Profile Optimizer logo

Profile Optimizer

CommunityPopular
charlie947
profile-optimizer

Rebuild a LinkedIn profile for maximum conversions. Produces new headline options, about section, experience section, featured section strategy, and 4 image generation prompts (banner, profile picture, 2 featured tiles). Use this skill whenever the user says "optimize my profile", "fix my LinkedIn", "rewrite my headline", "profile review", "LinkedIn audit", "rebuild my profile", or wants help with any part of their LinkedIn profile. Also trigger when the user uploads a LinkedIn profile PDF or screenshot for review.

Overview

Publishercharlie947
Repositorysocial-media-skills
Skill nameprofile-optimizer
Stars
3.6K
Forks
836
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by charlie947 on GitHub. Read the source before you install it.

Installation

Install the Profile Optimizer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/charlie947/social-media-skills.git /tmp/social-media-skills
mkdir -p .claude/skills
cp -r /tmp/social-media-skills/skills/profile-optimizer .claude/skills/profile-optimizer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Profile Optimizer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Profile Optimizer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Profile Optimizer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Profile Optimizer

Codex and Claude runtime

  • Use this skill in Codex or Claude with the tools actually available in the current task. AskUserQuestion examples describe the questions, not a required API: use an available question tool within its limits, or ask in chat. Reuse answers and source material already supplied.
  • Work in the user-selected project. Read its about-me.md, voice.md and relevant brand files before personalised work. Confirm the intended author if files conflict or contain starter defaults. Ask for missing facts or run voice-builder; never inherit the maintainer's identity, accounts or private files.
  • Resolve bundled references/ relative to this skill folder. For an explicitly requested profile refresh, read and update the canonical about-me.md, voice.md or newsletter-voice.md in place, preserving unrelated user facts and rules. Consumers must reread those canonical files. Use a new filename only for new deliverables that would collide with unrelated existing files. Installation alone never starts an interview or writes files. Do not write persistent learnings unless requested.
  • Use supplied evidence first. Verify external claims through available search/source tools when needed. If a source or integration is unavailable, name the missing capability and offer supplied text/export input. Never invent facts, first-person experience, metrics or a successful tool run.
  • Connect only services needed for the chosen route through the user's existing account. Never print credentials or overwrite connections. Drafting, saving and reviewing do not authorise publishing, sending messages or changing accounts.

Visual completion state

This skill's image prompts are prompt-ready, not generated or visually reviewed assets. Keep its named Gemini workflow unless the user requests another generator. A missing image service does not block writing a prompt. When images are supplied or generated, open and inspect each export at full size and feed size (about 360px wide, 320px for thumbnails). Check exact copy, dimensions, clipping, legibility, brand colours, font appearance, logos and reference fidelity. Fix and re-inspect failed exports. Record any unavailable export or inspection as pending. An image prompt or raster export is not an editable design file.

CRITICAL: Auto-start on load

When this skill triggers, go straight to Step 1. Do not summarise. Do not explain what you will produce. Start input gathering immediately.

Step 1. Gather inputs

Check the project for about-me.md. If it exists, pre-fill name, audience, topics, and POV from it. Skip those questions and tell the user what you pulled.

Call AskUserQuestion in two batches.

Batch 1

json
[
  {
    "question": "What is the primary goal of your LinkedIn presence?",
    "header": "Goal",
    "multiSelect": false,
    "options": [
      {"label": "Booked calls", "description": "Drive discovery calls or demos"},
      {"label": "Inbound leads", "description": "Attract prospects who reach out to you"},
      {"label": "Newsletter subscribers", "description": "Grow your email list from LinkedIn"},
      {"label": "Job opportunities", "description": "Get recruiters and hiring managers to reach out"}
    ]
  },
  {
    "question": "What is your main offer or service?",
    "header": "Offer",
    "multiSelect": false,
    "options": [
      {"label": "Coaching", "description": "1-on-1 or group coaching"},
      {"label": "Consulting", "description": "Advisory or strategy work"},
      {"label": "Agency services", "description": "Done-for-you services for clients"},
      {"label": "Freelance", "description": "Project-based or contract work"}
    ]
  },
  {
    "question": "Do you have brand colours (hex codes)?",
    "header": "Colours",
    "multiSelect": false,
    "options": [
      {"label": "No, suggest for me", "description": "Pick colours based on my positioning"},
      {"label": "Yes, I will paste them", "description": "I have specific hex codes to use"}
    ]
  },
  {
    "question": "Any social proof you want highlighted?",
    "header": "Proof",
    "multiSelect": false,
    "options": [
      {"label": "Years of experience", "description": "e.g. 10+ years in marketing"},
      {"label": "Client results", "description": "e.g. Helped 200+ clients"},
      {"label": "Media features", "description": "e.g. Featured in Forbes"},
      {"label": "I will type my own", "description": "Let me paste specific proof points"}
    ]
  }
]

