai · hiteshbandhu bundle
Runs OpenAI API workflows for agents, function calling, voice/Realtime, fine-tuning (SFT/DPO/RFT), sandboxes, Codex coding agents, and multimodal products. Use when building with OpenAI Agents SDK, Realtime API, tool loops, enterprise agent rollout, microVM sandboxes, or GPT-4o vision/voice.

0
installs
▌
Plan Sovereign AI · hiteshbandhu bundle
Runs checklists for sovereign AI planning — four control pillars, retrofit failure modes, guardrailed agent architecture, and sovereignty acceptance tests. Use when the user must meet GDPR, EU residency, on-prem, air-gap, model swap, or says "sovereign AI", "data sovereignty", "Cloud Act", "Haystack on-prem".

0
installs
▌
Price AI Products · hiteshbandhu bundle
Runs Stripe-style workflows for AI product pricing — value definition, charge metrics, hybrid models, billing guardrails, and fast iteration. Use when the user prices an AI feature, picks usage vs seats, designs credits, or says "AI pricing", "hybrid pricing", "margin risk", "price AI SaaS".

0
installs
▌
Train Llms Locally · hiteshbandhu bundle
Runs workflows to train a small LLM from scratch on a laptop — tokenizer, data, architecture, training loop, and nanochat-style hands-on paths. Use when the user wants local pre-training, learns fundamentals, or says "train LLM from scratch", "nanochat", "tokenizer", "pretraining loop".

0
installs
▌
Author Agent Skills · hiteshbandhu bundle
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".

0
installs
▌
Build With Deepmind · hiteshbandhu bundle
Builds products on Google DeepMind Gemini, Gemma, Nano, Live agents, proactive async agents, and edge deployment. Use when integrating Gemini API, Gemma open models, Android on-device AI, conversational/voice agents, agent manager patterns, or edge Gemma inference.

0
installs
▌
Design Agent Skills · hiteshbandhu bundle
Runs workflows for authoring agent skills — SKILL.md structure, MCP pairing, Langfuse lessons, progressive disclosure, validation. Use when the user writes skills, combines MCP+skills, or says "agent skills", "SKILL.md", "context gap".

0
installs
▌
Build Aiewf 2024 RAG · hiteshbandhu bundle
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.

0
installs
▌
Operate Agent Memory · hiteshbandhu bundle
Runs checklists and workflows for agent context engineering — separating context from memory, smart truncation, sub-agent offload, and long-session evals. Use when the user hits context limits on observability or trace-heavy agents, designs multi-turn memory, or says "context management", "escape context window", "agent forgets follow-ups".

0
installs
▌
Run Aiewf 2024 Evals · hiteshbandhu bundle
Runs checklists for AIEWF 2024 eval and LLM ops talks — domain eval ladders, LLM judges, enterprise deploy, Zapier+Braintrust loops, GenAI maturity before fine-tune. Use when the user says "evals", "LLM judge", "fine-tune decision", "enterprise GenAI deploy", or AIEWF eval playlist.

0
installs
▌
Build Agent Harnesses · hiteshbandhu bundle
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".

0
installs
▌
Observe AI Production · hiteshbandhu bundle
Observes and improves production LLM apps with Arize Phoenix—tracing, layered agent evals, prompt learning loops, and PM/engineering eval pipelines. Use when the user mentions Arize, Phoenix, OpenInference, agent router evals, prompt optimization from traces, or shipping AI with production observability.

0
installs
▌
Build Generative Media · hiteshbandhu bundle
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.

0
installs
▌
Lead AI Transformation · hiteshbandhu bundle
Leads enterprise AI transformation—platform engineering, hiring AI teams, ROI via eval frameworks, values-based investment review, and safe adoption patterns. Use when a VP/Director plans AI platform teams, enterprise LLM ROI, hiring, or governance at AI Engineer World's Fair 2024 leadership sessions.

0
installs
▌
Optimize LLM Inference · hiteshbandhu bundle
Runs workflows for GPU/inference talks — Groq LPU latency, OSS inference stacks, MoE networking, serverless fine-tune, frontier cluster design, Devin agent infra, Gemma sizing. Use when optimizing inference $/token, training networks, or picking open models.

0
installs
▌
Ship Aiewf 2024 Agents · hiteshbandhu bundle
Runs workflows for AIEWF 2024 agent talks — Vertex governance, Minecraft JSON actions, voice pipelines, agentic commerce, personas, CrewAI dogfooding, job automation realism. Use when shipping agents, voice agents, or agent marketplaces.

0
installs
▌
Architect Enterprise AI · hiteshbandhu bundle
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".

0
installs
▌
Build RAG Search Stacks · hiteshbandhu bundle
Runs checklists and workflows for designing, layering, evaluating, and operating production RAG and AI search — hybrid retrieval, agentic context tools, enterprise eval, web neural search, managed platforms, document agents. Use when the user builds retrieval for agents, picks vector vs lexical vs hybrid, designs eval for augmented AI, scales regulated RAG, compares search APIs, or says "RAG stack", "hybrid search", "agentic RAG", "vector benchmark".

