Skip to content
Claude Code · field guide · 2026
AI Skills on Claude Code

Every skill in Claude Code
— and how to actually use it.

Claude Code ships with far more than a chat box. Underneath are slash-commands, skills, subagents and multi-agent workflows that most people never switch on. This is the plain-English map: what each one does, how to trigger it, and one real example.

⌨️ Type / to fire a skill 🧠 Skills auto-trigger on intent 🤖 Subagents fan out work 🔁 Schedule & loop in the cloud
00

How skills actually work

Two ways to trigger anything in Claude Code — type it, or just describe what you want.

⌨️ Type a slash-command

Press / and a menu appears. Pick a skill (e.g. /code-review), optionally add arguments, and it runs in your current session.

Try/init  /review  /security-review

🧠 Just say what you want

Most skills auto-trigger on intent. You never type the name — you describe the outcome and Claude loads the right skill behind the scenes.

“make me a cinematic product video” → loads the cinematic video skill on its own.

📌 Memory & CLAUDE.md

Claude keeps a file-based memory and reads a CLAUDE.md in your repo for standing instructions — so preferences and project rules persist across sessions.

“remember I always want videos copied to Downloads” → saved as a fact, applied next time.

🛡️ Plan mode & permissions

Ask Claude to plan before touching files, and approve the plan first. Permission prompts gate risky actions until you allow them.

“plan this first, don’t edit yet” → read-only design pass, then your sign-off.
01

Core built-in commands

These ship with Claude Code itself — the everyday workhorses.

📄 /init

Scans your codebase and writes a CLAUDE.md documenting structure, commands and conventions so every future session starts smart.

Run/init
Best first command in any new repo.

🔍 /code-review

Reviews your current diff for real bugs plus reuse/simplification cleanups. Effort scales from low to ultra (a deep multi-agent cloud review).

Run/code-review high
Add --fix to apply findings, --comment to post them on a PR.

🔒 /security-review

Security audit of the pending changes on your branch — injection, auth, secrets, unsafe input handling.

Run/security-review
Run it before every push on anything user-facing.

/review

Reviews a full pull request end-to-end, not just the local diff.

Run/review 142
Hand it a PR number and get a structured verdict.

🧹 /simplify

Quality-only pass over changed code — reuse, simplification, efficiency, altitude — then applies the fixes. It won’t hunt for bugs (that’s code-review’s job).

Run/simplify
Great right after getting something working.

▶️ /run

Launches and drives your actual app so you can see a change working — CLI, server, browser app, whatever the project is.

Run/run
“start the app and screenshot the new screen.”

🧪 /verify

Confirms a change really does what it should by running the app and observing behaviour — not just trusting the tests.

Run/verify
“verify the fix on PR 88 actually works.”

📚 /learn

Captures and manages project “learnings” — durable notes Claude reuses so the same lesson isn’t re-learned every week.

Run/learn

⚙️ /update-config

Configures the harness via settings.json — permissions, env vars, and hooks (automated “whenever X, do Y” behaviours the harness runs for you).

Ask“allow npm commands” · “run the linter after every edit.”

⌨️ /keybindings-help

Customise keyboard shortcuts, rebind keys, add chord bindings.

Ask“rebind the submit key.”

🔕 /fewer-permission-prompts

Scans your history for safe, repeated commands and builds an allowlist so Claude stops asking permission for the harmless ones.

Run/fewer-permission-prompts

📘 claude-api

An always-accurate reference for the Claude API / Anthropic SDK — model IDs, pricing, tool-use, caching, token counting. Auto-loads whenever you build with Claude.

“which Claude model is cheapest for classification?”
02

Ship & release

From “it works on my machine” to a clean PR, deployed and watched. (gstack suite.)

🚀 /ship

The full release ritual: detect & merge the base branch, run tests, review the diff, bump VERSION, update CHANGELOG, commit, push, open a PR.

Run/ship

🌐 /land-and-deploy

Lands the change and runs your deploy flow in one move. Pair with /setup-deploy once to configure targets.

Run/land-and-deploy

🐤 /canary

Post-deploy canary monitoring — watches the freshly shipped build for errors before you trust it.

Run/canary

📊 /health & /retro

/health is a code-quality dashboard; /retro runs a weekly engineering retrospective across what changed.

Run/health

🐞 /investigate

Systematic debugging that drives to a real root cause instead of patching symptoms.

Run/investigate
“the checkout total is wrong sometimes — find out why.”

📐 /spec

Turns vague intent into a precise, executable spec in five phases — before a line of code is written.

Run/spec
03

Browser, QA & the web

Claude can drive a real headless browser — test flows, scrape data, dogfood your own site.

🧭 /browse

A fast headless browser for QA and dogfooding — Claude opens pages, clicks, reads, and reports what a real user would see.

Run/browse
“walk the signup flow on my staging site.”

🧪 /qa & /qa-only

/qa systematically tests a web app and fixes the bugs it finds; /qa-only reports without touching code.

Run/qa

🕷️ /scrape & /skillify

/scrape pulls structured data off any page; /skillify then freezes that flow into a permanent reusable browser-skill on disk.

Run/scrape
“grab all prices from this competitor’s catalogue.”

🔗 /connect-chrome

Launches an AI-controlled Chromium with the sidebar extension built in, so Claude shares a live browser with you.

Run/connect-chrome
04

Design

From a blank brief to a finished, on-brand interface — with a designer’s eye on the details.

🎨 /design-consultation

Understands your product, researches the landscape, and proposes a full design system — aesthetic, type, colour, layout, spacing, motion — with font + colour previews.

Run/design-consultation

👁️ /design-review

A designer’s-eye QA pass: finds spacing issues, broken hierarchy, “AI-slop” patterns and slow interactions — then fixes them.

