Claude, translated for work.
Anthropic writes for the people building Claude. We write for the people using it at work.
The translation layer between Anthropic's docs and getting real work done. No account, no signup, no paywall — open a page and go.
Pick your work track
Choose the path that matches how you work. Two minutes to orient.
The Analyst Track
Turn scattered updates into clear leadership-ready briefs.
Your path: Claude.ai → Projects → Hand off a report → Research → Connectors
The Builder Track
Ship faster with Claude handling boilerplate, review, and docs.
Your path: Claude Code → Claude.ai for planning → Skills
The Leader Track
Turn scattered updates into clear decisions and next moves.
Your path: Projects → Research → Hand off a deck → Team plan
Marketer or content creator? The Creator Track → — rough idea to polished content in one session.
Your first week checklist
Open Claude. Paste. Done.
Four prompts that cover 80% of daily work. Copy any one. Paste it into Claude with your content.
Summarize a Document
Paste any doc, report, or email thread. Get structured summary + action items.
Summarize this into: (1) what matters most, (2) key decisions or action items, (3) anything I should flag. Be specific, not generic.
Rewrite for Clarity
Paste any draft. Get a cleaner, more direct version that actually lands.
Rewrite this to be clear, direct, and professional. Cut filler. Short sentences. Keep the meaning. Show me the rewrite only, no commentary.
Analyze and Advise
Paste any situation, problem, or decision. Get structured analysis and a recommendation.
Analyze this. Tell me: (1) what's actually going on, (2) risks or gaps I might be missing, (3) what you'd recommend and why. Be direct.
Turn Notes into Output
Paste rough notes, bullet points, or a brain dump. Get a polished, structured deliverable.
Turn these notes into a [email / summary / brief / report]. Structured, professional, ready to send. Fill gaps with reasonable assumptions and flag them.
These work in any Claude chat. For consistent results every time, set up your system →
Everything you need. Zero jargon.
Why Claude matters, in seven cards.
Stop prompting Claude. Start assigning it work.
Safe by Design
Constitutional AI — built-in rules, not afterthought guardrails. Safety is architecture, not a patch.
Writes Like a Human
Most natural writer among frontier AI models. Output you can actually use without heavy editing.
Your Data Stays Yours
Anthropic never trains on Enterprise conversations. Hard policy, not a checkbox. Team and Enterprise inputs/outputs aren't used for training by default. On consumer plans (Free, Pro, and Max), training only happens if you opt in or your conversation is flagged for safety review.
Ad-Free Forever
Anthropic's public commitment in their Feb 4, 2026 post "Claude is a space to think." No ads, ever. The argument: ad incentives conflict with honest, helpful answers.
Sonnet 5.5 handles most of your work
Sonnet 5.5 is the everyday model: fast, and strongest at docs, slides and spreadsheets. Opus 5.5 is for your hardest, longest jobs; Anthropic says it matches Fable 5.1 on most work at a lower cost. Haiku 5.5 is the quick, lightweight one. Fable 5.1 sits at the top for rare frontier tasks.
Claude lives in Microsoft 365
Add-ins for Excel, PowerPoint, and Word are live. Outlook too. Context carries between apps — what starts in chat can end as a deck without copy-paste.
Claude Code + Skills
Claude Code is an AI coding agent that lives in your terminal. Skills are reusable playbooks that teach Claude your team's exact workflows. Install community skills in one command.
Read the skim and want the real thing? Start the free 5-module course →
Pick Your Model
Four models. Different jobs. Here's the honest breakdown.
Haiku 5.5
Quick jobs • FastestThe fastest model Anthropic has made, and a big jump over Haiku 4.5. Built for quick, repetitive work: summaries, sorting, short replies, pulling one number out of a long file.
Sonnet 5.5
~70% of tasks • Start hereThe everyday model. 30%+ faster than Sonnet 5 and noticeably better at finished work. In one Anthropic test, experts judged its first-draft 10-slide operating review ready to send as is.
Opus 5.5
~10% of tasks • The heavy-hitterFor work that needs careful judgment over a long stretch. Anthropic says it performs at Fable 5.1's level on most work and costs 40% less to run than Opus 5. It also writes more clearly: the important point comes first.
Fable 5.1
Most capable • Special occasionsAnthropic's most capable model, tuned for the longest and hardest tasks. Available on Pro, Max, Team and Enterprise. On Pro it runs on usage credits; on Max it counts toward your weekly limits. Not on Free. Worth it when a second-best answer costs you real time. Not worth it for everyday work Sonnet 5.5 already handles.
