wfc.
Claude resource hub
Client resource
Claude
resource hub.
Everything you need to understand, set up, and get real work done with Claude. Four resources, built for clarity. Use the sidebar to navigate — or start with any card below.
4.
Resources
18.
Guides
8.
Setup steps
32.
Terms defined
01
Reference
Anatomy of a Claude prompt
Eight structural layers — from task and context through to plan and alignment. A framework for consistent output every time.
8 layers
copy-paste template
02
Glossary
Claude glossary
The terms worth knowing — AI concepts, core features, products, and automation vocabulary, organised by category.
4 categories
32 terms
03
Guide
Claude learning stack
18 free guides sequenced by level — from a first conversation through to connectors, code, and computer use.
18 guides
4 levels
all free
04
Setup
Claude Cowork setup
Eight steps to configure Cowork properly. Follow it once and Claude starts behaving like a coworker, not a chatbot.
8 steps
one-time setup
wfc.
Client resource — prompt architecture
Anatomy of a
Claude prompt.
Eight structural layers. Each serves a distinct function. Together they define the task, constrain the execution, and protect the output from drift.
Task + success criteria. I want to [task] so that [success criteria]. First, read these files completely before responding.
[filename.md] — what it contains
[filename.md] — what it contains
[filename.md] — what it contains
Here is a reference for what I want to achieve.
[Upload reference file, or paste here]
Here's what makes this reference work:
[Paste your reverse-engineered blueprint — patterns, tone, structure, and rules. Format each as a rule starting with "Always" or "Never."]
Success brief.
Type of output + length: [contract, memo, report, proposal, post?]
Recipient's reaction: [what should they think, feel, or do after reading?]
Does not sound like: [what to avoid — generic, casual, formal, jargon-heavy?]
Success means: [they sign? they approve? they reply? they take action?]
My context file contains my standards, constraints, landmines, and audience. Read it fully before starting. If you are about to break one of my rules, stop and tell me.
Do not start executing yet. Instead, ask me clarifying questions so we can refine the approach together step by step.
Before you write anything, list the 3 rules from my context file that matter most for this task.
Then give me your execution plan (5 steps maximum). Only begin work once we have aligned.
Task
Context files
Reference
Success brief
Rules
Conversation
Plan
Alignment
wfc.
wildflower creative limited · client resource · 2026
wfc.
Reference — Claude glossary
Claude.
AI Concepts
Token
The tiny chunk of text Claude reads and writes — approximately ¾ of a word.
Context window
Claude's working memory — everything it can hold in mind at once.
Model
The specific version of Claude you're talking to — Haiku, Sonnet, or Opus.
Extended thinking
Claude reasons step-by-step before answering.
Hallucination
When Claude confidently states something false.
Prompt
The message or instruction you give Claude.
System prompt
Hidden instructions set by a developer that shape Claude's behaviour.
Temperature
A dial that controls how creative vs. predictable Claude's responses are.
Core Features
Artifact
A file or app Claude creates in a side panel — doc, code, chart, or widget.
Project
A dedicated workspace with its own files, instructions, and history.
Memory
Claude remembers facts about you across conversations.
Deep research
Claude searches the web, reads sources, and writes a full report.
Web search
Claude looks things up on the internet in real time.
Style
Claude learns your writing voice and matches it.
User preferences
Settings that tell Claude your preferred tone and format.
Compaction
Claude auto-summarises old messages to keep long chats running.
Products
Claude.ai
The main website and app where most people chat with Claude.
Claude Desktop
The downloadable app that unlocks Cowork and Code.
Cowork
Claude as a desktop agent that works on your actual files and apps.
Claude Code
Claude for developers, living in the terminal and your IDE.
Claude in Chrome
A browser extension that lets Claude see and act on web pages.
Claude in Excel
Claude living inside your spreadsheets.
Claude in PowerPoint
Claude helping build and edit slides directly in PowerPoint.
Claude Marketplace
A hub to discover and install connectors, plugins, and skills.
Agents & Automation
Connector
A live link between Claude and an external app — Gmail, Slack, Notion, and others.
MCP
Model Context Protocol — the open standard that powers all connectors.
Skill
A markdown file that teaches Claude a specific workflow or best practice.
Bundled package
Skills + connectors + commands for a whole job role.
Slash command
A shortcut like /sales:call-prep that triggers a preset workflow.
Scheduled task
A recurring job Claude runs automatically on a timer.
Dispatch
Remote control for Cowork from your phone via the Claude mobile app.
Computer use
A background document Cowork reads every session so you don't re-explain things.
wfc.
wildflower creative limited · client resource · 2026
wfc.
Client resource — guides
Claude learning
stack.
18 free guides from beginner to expert. Start anywhere.
18 guides
4 levels
all free
wfc.
wildflower creative limited · guides by claude101.com · 2026
wfc.
Client resource — setup guide
8 steps to set up
Claude Cowork.
Follow this once. Claude starts behaving like a coworker, not a chatbot.
01
Download the app
Go to claude.com/download. You need a Pro plan ($20/mo). macOS or Windows only. Open the app.
2 minutes. Don't overthink it.
02
Click the Cowork tab
Open the app. Click Cowork at the top. Select Opus 4.6. Turn on Extended Thinking.
Wrong model = bad output.
03
Build this exact folder
Create one folder: Claude-Work. Inside it, four subfolders:
Claude-Work/
  ABOUT-ME/
  PROJECTS/
  TEMPLATES/
  OUTPUTS/
Cowork has read/write access. Keep it tight.
04
Create 3 context files
Inside ABOUT-ME, create:
  • about-me.md — what you work on day-to-day
  • my-voice.md — your tone, 2–3 real writing samples
  • my-rules.md — ask before starting, show a plan, never delete
One great file beats 30 random uploads.
05
Set instructions
Settings → Cowork → Edit Instructions. Paste this:
"I'm [Name], [Role]. Read my files before every task. Ask questions before executing. Show a plan. Never delete without approval."
Set once. Runs forever.
06
Stop prompting. Start clicking.
Paste this for every task:
"I want to [TASK]. Read all files first. Ask me questions before you execute. If something is off, generate new questions. Do not guess."
Claude generates clickable buttons. You click, it executes.
07
Install your first plugin
Customize → Browse Plugins → Install. Type / to see slash commands.
  • Marketing/marketing:draft-content
  • Data/data:explore
  • Legal/legal:review-nda
Start with 2.
08
Connect your tools
Settings → Connectors → Browse → Add.
  • Slack, Google Drive, Notion, Figma — 50+ more
  • Claude reads your tools mid-conversation
  • No copy-pasting. Free on all plans
Claude stops being a chatbot. Starts being a coworker.
wfc.
wildflower creative limited · client resource · 2026