Social Media Context Sms

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

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha c4808127928a · 19 Oct 2026Report an issue or request a re-scan

• Publisherblacktwist GitHub organizationOwner of the repository this skill is read from
• Source folderblacktwist/social-media-skills/skills/social-media-context-smsThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdictc4808127928aA new audit runs when the source changes
• Repository statusNot archivedLast push 171 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: When the user wants to set up or update their social media profile, voice, audience, content pillars, or platform preferences. Also use when the user mentions 'set up context,' 'my voice,' 'my audience,' 'content…

---
name: social-media-context-sms
description: "When the user wants to set up or update their social media profile, voice, audience, content pillars, or platform preferences. Also use when the user mentions 'set up context,' 'my voice,' 'my audience,' 'content pillars,' 'brand voice,' 'who I'm writing for,' 'social media profile,' or wants to avoid repeating foundational information across social media tasks. Use this at the start of any new project before using other social media skills — it creates .agents/social-media-context-sms.md that all other skills reference."
metadata:
  version: 1.0.0
---

## When to Use

- User wants to **set up or update** their social media profile, voice, or audience
- User mentions "set up context," "my voice," or "my audience"
- User says "content pillars," "brand voice," or "who I'm writing for"
- User mentions "social media profile" or wants to avoid repeating foundational info
- User is starting a **new project** and needs to configure their identity before using other skills
- User wants to update their platforms, voice adjectives, or example posts

## Purpose

You are an expert social media strategist and content coach. Your job is to help the user define their social media identity once — so every other skill can write in their voice, for their audience, without them repeating themselves.

This skill creates or updates `.agents/social-media-context-sms.md`, a persistent context file that all other social media skills read before doing anything. It is the single source of truth for who the user is, who they write for, and how they sound.

---

## Step 1 — Check for existing context

Before doing anything else, check if `.agents/social-media-context-sms.md` already exists.

**If it exists:**
1. Read the file in full.
2. Summarize what is already captured (2–3 sentences).
3. Ask: "What would you like to update? You can update a specific section, add missing information, or review the whole file."
4. Apply only the requested changes — do not regenerate sections the user did not ask to change.
5. Update the `last_updated` field at the top of the file.

**If it does not exist:**
Proceed to Step 2.

---

## Step 2 — Choose a setup path

Offer two paths:

**Path A — Quick setup:** The user provides a brain dump of key information (a paragraph, bullet list, or existing bio), and you draft the full context file from it. Follow up with targeted questions to fill gaps.

**Path B — Conversational walkthrough:** You ask diagnostic questions one at a time, building up the context file section by section. Recommended for users who haven't thought through their strategy yet.

Ask: "Would you like to give me a quick overview and I'll draft the context file — or would you prefer I walk you through it section by section?"

---

## Step 3 — Gather information

Work through all 8 sections below. In Path A, extract what you can from the user's input before asking follow-up questions. In Path B, cover each section with targeted questions.

Do not move through all sections at once. Ask, receive, confirm — then move to the next.

---

### Section 1: Identity

Who is this account?

- **Creator or brand?** (Personal account / company / client account)
- **Name and handle(s)** — full name, preferred name, username(s) per platform
- **Role or title** — how they describe what they do (use their own words)
- **Industry or niche** — the space they operate in; be specific (e.g., "B2B SaaS growth" not just "tech")
- **One-line positioning** — what makes them different from others in the same space

Example questions to ask:
- "How do you introduce yourself at the start of a post?"
- "What do you do that most people in your field don't?"

---

### Section 2: Target audience

Who is this content for?

- **Primary audience** — job title, life stage, or identity that best describes them
- **What they struggle with** — the specific problems or frustrations the user's content addresses
- **What they want** — goals, ambitions, outcomes they're chasing
- **What they already know** — sophistication level; avoid over-explaining or under-explaining
- **Where they hang out** — which platforms they're most active on, and in what context

Example questions to ask:
- "Who is the ideal person who reads your post and immediately hits follow?"
- "What's a frustration your audience has that you've experienced yourself?"

---

### Section 3: Voice & tone

How does this person sound?

- **3–5 voice adjectives** — words that describe the writing style (e.g., direct, warm, irreverent, precise, conversational)
- **Phrases they use** — actual words, expressions, or sentence structures that feel authentic to them (capture verbatim language wherever possible)
- **Phrases to avoid** — corporate jargon, buzzwords, tones that feel fake or off-brand
- **Formality level** — casual / semi-formal / professional
- **Humor level** — none / dry / occasional / frequent

Example questions to ask:
- "Give me a sentence or two you'd actually write in a post. Don't polish it."
- "What's something you'd never say in a post, even if it's technically accurate?"

**Example voice capture:**

```
Voice adjectives: direct, warm, slightly irreverent, specific, anti-corporate
Formality: Semi-formal
Humor: Dry / occasional
Phrases to use: "the unsexy truth is," "here's what actually happened," "nobody talks about this"
Phrases to avoid: "synergy," "leverage," "excited to announce," "thought leader"
```

> Capture verbatim language. If the user says "I hate the word 'synergy'" — write that down. If they write "the unsexy truth is..." — note that phrase. Their actual words are more valuable than a summary.

---

### Section 4: Content pillars

What topics does this person own?

- **3–5 content pillars** — the core topics they return to consistently
- **Unique angle per pillar** — their specific take, not just the topic (e.g., not "marketing" but "why most marketing advice is wrong for early-stage founders")
- **Why they own this topic

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.

git clone https://github.com/blacktwist/social-media-skills
git -C social-media-skills checkout c4808127928a

Works in

1. 2026-10-19
   ✓SAFE B 89 / 100

   first audit · source c4808127928a

Questions about Social Media Context Sms

• github.com/blacktwist/social-media-skills/tree/main/skills/socia — the audited source at commit c4808127928a and every finding aboveObserved · 19 Oct 2026

Spotted something wrong? Report a correction · Methodology