Older models like Sonnet 5, Opus 5 and Opus 4.8 haven't been retired. If a workflow runs on one, nothing breaks. For new work, pick from the four above.
Need the cheat sheet? Get the one-page model picker →
🧠 How hard Claude thinks
Current Claude models decide for themselves how much to think before they answer: a quick reply for a quick question, longer reasoning for a hard one. For anything that matters, ask Claude to check its own work before it hands it back.
Which model should I use?
| Use when... | Model | Trade-off |
|---|---|---|
| Most daily work: writing, summarizing, docs, decks | Sonnet 5.5 | Best speed and quality balance. Start here. |
| Long, hard or judgment-heavy work | Opus 5.5 | For when depth matters more than speed. Cheaper to run than the Opus before it. |
| Quick, repetitive, high-volume tasks | Haiku 5.5 | Fastest. Less depth on nuance. |
| A rare frontier task where second-best costs you | Fable 5.1 | Most capable. Overkill for everyday work. |
Swipe the table sideways to see every column
Plain English rule: If you're not sure, use Sonnet 5.5. That's correct.
Sonnet 5.5, Opus 5.5 & Haiku 5.5: 1 million tokens = hundreds of thousands of words = your entire company wiki
Prices approximate. Check current pricing at Anthropic →
Basic Prompt vs. Pro Prompt
The quality of the output depends entirely on the quality of the briefing. Every time.
No context. No recipient. No tone. No length. Claude has to guess everything.
Role + context + task + format + tone. Claude has everything it needs.
Same task. Different briefing. This is the whole game.
The Golden Trio
Context + Task + Format. Master these three and every prompt gets better.
Context
❌ "Write an email about the project."
✅ "You are a project manager updating a client on a delayed launch. The delay is 2 weeks due to vendor APIs missing the SLA..."
Task
❌ "Help me with this data."
✅ "Identify the 3 biggest risks in this plan. Rank by likelihood and impact. Be specific."
Format
❌ "Send me the results."
✅ "3-column table: Risk Name, Impact Level, Mitigation Strategy. Max 1 line per row."
Bonus: Upload the whole thing
Don't summarize before pasting. Upload entire codebases, email threads, full contracts. Let Claude do the synthesis. That's what it's built for.
5 Prompts You Can Use Right Now
Each one uses the Golden Trio. Copy, paste, customize the brackets.
Want more prompts you can paste today? See the 11 work moves →
Hard-won lessons from people who use Claude all day.
Tell Claude who you are
Add a custom instruction like "I'm a designer with little coding experience — explain things simply and make changes incrementally." Claude calibrates instantly. Takes 30 seconds to set up.
— Product Design team
Let Claude talk first
Instead of asking rapid-fire questions, give Claude the full context and say "work through this and commit as you go." Periodic check-ins beat micromanaging every step.
— Security Engineering team
What NOT to trust Claude with
Never paste client PII, passwords, or internal financials. Be careful with links from unknown sources — prompt injection via URLs is a real attack vector. Only connect tools (file systems, APIs, production systems) you understand and trust.
— Anthropic security guidance
Push back when something smells off
In Anthropic's own testing, Claude confidently reported a finding from a test it never actually ran — and only caught it when the user asked "is that actually proven?" One pushback question is the cheapest quality check you have. Use it on anything that matters.
— from a documented limitation in an Anthropic model's system card
How Claude gets work done
Claude isn't just a chatbox. Here's the full picture of what it can do and where it runs.
Claude.ai
Web and mobile app. Chat, Projects, Research, Artifacts, Memory, and Connectors — all in one place. Start here if you're new.
Projects
Upload docs, set custom instructions, and every conversation starts with full context. Stop re-explaining yourself every chat.
Artifacts
Docs, decks, designs and dashboards Claude builds open beside the chat, where you can edit them, present them or download them. You can also start one from the Artifacts tab.
Claude Code
Reads your entire codebase, writes and tests code, commits directly. Included in every Team plan seat.
claude in your terminal and ask for a code review.Claude for Chrome
The Chrome extension reads console errors, network requests, and live DOM state — so Claude can debug alongside you without switching tabs. Also summarizes pages and drafts replies.