Run/design-review

🧱 /design-html

Generates production-quality, hand-written HTML/CSS — not framework mush.

Run/design-html

🔀 /design-shotgun

Generates several design variants at once, opens a comparison board, collects structured feedback, and iterates.

Run/design-shotgun
Best when you don’t know the direction yet.
05

Research, docs & developer experience

Deep answers, written documentation, and a critical look at how your tooling feels to use.

🔬 /deep-research

Fan-out web research: searches many sources, fetches them, adversarially fact-checks the claims, and writes a cited report. Ask it something specific.

Run/deep-research
“UAE F&B delivery commission rates in 2026, with sources.”

📝 /document-generate

Writes missing documentation from scratch for a feature, module, or the whole project.

Run/document-generate

📦 /document-release

Post-ship docs update — keeps the manual in step with what you just shipped.

Run/document-release

🧰 /devex-review

A live audit of your developer experience — setup friction, confusing scripts, slow loops — with fixes.

Run/devex-review

📄 /make-pdf

Turns any markdown file into a publication-quality PDF.

Run/make-pdf report.md

🔎 /seo-aeo-geo

Audits and fixes a site for classic SEO, AEO (answer-engine / featured-snippet optimisation) and GEO (getting cited by ChatGPT, Perplexity, Gemini, Claude). Runs a report → fix → verify loop.

Run/seo-aeo-geo
“make this page get cited by AI assistants.”
06

Automation, scheduling & orchestration

The part most people miss — Claude can run on a clock, in the cloud, and fan out into a fleet of agents.

🔁 /loop

Runs a prompt or slash-command on a recurring interval inside the session — or lets Claude self-pace until a condition is met.

Run/loop 5m /canary
“check the deploy every 5 minutes until it’s green.”

📆 /schedule

Creates cloud routines — cron-scheduled agents that run on their own, even when your laptop is closed. List, edit, or fire them on demand.

Run/schedule
“post the daily reel at 9 AM Dubai time every day.” (Exactly how my ECJ pipeline runs.)

🕸️ Multi-agent workflows

For big jobs Claude can orchestrate dozens of subagents deterministically — fan out, verify adversarially, then synthesise. Opt in by asking for a “workflow” or using ultracode.

“use a workflow to audit all 200 pages for broken links.”

🧩 Hooks (via /update-config)

True “whenever X, automatically do Y” behaviour — the harness, not Claude, runs these, so they fire every time without asking.

“whenever a test file changes, run that test.”
07

Media & video generation

Image, video, voice, decks and marketing creative — generated and auto-published. (Higgsfield · Seedance · Veo · Nano Banana · Gamma.)

🖼️ higgsfield-generate

The core image/video engine — text-to-image, image-to-video, edits, references, and a Marketing Studio for ads with avatars and products.

“animate this product photo into a 5-second clip.”

🧑 higgsfield-soul-id

Trains a “Soul” model on a real face once, then reuses it for identity-faithful images and video — your digital twin across every generation.

“train my face, then put me in the ad.”

📸 higgsfield-product-photoshoot

Brand-quality product imagery — studio shots, lifestyle scenes, hero banners, ad creative packs, virtual try-on.

“studio hero shot of this bottle on marble.”

🛒 higgsfield-marketplace-cards

Compliant marketplace listing images — main image, secondary shots, A+ content modules ready to upload.

🍌 nanobanana

Fast 4K image generation & editing (Gemini “Nano Banana”) with subject consistency and search grounding.

🎬 Veo

Google Veo video — generate clips, animate a still image, extend a clip, or apply a style.

📊 Gamma

AI-built presentations, documents, webpages and social posts from a prompt.

“turn this report into a 10-slide investor deck.”

🎥 Seedance video styles (01–15)

Fifteen specialist video-prompt skills for Seedance 2.0, each tuned to a look or use-case. You never name them — describe the vibe and the right one loads.

Covers Cinematic · 3D/CGI · Cartoon · Comic-to-video · Fight scenes · Motion-design ads · E-commerce ads · Anime · Product 360° · Music video · Social hooks · Brand story · Fashion lookbook · Food & beverage · Real estate.
“make a viral TikTok hook for my app.” → loads the social-hook skill.
08

Subagents — Claude’s teammates

Specialised agents Claude can dispatch to work in parallel, each with its own tools and focus.

🔭 Explore

A read-only search agent for sweeping many files fast — it locates code and reports the conclusion without dumping the whole repo on you.

“find everywhere we handle refunds.”

🗺️ Plan

A software-architect agent that designs an implementation plan — steps, critical files, trade-offs — before any code is touched.

📖 claude-code-guide

An agent that answers “can Claude…/how do I…” questions about Claude Code, the Agent SDK and the Claude API.

“how do I add an MCP server?”

general-purpose

The all-rounder for multi-step research and searches when you’re not sure where the answer lives.

09

Custom skills I’ve built

Skills aren’t just the defaults — you can author your own. These run my businesses on autopilot.

🥘 ecj-uae-brand

A locked brand system for EatCookJoy UAE — logo, colours, type, pricing and guardrails. Any branded output (deck, newsletter, social post) stays perfectly on-brand automatically.

📹 ecj-uae-ugc-reels

End-to-end branded UGC reels — image → video → captioned, voiced, branded 12-second reel saved to Downloads. Scheduled daily to the brand’s channels.

🔧 Want one for your business?

A custom skill turns a repeatable job — your reporting, your creative, your outreach — into one command (or a scheduled agent) that runs the exact same way every time.

Let’s talkWhatsApp →
How to read this page: you almost never type these names. Tell Claude Code the outcome you want in plain English and it loads the matching skill on its own. The slash-commands above are just the manual override when you want to fire one directly. New skills land often — this guide is updated as they ship.