Free Guide · No setup required
Where do you actually put Claude instructions?
Claude has four places you can write instructions — org-wide, individual global, project-level, and skill-level. Most people put the wrong things in the wrong place. This guide explains what belongs where, with examples you can copy.
Written for two audiences: individuals setting up their own Claude account, and teams rolling out Claude Teams or Enterprise across an organization. The same hierarchy applies; the leverage is different.
Level 1 · Org-wide
Organization Instructions (Teams / Enterprise only)
Who sees it: Visible to everyone in your Claude Teams or Enterprise workspace.
Where you set it: Requires Claude Teams or Enterprise. Set by a workspace admin.
Put here
- Your company name, what you do, who you serve
- Brand voice rules (sentence shape, banned phrases, tone)
- Privacy + data handling rules (e.g. 'never paste customer PII')
- Common references everyone needs (the product taxonomy, the customer segments, the OKR framework)
- Default Claude model preference for the team
Don't put here
- Anything specific to one person's role (that's individual global)
- Anything specific to one project (that's project instructions)
- Confidential context that shouldn't be visible to every team member
Example you can adapt
# COMPANY CONTEXT We are [Company Name]. We sell [product] to [ICP]. Our customers care most about [outcome]. # VOICE Direct. Plain English. Short sentences. We don't say "leverage" or "synergy." We do say "we" and "you." # PRIVACY Never include customer PII, internal financial data, or pre-public information in any output unless the user has explicitly flagged the conversation as approved for that context.
Level 2 · You
Individual Global Instructions
Who sees it: Visible only to you. Applies to every Claude conversation in your account, including every Project.
Where you set it: Available on every plan, including free. Set in Settings → Profile (or 'About you').
Put here
- Your role, function, and what you're trying to do
- How you want Claude to talk to you (push back, don't validate; cite sources; be direct)
- Format preferences (no em-dashes, no bullet lists unless asked, etc.)
- Stable facts about you and your work that come up often (your name, title, region, key relationships)
- Your stress signals or context (e.g. 'I prefer brevity when I'm in back-to-back meetings')
Don't put here
- Anything project-specific — those instructions live on the Project itself
- Anything that changes often (project status, current priorities for this quarter — put those in your Strategic Advisor Project as a knowledge file you update)
- Confidential org context you wouldn't want surfacing in unrelated conversations
Example you can adapt
# ABOUT ME
I'm [Name], [Role] at [Company]. I work in [time zone], I'm time-poor, and I think in 5/20/30-minute pockets.
# HOW TO TALK TO ME
Push back instead of validating. If you don't know something, say so and ask the question that would change your answer. Be direct. Use plain English. Sentences are short.
# FORMAT
No em-dashes. No bullet lists unless I ask for them. When I ask "what should I do," give me one recommendation and the main tradeoff — not a balanced list of options.
# CITATIONS
When pulling from my uploaded files, name the source ("from your Q3 priorities doc"). When you don't have a source, say so.Level 3 · A Project
Project Instructions
Who sees it: Visible only to you (or your collaborators if the Project is shared). Applies only when you're working inside that Project.
Where you set it: Available on every plan that has Projects (Pro, Teams, Enterprise).
Put here
- The role this Project plays — 'Strategic Advisor,' 'M&A triager,' 'Voice profile for external comms'
- The specific domain context this Project covers (and ONLY this Project)
- How this Project should behave differently from a default Claude conversation (e.g. more skeptical, more concise, more research-heavy)
- Format rules unique to this Project's outputs (e.g. memos always in 6-section BRIEF format)
Don't put here
- Things that should apply to every Project — those go in global instructions
- Long reference content — that goes in knowledge files inside the Project, not in the instructions
Example you can adapt
# ROLE You are my strategic advisor. You know my operating priorities, recent decisions, and the shape of my week. # JOB Make me sharper, not faster. Surface what I'm not seeing instead of validating what I already think. # FRAMES Use my decision frames: capital allocation, talent leverage, product velocity, brand. Default to those when evaluating any new question. # OUTPUT Memos: 1 page max in 6-section BRIEF format (Question, Options, Criteria, Recommendation, Open Questions, Reversibility). Briefs: 1 page max with Top 3, replies drafted, heads up.
Level 4 · A Skill
Skill Instructions
Who sees it: Visible only to you. Applies when you invoke that specific Skill (via slash command or skill invocation).
Where you set it: Available wherever Skills are supported in Claude.
Put here
- Repeatable workflows: 'turn this transcript into a follow-up email,' 'generate a board update from these KPIs,' 'triage these candidate notes into a scorecard'
- A specific output template you want every time
- Skill-specific tool use rules (e.g. 'always read the Drive doc first')
Don't put here
- Your role or operating frame — those are in global instructions
- Project-specific context — that's in the Project the Skill is invoked from
- Anything that changes per use — that goes in the prompt arguments, not the Skill instructions
Example you can adapt
# SKILL: meeting-prep-brief INPUT: meeting topic + attendees (you'll get these via slash command). ACTION: Pull my Strategic Advisor knowledge files. Generate a 1-page prep brief: meeting context, the 3 things to push on, the 1 question I should be asking. OUTPUT: Plain markdown, no preamble. Save to my Drive folder called "Meeting prep" with the date in the filename.
Quick decision
Not sure which level? Ask one question.
Would I want this in EVERY conversation I have with Claude?
→ Individual Global Instructions (Level 2).
Would I want this in every conversation EVERYONE on my team has?
→ Organization Instructions (Level 1) — requires Teams or Enterprise.
Would I want this only when I'm working on this specific role or domain?
→ Project Instructions (Level 3).
Is this a repeatable workflow I run on different inputs?
→ Skill Instructions (Level 4).
Common mistakes
Four traps to avoid
Every one of these is fixable in 10 minutes once you spot it.
Putting the company brand voice in individual global instructions
Then it only applies to you. The marketing director writing the same email gets a different voice. Move to org-level if you have Teams.
Putting current-quarter priorities in global instructions
They change every quarter. You'll forget to update them. Put them in a Drive doc that your Strategic Advisor Project reads as a knowledge file — update the doc, the Project updates with it.
Stuffing long reference content into Project instructions
Project instructions are for behavior rules. Reference content goes in knowledge files (uploaded documents or linked Drive files). The Project reads the files when needed — much more capacity than instructions allow.
No global instructions at all
Claude reverts to its default voice and behavior on every new chat — which means you keep retyping the same context. Even a 5-line global instructions file pays for itself the first week.
Bonus
Get the editable templates
Drop your email and we'll send you the editable versions of every example on this page — global instructions template, project instructions BRIEF template, and a one-page org-rollout worksheet for teams configuring Claude Teams or Enterprise. Plus the occasional Claude release brief (Nicole's, not Anthropic's — what to adopt, what to skip).
One email with the templates. Then occasional release briefs — unsubscribe anytime.
Setting this up across a team?
The Custom Workshop walks your team through the full instructions hierarchy live — org-level rules, individual global, projects, skills — built around your actual tools and roles. Up to 25 people, 90 minutes, $4,500.