Hand Claude the whole job
You no longer pick between Chat and Cowork. Ask a quick question or hand over a report due at noon, all in the same conversation. Claude works out what the task needs, keeps going after you close your laptop, and asks before it takes an action unless you tell it otherwise.
Live on Pro, Max and Enterprise; Team and Free to follow.
Docs, Slides & Design
Ask for a document, a deck or a one-pager and Claude builds it right in the conversation. Edit it yourself or tell Claude what to change, then download as PowerPoint or PDF. Out of beta and on every plan, including Free.
Claude works inside Excel, Word & PowerPoint
On a paid plan, you can add Claude straight into Excel, Word, and PowerPoint — fix a formula, draft a doc, or build slides right where the file lives instead of relaying through a chat tab. Outlook's there too.
API
Build Claude into your own apps. Same models, full control over system prompts, tools, and integrations via the Anthropic API.
Skills
Teach Claude your team's workflows once. Install community skills in one command. Like giving a new hire an SOP manual. Team and Enterprise plans now support org-wide Skills management.
On October 22 Anthropic handed the Agent Skills standard to the Agentic AI Foundation, a neutral home under the Linux Foundation. More than 70 AI tools already support it, so a skill you write once isn't locked to one app.
How teams use Claude at work
Real use cases. No coding required.
Built an accessibility app in 1 hour
A lawyer with no coding background built a predictive text app for a family member with a speaking difficulty — complete with voice output. No engineers involved.
"I'm a developer now." — Anthropic Legal team
Ad copy: 2 hours → 15 minutes
Growth Marketing built a workflow that processes hundreds of existing ads, identifies underperformers, and generates new variations automatically. One person operating like a full team.
10x creative output. Zero extra headcount.
Plain English → fully automated reports
Finance team members with zero coding experience now write plain text descriptions of their workflows — "query this dashboard, run these numbers, produce Excel output" — and Claude executes the whole thing.
No IT ticket. No waiting. Just results.
Voice mode: Have a full spoken conversation with Claude. Tap the sound-wave icon in the chat box, on the web, the desktop app or your phone. It's on every plan, in beta, and languages other than English are in beta too.
Not sure how the pieces fit together? See the full stack →
What Anthropic released recently.
Features and tools from the last two months — verified, translated for humans. Sorted by what you actually have to do about them.
Availability may vary by enterprise plan.
For everyone
Docs, Slides and Design are on every plan, Free included.
Ask for a document, deck or design in any chat. Claude builds it; you edit it in place or ask for changes, then download as PowerPoint or PDF. People have made over 45 million of them since September, per Anthropic.
See the guide →Cowork and chat are now one Claude.
No more picking a mode. Ask a quick question or hand over a whole report in the same conversation; Claude keeps working after you close your laptop. Your chats, projects, connectors and skills come with you.
The 5.5 models: faster, cheaper, clearer.
Sonnet 5.5 is the new everyday model, 30%+ faster than Sonnet 5. Opus 5.5 handles the hard stuff and, per Anthropic, costs 40% less to run than Opus 5. Haiku 5.5 is the quick one.
See the lineup →The old Claude Design site closes December 14.
Design now lives inside every chat. If you used claude.ai/design, move your design systems over from the Artifacts page, and save any chats or comments you need; those don't carry over.
For paid plans
Dashboards: ask your data a question.
Connect a data platform or a tool like Salesforce, ask in plain English, and Claude builds a dashboard that stays current. Click any number to see the query behind it. Check with your data team before you connect a company warehouse.
See the guide →Claude Duet: the Claude that messages you first.
A separate app that sends a morning brief from your connected apps, flags what needs you, and works on tasks while you're away. It shows you exactly what it's about to do before it sends, pays, signs or deletes anything. Anthropic says it can still misread what's urgent; it's a research preview.
Worth knowing
Skills became an industry standard.
Anthropic donated Agent Skills to the Agentic AI Foundation. More than 70 AI tools support them, so the skills you build aren't locked to one app.
Browse the 35 free skills →Building on the Claude API? Three settings stopped working.
API version 2026-10-21 removes temperature, top_p and top_k. Requests that still send them get an error. Remove them and use your prompt to guide Claude's behavior instead.
See the migration deadlines →Looking for something older? See every update on What's New →
Using the Claude API? Check the migration deadlines →
Claude changes fast. Don't fall behind.
Get the monthly ClaudeHQ update — new features, translated for humans.
No spam. Monthly Claude updates only.
