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

Agent skill · Audited from source

linkedin-writer

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

★ 643pushed 160 days ago
✓SAFEGrade B · 89/100 · 26 Oct 2026 · 90bc6f1
643repo 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: Creates viral LinkedIn posts using proven formats, post templates, and voice matching. Use when user needs engaging, high-performing posts for LinkedIn.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

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

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/linkedin-writerThe 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: Creates viral LinkedIn posts using proven formats, post templates, and voice matching. Use when user needs engaging, high-performing posts for LinkedIn.

---
name: linkedin-writer
description: Creates viral LinkedIn posts using proven formats, post templates, and voice matching. Use when user needs engaging, high-performing posts for LinkedIn.
---

# LinkedIn Writer

## Purpose
Generate 2 viral LinkedIn posts in different proven formats, matched to the founder's voice, using battle-tested templates and patterns that drive engagement on LinkedIn.

---

## Execution Logic

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

### If $ARGUMENTS is empty or not provided:
Respond with:
"linkedin-writer loaded, proceed with your topic or idea"

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 ALL reference files. This is non-negotiable:

```
Read: ./references/linkedin-formats.md
Read: ./references/linkedin-posts.md
```

**What you will find:**
- **linkedin-formats.md**: 7 proven LinkedIn post formats with structure templates, psychology, rules, and when-to-use matching logic
- **linkedin-posts.md**: 8+ proven viral LinkedIn posts organized by format type — the example and voice library

**DO NOT PROCEED** to Step 2 until you have read all files and have their content 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 output (industry terminology, audience pain points, brand voice, company name, products, achievements).
- **If it doesn't exist:** Proceed using defaults from "Defaults & Assumptions."

### 3. Analyze Input & Auto-Select Formats
From the user's requirements, extract:
- **Topic/idea** — What they want to post about
- **Goal** — What they want the post to achieve (engagement, authority, leads, thought leadership)
- **Any specific format preference** — If they mentioned a format type

**Format Auto-Selection Logic:**

If the user specified a format → use that format for one post, auto-select the best complementary format for the second.

If the user did NOT specify a format, auto-select 2 different formats based on the topic:

| If the topic involves... | Best format match |
|---|---|
| Multiple tips, lessons, mistakes, or advice points | **Lessons Learned** |
| A complete process, roadmap, or "how to achieve X" | **Actionable Blueprint** |
| A personal experience, failure, setback, or pivotal moment | **Personal Story** |
| Explaining one specific technique, hack, or strategy with proof | **Strategy Breakdown** |
| Analyzing a specific company, product, or brand | **Case Study** |
| A strong opinion, industry trend, prediction, or contrarian view | **Industry Hot Take** |
| A small but impactful tip or optimization | **Quick Hack** |

**Always select 2 DIFFERENT formats.** Choose the primary format based on the strongest topic match, then select a complementary second format that gives the user a different angle on the same topic.

### 4. Generate 2 Viral LinkedIn Posts
Using the formats and posts you loaded in Steps 1-3:

1. **Study the example posts** in linkedin-posts.md for your selected formats — internalize the rhythm, structure, hook style, and length
2. **Extract the voice DNA** from the reference posts — match the writing style:
   - Conversational and direct, like talking to a peer
   - Short paragraphs (1-3 sentences each)
   - Heavy line breaks for readability
   - Mixes professional insight with personality
   - Uses specific numbers and data
   - First-person perspective with real examples
   - No corporate jargon
3. **If FOUNDER_CONTEXT.md exists**, blend the founder's brand voice with the voice DNA from the reference posts
4. **Draft each post** following the format's structure template, the voice DNA, and all Writing Rules below
5. **Run each post through the Engagement Test:** "Would someone save this post or leave a comment?" If no → rewrite before continuing

**Critical requirements:**
- Each post must use a DIFFERENT format (no repeats)
- Each post must match the voice DNA from the reference posts
- Each post must be about the user's SPECIFIC topic (not generic advice)
- Each post must follow the format's structure template from linkedin-formats.md
- Each post must be ready to copy-paste and post immediately — no placeholders, no [brackets], no instructions
- The first 2 lines of each post must work as a compelling hook above LinkedIn's "see more" fold

### 5. Format and Verify
- Structure output according to **Output Format** section
- Complete **Quality Checklist** self-verification before presenting output
- If any post feels generic, forced, or wouldn't pass the Engagement Test → rewrite before presenting

---

## Writing Rules
Hard constraints. No interpretation.

### Core Rules (Apply to ALL LinkedIn posts)
- **First 2 lines are everything.** LinkedIn cuts off at ~210 characters with "see more." Your hook must compel the click. Make it the strongest part of the post.
- Use frequent line breaks. On LinkedIn, white space = readability = engagement. One idea per paragraph.
- Short paragraphs only — 1-3 sentences max per paragraph. Wall of text = scroll past.
- Specific numbers > vague claims ("52% increase" not "significant increase", "23-person agency" not "large agency").
- Active voice only. Never passive.
- Present tense preferred.
- Conversational tone — write like you're talking to one person, not presenting to a boardroom.
- No hashtags in the body of the post. If used at all, maximum 3 at the very end below a line break.
- No engagement bait ("Like if you agree", "Share this with someone who needs it"). It kills credibility on LinkedIn.
- Every sentence must earn its place. If 

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 which agents?

What its own text says, not a test

AgentStatusMore
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 90bc6f1424df

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/ognjengt/linkedin-writer/badge.svg)](https://modelsatlas.com/skills/ognjengt/linkedin-writer/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/ognjengt/linkedin-writer/badge.svg)](https://modelsatlas.com/skills/ognjengt/linkedin-writer/)

Questions about linkedin-writer

What does the linkedin-writer skill do?
Claude skills for founders
Is linkedin-writer 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 linkedin-writer access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does linkedin-writer work with?
Its documentation mentions cursor. That is what the text claims, not a compatibility test we ran.
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.