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

Agent skill · Audited from source

outreach-specialist

skill · ognjengt/founder-skillsMIT licenceAudited 27 Oct 2026 · source 90bc6f1424df

★ 646pushed 161 days ago
✓SAFEGrade B · 89/100 · 27 Oct 2026 · 90bc6f1
646repo 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: Crafts high-converting outreach messages and email sequences for cold outreach, LinkedIn DMs, and follow-ups. Use when user needs personalized outreach messages that book calls and get replies.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “outreach-specialist (ognjengt/founder-skills)”. Retrieved 27 Oct 2026. https://modelsatlas.com/skills/ognjengt/outreach-specialist

Trust audit

Audit 0.4.1 · source read 27 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 · 27 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/outreach-specialistThe 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 161 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Crafts high-converting outreach messages and email sequences for cold outreach, LinkedIn DMs, and follow-ups. Use when user needs personalized outreach messages that book calls and get replies.

---
name: outreach-specialist
description: Crafts high-converting outreach messages and email sequences for cold outreach, LinkedIn DMs, and follow-ups. Use when user needs personalized outreach messages that book calls and get replies.
---

# Outreach Specialist

## Purpose
Generate a personalized outreach sequence (default 3 messages) that sounds human, builds trust, and books calls — tailored to the prospect, platform, and offer.

---

## Execution Logic

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

### If $ARGUMENTS is empty or not provided:
Respond with:
"outreach-specialist loaded, tell me who you're reaching out to and what you're offering"

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/outreach-templates.md
Read: ./references/sequence-strategy.md
```

**What you will find:**
- **outreach-templates.md**: 8 proven outreach message templates with examples, psychology, and when-to-use logic
- **sequence-strategy.md**: Follow-up sequence structures, timing, and platform-specific rules

**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 extract everything relevant to outreach: company name, offer, ICP, value proposition, case studies, brand voice, pricing model.
- **If it doesn't exist:** Proceed using defaults from "Defaults & Assumptions."

### 3. Analyze Input & Determine What's Missing

From the user's requirements, extract:
- **Who they're reaching out to** (ICP, role, company type)
- **What they're offering** (product, service, specific solution)
- **What platform** (LinkedIn DM, email, X DM, Instagram DM, other)
- **The goal** (book a call, get a reply, send a lead magnet, get a referral)
- **Available proof** (case studies, results, testimonials, metrics)
- **Sequence length** (default: 3 messages if not specified)

### 4. Ask Diagnostic Questions (If Needed)

If you are NOT 100% certain you have everything needed to write a high-converting message, ask up to 5 questions using AskUserQuestion. Only ask what's genuinely missing.

**Question Bank (priority order):**

| # | Question | Why it matters | Skip if... |
|---|----------|----------------|------------|
| 1 | Are you reaching out on LinkedIn, email, or another platform? | Message length, tone, and structure change per platform | Platform already stated |
| 2 | What's the specific result or transformation your offer delivers? | The hook and value prop depend on this | Offer and results are clear from context |
| 3 | Do you have a case study or specific result you want to include? | Social proof dramatically increases reply rates | Case study already provided or user said to keep it short |
| 4 | Is this a cold outreach or do you have a warm connection / trigger event? | Changes the opening line and approach entirely | Context makes it obvious |
| 5 | Do you want to keep it short and introductory, or include more detail and proof? | Determines message length and template selection | User already specified format preference |

**Ask up to 4 questions per batch.** Stop as soon as you have enough to write a confident sequence.

### 5. Select Templates & Build the Sequence

Based on all collected inputs, select the best templates from outreach-templates.md:

**Template Selection Logic:**

| Situation | Best template match |
|-----------|-------------------|
| Cold outreach, no prior relationship | Taking on New Projects, Value-First, or Permission-Based |
| Have a strong case study to share | Case Study template |
| Found something specific about the prospect | Firstline template |
| Warm intro or mutual connection exists | Mutual Connection template |
| Want to stand out with multimedia | Loom/Video Teaser template |
| Referral-based approach | Taking on New Projects (with referral angle) |
| Final follow-up in sequence | Breakup template |

**Sequence Structure (default 3 messages):**

- **Message 1 (Day 1):** Initial outreach — the hook. Use the strongest template for the situation.
- **Message 2 (Day 3-4):** Follow-up — add value, share proof, or reframe the ask. Never just "bumping this up."
- **Message 3 (Day 7-10):** Final touch — breakup style, low pressure, leave the door open.

If the user requests more or fewer messages, adjust accordingly.

### 6. Write the Sequence

For each message in the sequence:
1. **Start from the selected template** as your structural base
2. **Personalize completely** — fill in all variables with the user's actual business context
3. **Follow all Writing Rules** below
4. **Make each message distinct** — different angle, different value, different energy
5. **Include clear next steps** — every message needs a soft CTA

### 7. Format and Verify
- Structure output according to **Output Format** section
- Complete **Quality Checklist** self-verification before presenting output
- Read each message out loud in your head — if it sounds like a template or like AI wrote it, rewrite it

---

## Writing Rules
Hard constraints. No interpretation.

### Core Rules
- **Sound human.** If it reads like a template, it's bad. Every message should feel like one person wrote it to one other person.
- **No em dashes.** Never use "—" in outreach messages. Use commas, periods, or line breaks instead.
- **No AI slang.** Never use: "leverage", "streamline", "utilize", "synergy", "cutting-edge", "game-changer", "revolutionize", "empower", "spearheaded", "delve", "I hope this

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 outreach-specialist

What does the outreach-specialist skill do?
Claude skills for founders
Is outreach-specialist 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 outreach-specialist 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 2026-10-27. 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.