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

Agent skill · Audited from source

marketing-ideas

skill · ognjengt/founder-skillsMIT licenceAudited 26 Oct 2026 · source 90bc6f1424df

★ 644pushed 160 days ago
✓SAFEGrade B · 89/100 · 26 Oct 2026 · 90bc6f1
644repo 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: Produces the best marketing ideas for your business by analyzing your FOUNDER_CONTEXT and matching it against a curated database of 170+ proven marketing strategies. Use when user needs creative, actionable marketing…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “marketing-ideas (ognjengt/founder-skills)”. Retrieved 26 Oct 2026. https://modelsatlas.com/skills/ognjengt/marketing-ideas

4 skills are called “marketing-ideas”. You are viewing ognjengt/founder-skills.

Trust audit

Audit 0.4.1 · source read 26 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 · 26 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/marketing-ideasThe 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 160 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Produces the best marketing ideas for your business by analyzing your FOUNDER_CONTEXT and matching it against a curated database of 170+ proven marketing strategies. Use when user needs creative, actionable marketing…

---
name: marketing-ideas
description: Produces the best marketing ideas for your business by analyzing your FOUNDER_CONTEXT and matching it against a curated database of 170+ proven marketing strategies. Use when user needs creative, actionable marketing ideas tailored to their business.
---

# Marketing Ideas

## Purpose
Analyze the user's business context and produce the 5 best marketing ideas from a curated database of proven strategies, each with a clear explanation and a specific action plan tailored to their business.

---

## Execution Logic

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

### If $ARGUMENTS is empty or not provided:
Respond with:
"marketing-ideas loaded, proceed with additional instructions or tell me what marketing goal you're focused on (e.g., more leads, buzz without paid ads, customer retention, crushing competitors, 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 the marketing ideas database:

```
Read: ./references/marketing-ideas-database.md
```

**What you will find:**
- **marketing-ideas-database.md**: 170+ proven marketing strategies organized by goal category (Leads & Conversions, Buzz Without Paid Ads, Customer Sharing & Virality, Crushing Competitors, Customer Retention, Winning at Events, Future-Proofing, Buzz Generation Stunts, Brand Awareness, Acquisition, Retention, Monetization). Each idea has a title, strategy, real-world example, applicability, and psychological reasoning.

**DO NOT PROCEED** to Step 2 until you have read the database and have all ideas loaded in context.

### 2. MANDATORY: Read Business Context
Check if `FOUNDER_CONTEXT.md` exists in the project root.
- **If it exists:** Read it and extract: company name, industry, target audience, value proposition, products/services, business goals, team size, competitors, and brand voice.
- **If it doesn't exist:** Ask the user to briefly describe their business, target audience, product/service, and current marketing goal. Do NOT proceed without business context — this skill requires it to produce relevant recommendations.

### 3. Analyze Input
From the user's requirements and business context, extract:
- **Marketing goal:** What they want to achieve (more leads, buzz, retention, competitive edge, etc.)
- **Business type:** B2B SaaS, B2C, e-commerce, agency, creator, etc.
- **Stage:** Early-stage, growth, established
- **Constraints:** Budget, team size, technical capability
- **Current channels:** Where they already market (social, email, events, etc.)

If the user doesn't specify a marketing goal, analyze their FOUNDER_CONTEXT to determine the most impactful goal based on their business stage and goals.

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

### 4. Select the 5 Best Ideas
Using the database from Step 1 and the business context from Step 2:

1. **Score every idea** in the database against the user's business using these criteria:
   - **Relevance:** Does this idea apply to their business type and industry?
   - **Impact:** How much could this move the needle for their specific goal?
   - **Feasibility:** Can they execute this with their current resources (team, budget, tech)?
   - **Uniqueness:** Would this be unexpected in their industry? (unexpected = more impact)

2. **Select the top 5 ideas** with the highest combined score.

3. **Ensure variety:** Pick ideas from at least 3 different categories when possible. Don't cluster all 5 in one category unless the user's goal is extremely specific.

### 5. Write Recommendations
For each of the 5 selected ideas, write two parts:

**Part A — The Strategy (What & Why)**
- Explain the strategy clearly in 2-3 sentences
- Include the real-world example from the database
- Explain the psychology of why it works

**Part B — Applied to Your Business (How)**
- Write a specific, actionable plan for how THIS business should implement this strategy
- Use the company name, product, audience, and industry from FOUNDER_CONTEXT
- Include concrete next steps (not vague advice)
- Mention specific platforms, tools, or channels relevant to their business
- If applicable, suggest a timeline or first step to get started this week

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

---

## Writing Rules
Hard constraints. No interpretation.

### Core Rules
- Every recommendation must come from the database. Do NOT invent strategies.
- The "Applied to Your Business" section must be specific to the user's business. Generic advice is useless. Use their company name, product, audience.
- Lead with the highest-impact idea first.
- Use specific numbers and examples, not vague promises.
- Keep each recommendation concise. Strategy explanation: 3-5 sentences. Application: 4-8 sentences.
- No fluff, no filler, no motivational padding.
- Active voice only.

### Selection Rules
- If the user specifies a goal (e.g., "I want more leads"), prioritize ideas from that category but don't limit yourself to it. Cross-category ideas that serve the goal are fine.
- If an idea requires resources the business clearly doesn't have (e.g., "send physical items" for a solo bootstrapped founder), skip it in favor of a more feasible alternative.
- Never recommend two ideas that are too similar. Each idea should attack the problem from a different angle.

### Context Rules
- For B2B SaaS: Prioritize ideas around product-led growth, LinkedIn, content, and competitor positioning.
- For B2C / e-commerce: Prioritize ideas around virality,

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

Similar skills

Questions about marketing-ideas

What does the marketing-ideas skill do?
Claude skills for founders
Is marketing-ideas 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 marketing-ideas 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 2026-10-26. 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.