Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

brand-copywriter

skill · ognjengt/founder-skillsMIT licenceAudited 20 Oct 2026 · source 90bc6f1424df

★ 559pushed 155 days ago
✓SAFEGrade B · 89/100 · 20 Oct 2026 · 90bc6f1
559repo stars · whole ognjengt/founder-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 90bc6f1424df and found no filesystem, network or shell access and no hard-coded secrets. What it does: Writes marketing copy using proven copywriting frameworks. Use when user needs copy for ads (Facebook, Instagram, TikTok, YouTube), landing pages, sales pages, email sequences, LinkedIn posts, product descriptions, or…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “brand-copywriter (ognjengt/founder-skills)”. Retrieved 20 Oct 2026. https://modelsatlas.com/skills/ognjengt/brand-copywriter

Trust audit

Audit 0.4.1 · source read 20 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 90bc6f1424df · 20 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherognjengt GitHub userOwner of the repository this skill is read from
  • Source folderognjengt/founder-skills/skills/brand-copywriterThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict90bc6f1424dfA new audit runs when the source changes
  • Repository statusNot archivedLast push 155 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Writes marketing copy using proven copywriting frameworks. Use when user needs copy for ads (Facebook, Instagram, TikTok, YouTube), landing pages, sales pages, email sequences, LinkedIn posts, product descriptions, or…

---
name: brand-copywriter
description: Writes marketing copy using proven copywriting frameworks. Use when user needs copy for ads (Facebook, Instagram, TikTok, YouTube), landing pages, sales pages, email sequences, LinkedIn posts, product descriptions, or any marketing content.
---

# Brand Copywriter

## Purpose
Generate professional marketing copy in two versions: one using the optimal framework for the platform/use case, and one using an AI-selected alternative framework for comparison.

---

## Execution Logic

**Check $ARGUMENTS first to determine execution mode:**

### If $ARGUMENTS is empty or not provided:
Respond with:
"brand-copywriter loaded, proceed with what you need copy for (e.g., Facebook ad, landing page, TikTok video, LinkedIn post, email sequence, etc.)"

Then wait for the user to provide their requirements in the next message.

### If $ARGUMENTS contains content:
Proceed immediately to Task Execution (skip the "loaded" message).

---

## Task Execution

When user requirements are available (either from initial $ARGUMENTS or follow-up message):

### 1. MANDATORY: Read Reference Files FIRST
**BLOCKING REQUIREMENT — DO NOT SKIP THIS STEP**

Before doing ANYTHING else, you MUST use the Read tool to read BOTH reference files:

```
Read: ./references/copy_frameworks.md
Read: ./references/writing_styles.md
```

**What you will find:**
- **copy_frameworks.md:** 14 proven copywriting frameworks with detailed structures, selection matrix, and quick reference tables
- **writing_styles.md:** Voice and tone rules built from Ogilvy, Schwartz, Hopkins, Halbert, Sugarman, Caples, and Collier. Contains the Banned Phrases list, AI tell patterns to avoid, and how human copy actually sounds.

**DO NOT PROCEED** to Step 2 until you have read both files and have the frameworks AND voice rules loaded in context.

### 2. Check for Business Context
Check if `FOUNDER_CONTEXT.md` exists in the project root.
- **If it exists:** Read it and use the business context to personalize your copy (company name, product details, brand voice, target audience, unique selling points, pain points).
- **If it doesn't exist:** Proceed using defaults from "Defaults & Assumptions" and ask clarifying questions if critical information is missing.

### 3. Analyze Input
From the user's requirements, extract:
- **Copy type:** What are they writing? (Facebook ad, landing page, TikTok script, etc.)
- **Product/service:** What are they selling?
- **Target audience:** Who is this for?
- **Key benefit/transformation:** What outcome does the customer get?
- **Tone:** Professional, casual, bold, friendly, etc.
- **Length constraints:** Character limits, word count, duration (for video)

For any missing information, apply defaults from **Defaults & Assumptions**.

### 4. Select Frameworks
Using the Framework Selection Matrix and "Choosing Between Frameworks" guidance from copy_frameworks.md:

1. **Primary Framework:** Select the best framework based on:
   - Copy type/platform (use matrix as starting point)
   - Product's primary angle (pain-driven → PAS, transformation → BAB, features → FAB, etc.)
   - Audience awareness level (unaware → ACCA/AIDA, problem-aware → PAS/BAB, etc.)
   - Available copy length

2. **Alternative Framework:** Select a genuinely different framework that offers a contrasting approach:
   - If primary is pain-focused (PAS), try transformation-focused (BAB) or structured (AIDA)
   - If primary is feature-focused (FAB), try pain-focused (PAS) or story-focused (STAR)
   - The alternative should give the user a meaningfully different angle to test

### 5. Write Copy — Version A (Primary Framework)
Write the complete copy using the primary framework:
- Follow the framework's exact structure
- Apply brand voice from FOUNDER_CONTEXT.md (if available)
- Include all required elements (hook, body, CTA)
- Respect platform constraints (character limits, video length)
- Follow all Writing Rules below

### 6. Write Copy — Version B (Alternative Framework)
Write the complete copy using the alternative framework:
- Same product/message, different structure
- Explain why this framework was chosen as the alternative
- Follow all Writing Rules below

### 7. Format and Verify
- Structure output according to **Output Format** section
- Complete **Quality Checklist** self-verification before presenting output

---

## Writing Rules
Hard constraints. No interpretation. Every rule here exists because it kills conversion when broken.

### Core Rules
- Write to one specific person, not an audience
- Lead with the strongest element (pain, benefit, or hook)
- One idea per sentence
- Active voice only
- Specific numbers, always. "127%" not "over 100%". "$45K/month" not "six figures". "2.4 hours" not "significant time".
- Benefits over features. What they GET, not what it HAS.
- Clear, single CTA per piece of copy. Name what happens when they click. Not "Sign Up". "Get the free template."
- Every sentence should pull the reader to the next one (Sugarman's slippery slide)
- Use contractions. "You're" not "You are". "It's" not "It is".
- Have opinions. Bland copy sells nothing.
- Admit limitations when relevant. It builds trust faster than any claim.

### Voice Rules (Non-Negotiable)
**Read writing_styles.md for the full Banned List. These are the critical ones:**
- NO em dashes for dramatic effect. One brief aside per paragraph max. Never for building tension.
- NO "And honestly?", "Here's the thing...", "The truth is...", "At the end of the day..."
- NO "It's not X. It's Y." structure. Cut it entirely.
- NO "Let's dive in", "Whether you're a X or a Y...", "Unlock your potential"
- NO "game-changer", "revolutionary", "seamless", "robust", "leverage", "streamline", "delve"
- NO "Now," as a paragraph opener
- NO three consecutive fragments for artificial punch
- NO one-liner at the end that restates what you just said
- NO fake vulnerability that's actually a humble brag
- Adjectives like "incredible", "amazing", "powerful" are la

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 90bc6f1

Download folder ↗
git clone https://github.com/ognjengt/founder-skills
git -C founder-skills checkout 90bc6f1424df

The author documents no install command, so this uses the repository directly. Our verdict covers commit 90bc6f1424df only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 90bc6f1424df

Questions about brand-copywriter

What does the brand-copywriter skill do?
Claude skills for founders
Is brand-copywriter safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can brand-copywriter access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (90bc6f1424df), read on 2026-10-20. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.