0
installs
▌
Build With Microsoft AI · hiteshbandhu bundle
Runs workflows for Microsoft agent stacks — agent observability gaps, eval-driven alignment, and local vs background vs cloud agents in VS Code/Copilot. Use when the user builds on Azure Foundry, GitHub Copilot agents, agent evals, or says "mind the gap observability", "Copilot worktrees", "background agent".

0
installs
▌
Deploy Public Sector AI · hiteshbandhu bundle
Runs workflows for delivering AI inside government — insurgent central teams, forward-deployed engineers, fast in-building wins, department partnerships, and safety/red-team for policy tools. Use when the user works on govtech, civic platforms, public-sector embeds, or says "rewiring the state", "government AI", "No. 10", "FDE in government".

0
installs
▌
Learn Summit 2023 Talks · hiteshbandhu bundle
Applies AI Engineer Summit 2023 main-stage playbooks for RAG, agents, interfaces, local LLMs, fine-tuning, product velocity, TypeChat/Pydantic, LangChain observability, and the discipline of AI engineering (Swyx, Willison). Use when grounding team practice in summit talks, shipping RAG/agents, or onboarding to AI engineering; or when the user says "summit 2023 talks", "1000x AI engineer", "production RAG Jerry Liu", "open questions Willison".

0
installs
▌
Operate Legal AI Agents · hiteshbandhu bundle
Runs checklists for legal and vertical AI agents — artifact-first UX, tabular review, skills at work nodes, verifier's-rule task mapping, guardrails, decision logs, and human control vs trust. Use when building law-firm agents, contract workflows, Legora-style workspaces, or escaping chat-only legal copilots.

0
installs
▌
Operate Openclaw Agents · hiteshbandhu bundle
Runs checklists and workflows for deploying, securing, scaling, and evaluating OpenClaw agents — personal incremental setup, enterprise containers, Kubernetes, maintainer PR triage, malleable evals, local vs cloud, team Slack agents. Use when the user deploys OpenClaw, hardens a rollout, designs agent evals, sets up a personal agent, compares Viktor-style Slack agents vs OpenClaw, or says "OpenClaw K8s", "OpenClaw security", "agent eval harness".

0
installs
▌
Evaluate With Braintrust · hiteshbandhu bundle
Evaluates LLM and agent products with Braintrust—offline/online evals, SDK/CI workflows, eval platform design, Zapier/Notion product ops, and Loop-style optimization. Use when the user mentions Braintrust, eval playground, autoevals, production log evals, or agent quality platforms.

0
installs
▌
Learn Summit 2023 Remote · hiteshbandhu bundle
Applies AI Engineer Summit 2023 remote-talk playbooks for evals, hybrid RAG grounding, model selection, fine-tuning, prompt ops, multimodal apps, coding-agent maturity, and career transition from fullstack. Use when reproducing summit remote lessons, comparing LLM eval tools, or scoping hybrid retrieval; or when the user says "summit 2023 remote", "llmeval", "hybrid context query", "AI maturity model".

0
installs
▌
Navigate Aie Europe 2026 · hiteshbandhu bundle
Navigates AI Engineer Europe 2026 keynote themes — MCP and skills, agent orchestration, code mode, application layer shifts, judgment vs automation, replacing large codebases with skills, and platform talks (Vercel, Cloudflare, Anthropic, Cursor, OpenClaw). Use when planning 2026 agent architecture, MCP adoption, or skill-first development; or when the user says "AIE Europe 2026", "future of MCP", "code mode", "end of apps", "12k LOC skill".

0
installs
▌
Build Multimodal Products · hiteshbandhu bundle
Runs workflows for multimodal AI products — realtime voice latency, tiny VLMs, SSM streams, unbounded UX design, dataset hierarchy, AI education. Use when the user builds voice bots, edge vision, multimodal UX, or says "multimodal product", "voice latency", "Moondream".

0
installs
▌
Lead AI Engineering Teams · hiteshbandhu bundle
Runs leadership workflows for AI-era engineering — context CDLC, org-wide AI adoption, agent-first throughput, and post-engineer team design. Use when the user leads eng org change, measures AI productivity, or says "double throughput", "context is the new code", "agents don't do standups", "AI SDLC rollout".

0
installs
▌
Run Summit 2023 Workshops · hiteshbandhu bundle
Runs AI Engineer Summit 2023 workshop playbooks — foundations (101), inference (201), product patterns beyond inference (Rest of the Owl), and Anthropic prompt engineering principles. Use when onboarding to AI engineering, designing inference stacks, or improving task prompts; or when the user says "summit 2023 workshop", "AI engineering 101", "inference workshop", "prompt principles Karina".

0
installs
▌
Navigate Aiewf 2024 Keynotes · hiteshbandhu bundle
Navigates AI Engineer World's Fair 2024 keynote themes—LLM product discipline, copilots, multimodal APIs, enterprise agents, local inference, realtime data, and platform second-order effects. Use when planning AIEWF takeaways, auditing LLM team practices, or choosing vendor/platform direction from 2024 keynotes.

0
installs

48 published skills