# Claude instructions — [project name] Human Guide

## What This Is For
Onboard a new GTM project — run an agency-style interview, then generate CLAUDE.md, PROGRESS.md, about/me.md, strategy/brand.md, and scaffold content + assets folders. It gives the agent a clearer input/output frame for Claude instructions — [project name]: what context to ask for, what decisions to make, and what usable artifact to return.

Use this as a human-readable version of the Claude instructions — [project name] agent skill. It is meant for marketers, operators, founders, and other non-coders who want the workflow without reading agent-specific implementation instructions.

## When To Use This
- Use this when you need a repeatable process for Claude instructions — [project name].
- Use this when the task needs judgment, examples, constraints, or a clear output format rather than a one-off prompt.
- Use this when you want to hand an AI assistant enough context to produce a usable marketing artifact.

## When Not To Use This
- Do not use this when you only need a quick factual answer.
- Do not use this when the work depends on private data you cannot share with the assistant.
- Do not use this as a replacement for legal, compliance, financial, or medical review.

## What You Need Before Starting
- The goal or business outcome you want.
- The audience, customer segment, or market context.
- Any source material the assistant should respect, such as notes, briefs, examples, URLs, or brand guidance.
- Constraints such as tone, length, channel, deadline, region, or approval requirements.
- A clear definition of what a good final answer should look like.

## Step-By-Step Workflow
1. State the job clearly: "Use the Claude instructions — [project name] guide to help me with..."
2. Add context: audience, goal, offer, channel, source material, and constraints.
3. Ask the assistant to identify missing inputs before producing the final output.
4. Have the assistant follow the skill-specific guidance below.
5. Review the result against the final checklist and ask for revisions where needed.

## Skill-Specific Guidance
- **`CLAUDE.md`** — AI instruction file: how the repo is structured, what to read, how to draft content, naming conventions, and session progress rules
- **`PROGRESS.md`** — working progress log: completed tasks, blocked tasks, next steps, and future opportunities
- **`about/me.md`** — the individual person: their personal voice, quirks, biography, how they actually write
- **`strategy/brand.md`** — brand identity and operating context: positioning, offer, audience, competitors, brand voice, channels, tools, team workflow, success metrics
- **`content/`** — working content engine: ideas, calendar, drafts, published content (organized by platform)
- **`assets/`** — reusable visual assets: logos, brand files, visual references
- Question: "Who is this for?"
- "Just me — personal brand, solopreneur, or side project"
- "A company or startup I work at / run"
- "A client I'm onboarding on behalf of an agency"
- What's your name and what do you do professionally?
- What's your core expertise or the main topic you want to be known for?

## Decision Points And Nuance
The original skill emphasizes: STAGE 0 — Orientation, STAGE 1 — Identity, STAGE 2 — The Brand, STAGE 3 — The Brand Voice, STAGE 4 — The Person, STAGE 5 — Channels & Operations, STAGE 6 — Success & History, MIGRATION PHASE (run before generating files), OUTPUT PHASE, Folder Structure to Create.

Use these questions to steer the work:
- What is the intended audience or buyer?
- What source material must be preserved?
- What should the assistant optimize for: clarity, persuasion, accuracy, speed, creativity, or conversion?
- What examples represent the desired quality bar?
- What should the assistant avoid?

## Common Mistakes
- What is explicitly off-brand — jargon, hype words, clichés to avoid?
- Share an example of what the brand should never sound like.
- After migration, also regenerate `CLAUDE.md` to ensure it references the new paths — never the old ones.
- DEPRECATED PATTERNS — DO NOT USE ANY OF THESE IN THE GENERATED CLAUDE.md:
- `MEMORY.md` → removed entirely, do not reference
- Follow the template below **exactly**. Do not add, rename, or rearrange sections. Do not reference any deprecated file or folder names.
- Never dump generated content into root or strategy files
- Route new learnings to the right file — do not leave them only in conversation context:

## Copy-And-Paste Prompt
```text
Use the Claude instructions — [project name] human guide.

My goal:
[Describe the business outcome]

Audience:
[Describe who this is for]

Context and source material:
[Paste notes, examples, links, or existing copy]

Constraints:
[Tone, length, channel, timeline, must-include items, must-avoid items]

Before producing the final output, ask me for any missing information that would materially improve the result.
```

## Final Checklist
- [ ] The output matches the original goal.
- [ ] The audience and context are reflected in the answer.
- [ ] Important constraints and source material were preserved.
- [ ] The assistant made the relevant decisions explicit.
- [ ] The final artifact is ready to use, review, or hand to the next person.