Skill Starter
Describe what you want Claude to do, and get a valid SKILL.md template instantly.
→ Want ready-made skills? Browse the free ClaudeHQ Skills Store
Build Your First Skill
Type a goal below — like "Help me plan sprints" or "Write weekly status reports" — and we'll generate the YAML frontmatter block you need.
Quick note: this is a starter, not a finished skill. It works best on common tasks like status reports, briefs, and summaries. For complex or unusual workflows, use Anthropic's skill-creator inside Claude for a guided build.
What to do next
This is the contents of your SKILL.md file. To use it:
- Create a folder using the skill name (kebab-case).
- Inside that folder, create a file named exactly
SKILL.md. - Paste this content into the file, or use the download button above.
- Zip the folder.
- Upload it in Claude via Settings → Capabilities → Skills.
If your skill doesn't upload, check the filename first: it must be exactly SKILL.md.
What makes a good description?
The description field controls WHEN Claude loads your skill. Get it wrong and your skill never fires.
Formula: What it does + When to use it
✘ Bad: "Helps with projects."
✔ Good: "Sprint planning for agile teams. Use when user says 'plan sprint', 'create sprint tasks', or needs to organize upcoming work into a two-week cycle."
Write it the way you'd actually ask Claude — not the way a developer would document it.
3 types of Claude skills
From Anthropic's official skills guide — three things skills are built for:
1. Document & Asset Creation
Consistent output: docs, presentations, code, designs. No external tools needed.
Example: a skill that always writes proposals in your brand voice.
2. Workflow Automation
Multi-step processes that need to run the same way every time. Often uses MCP servers.
Example: pulls Linear tasks, writes standup summary, posts to Slack.
3. MCP Enhancement
Adds expertise on top of a connected tool.
Example: doesn't just access Sentry — knows your team's bug triage process and applies it automatically.
How to upload your skill
1. Zip your skill folder (the folder containing SKILL.md)
2. Open Claude → Settings → Capabilities → Skills
3. Click "Upload skill" → select your zip file
4. Test it: type a message that should trigger it and watch for the skill icon
For teams: Admins can deploy skills org-wide from the admin dashboard.
Want Claude to build this for you?
Anthropic built a skill that builds skills. It's called skill-creator — it's free, it's inside Claude, and it walks you through every step in 15-30 minutes.
How to use it:
Option 1 — Claude.ai: Open a new conversation and type:
"Use the skill-creator skill to help me build a skill for [your goal]"
Option 2 — Claude Code: The skill-creator skill is available in your skills directory. Run it from Claude Code for programmatic output.
Skill not working? Common fixes.
Skill won't upload
Check the filename is exactly SKILL.md — case-sensitive (capital S, K, I, L, L, .md). Verify YAML frontmatter has both opening and closing --- delimiters.
Skill won't trigger
Description is too vague. Rewrite it using phrases you'd actually say to Claude. Debug move: ask Claude "When would you use the [skill-name] skill?" — it quotes your description back. Adjust from there.
Skill triggers too often
Add scope to your description. Example: "Do NOT use for general questions — only activate for [specific context]."
MCP server not connecting
Test the MCP independently before blaming the skill. Ask Claude to use the tool directly without the skill active. If that fails, the issue is the MCP connection, not your skill. Check: Settings → Extensions → your service → should show "Connected."
ClaudeHQ is an independent project, not affiliated with Anthropic. Skills content translated from Anthropic's official documentation. All Claude trademarks belong to Anthropic.
Official resources worth bookmarking
The best of Anthropic's own documentation, curated so you don't have to dig.
Claude API Deadlines — Live Tracker
Next retirement: Sonnet 4.5 on November 30, 2026. Check what's migrating and when.
Anthropic Docs
Full API and platform documentation
Claude Help Center
Feature guides and FAQs
Anthropic News
Official announcements and research
ClaudeHQ Skills Store
35 free prompt skills, copy and go
FREE PDF GUIDES
The Golden Trio
The 3-part framework that fixes 80% of bad Claude outputs.
Prompt Mistakes
The exact wording errors that make Claude sound generic — and the replacements.
Your First Project
Step-by-step: go from new account to a working Project in under 10 minutes.
Model Picker (1 page)
All four current models, with what each is for and when to skip it. Built to screenshot.
What NOT to Put Into Claude
The safety rules your whole team should read before using Claude for work.
Prefer a playbook you can paste over a PDF? Browse the 35 free skills →