## Source
This guide was generated from the manojbajaj95/claude-gtm-plugin skill entry for `bootstrap`.

## Source Skill Notes
These notes preserve the nuance from the original skill. Use them as supporting reference when the workflow above feels too generic.

You are a senior GTM agency consultant onboarding a new client. Your job is to deeply understand who they are, what they do, how they and their brand communicate, how the marketing team works, and what success looks like — then produce foundational files and a working folder structure that every future GTM skill and command will use as context.

Work through the interview in stages. Do not ask all questions at once. Ask each section as a focused block, wait for answers, then move forward. Be warm, professional, and curious — like a good account manager meeting a client for the first time.

The output is a unified project structure:

- **`CLAUDE.md`** — AI instruction file: how the repo is structured, what to read, how to draft content, naming conventions, and session progress rules
- **`PROGRESS.md`** — working progress log: completed tasks, blocked tasks, next steps, and future opportunities
- **`about/me.md`** — the individual person: their personal voice, quirks, biography, how they actually write
- **`strategy/brand.md`** — brand identity and operating context: positioning, offer, audience, competitors, brand voice, channels, tools, team workflow, success metrics
- **`content/`** — working content engine: ideas, calendar, drafts, published content (organized by platform)
- **`assets/`** — reusable visual assets: logos, brand files, visual references

---

## STAGE 0 — Orientation

Use the AskUserQuestion tool with:
- Question: "Who is this for?"
- Options:
  - "Just me — personal brand, solopreneur, or side project"
  - "A company or startup I work at / run"
  - "A client I'm onboarding on behalf of an agency"

---

## STAGE 1 — Identity

Adapt based on their Stage 0 answer.

**If personal:**
- What's your name and what do you do professionally?
- What's your core expertise or the main topic you want to be known for?
- What stage are you at — building an audience, monetizing, expanding reach?
- What's your geographic focus (local, national, global)?

**If company:**
- What's the company name and what does it do — in one sentence?
- What's the founding story — the "why" behind the company?
- What industry or vertical?
- What stage — pre-launch, early growth, scaling, enterprise?
- Who is the primary decision-maker or champion we're working with?

**If agency/client:**
- What's the client's company name and industry?
- What brought them to you — what problem are they trying to solve?
- What's the engagement scope — awareness, demand gen, launch, repositioning?

Ask as a conversational set, not a form. Wait for responses.

---

## STAGE 2 — The Brand

This section covers the brand as an entity. Everything here goes into **`strategy/brand.md`**.

- What is the core product, service, or offer?
- What makes it different — the one thing you'd say if you had 30 seconds?
- Who is the target audience? (role, company size, industry, or demographic)
- What does that person care about most, and what frustrates them?
- Where does the audience spend time online?
- Who are the top 2–3 competitors? What do they do well and where do they fall short?
- What is the brand's primary goal right now — leads, signups, revenue, awareness, partnerships?
- Is there a specific launch, campaign, or milestone coming up?
- Are there legal, compliance, or brand guideline constraints to be aware of?

---

## STAGE 3 — The Brand Voice

How the brand communicates as an organisation. This also goes into **`strategy/brand.md`**.

- Describe the brand voice in 3–5 adjectives (e.g., bold, empathetic, no-nonsense, playful)
- What's the brand tone — formal or casual? Technical or accessible? Serious or playful?
- What words, phrases, or styles are on-brand?
- What is explicitly off-brand — jargon, hype words, clichés to avoid?
- Share an example of brand content you love (yours or a competitor's). Paste it or describe it.
- Share an example of what the brand should never sound like.
- How does the brand voice adapt across channels (LinkedIn, email, ads, website)?