Batch 2

json
[
  {
    "question": "What external links do you want in your Featured Section? (max 2)",
    "header": "Links",
    "multiSelect": false,
    "options": [
      {"label": "Booking page + newsletter", "description": "Primary link to book calls, secondary to subscribe"},
      {"label": "Portfolio + booking page", "description": "Show work first, then convert"},
      {"label": "I will paste URLs", "description": "I have specific links to use"}
    ]
  },
  {
    "question": "How should I get your current profile?",
    "header": "Current profile",
    "multiSelect": false,
    "options": [
      {"label": "I will paste it", "description": "I will copy-paste my headline, about, and experience"},
      {"label": "Start fresh", "description": "Ignore my current profile, build from scratch using my about-me.md"},
      {"label": "I will upload a screenshot", "description": "I will share a screenshot or PDF of my profile"}
    ]
  }
]

Wait for all inputs before proceeding.

Step 2. The Headline

Write 3 headline options. Output in a code block.

Constraints:

  • Maximum 50 characters each
  • Sentence casing only (not Title Case)
  • Lead with core value
  • Include target audience where character count allows
  • No job titles (no "Founder" / "CEO" / "Designer")
  • No fluff words

Format: [Core value] + [for target audience]

Option 1 (Direct): [outcome + audience]
Option 2 (Pain-focused): [problem + audience]
Option 3 (Differentiator): [unique angle + audience]

Then call AskUserQuestion to let the user pick:

json
[
  {
    "question": "Which headline do you want to go with?",
    "header": "Headline",
    "multiSelect": false,
    "options": [
      {"label": "Option 1", "description": "[The actual headline text from above]"},
      {"label": "Option 2", "description": "[The actual headline text from above]"},
      {"label": "Option 3", "description": "[The actual headline text from above]"}
    ]
  }
]

Step 3. The About Section

Output in a code block. Formatting rules:

  • Write in full sentences. Do not force line breaks mid-sentence.
  • One line break between sentences or short phrases for readability.
  • Double line break between sections (hook, story, authority, CTA).
  • LinkedIn handles text wrapping on mobile and desktop. Do not manually wrap at 50 or 60 characters.
  • Short punchy sentences are good. Chopping sentences in half is not.

Structure: Hook > Struggle/Empathy > Method/Philosophy > Authority > CTA

Tone: Punchy, direct, human. Not corporate.

Formatting example only; replace with supplied facts, never invented biography:

[User’s real starting point, if supplied.]
[Their verified result, with the correct timeframe.]

[What they do and how that helps their audience.]
[One concrete example from their supplied experience.]

[Their current offer and confirmed next action.]

Step 4. The Experience Section

Rewrite the top 2 roles. Output in a code block. Same formatting approach as the About section: full sentences, no forced mid-sentence line breaks, LinkedIn handles wrapping.

Structure per role: Context > Challenge > Action > Result

Storytelling format, not bullet points. 8 to 15 sentences per role maximum.

Formatting example only; replace with supplied facts, never invented biography:

I walked into a team that had lost 3 managers in 2 years.
Morale was gone. Revenue was slipping.

I didn't start with strategy decks. I started with listening.

Within 6 months we rebuilt the culture.
Within 12 months revenue was up 40%.

That taught me everything about leading through chaos.

Example of incorrect formatting:

  • Managed a team of 15 sales representatives
  • Responsible for Q3 revenue targets
  • Implemented new CRM system

Step 5. Featured Section Strategy

2 items maximum. Both must be external links.

Item 1: Primary conversion goal

  • Purpose: direct path to main offer (booking page, application form, sales page)
  • Title: 3 to 5 words, benefit-focused

Item 2: Secondary value builder

  • Purpose: build trust or capture leads (newsletter signup, free resource, portfolio, case study)
  • Title: 3 to 5 words, benefit-focused

No subtitles. No internal LinkedIn posts. No "DM me" items.

Step 6. Visual Design Brief

Output 4 separate image generation prompts, each in its own code block. Each prompt must be fully self-contained and work when pasted into Gemini as a standalone request.

State the brand colours at the top:

  • Primary hex: [user-provided or suggested]
  • Secondary hex: [user-provided or suggested]
  • One line on why these fit the positioning

Asset 1: LinkedIn Banner (1584 x 396 pixels)

The prompt must:

  • State "Using the attached photo of me..."
  • Create banner at exact dimensions
  • Place the chosen headline text centre-right
  • Place a 5 to 8 word tagline below the headline
  • Include a CTA button element (3 to 4 words)
  • Include only social proof supplied and confirmed by the user; omit it when absent
  • Use brand colours
  • Specify background style

Asset 2: Profile Picture (400 x 400 pixels)

The prompt must:

  • State "Using the attached headshot photo as the base..."
  • Apply brand colour background (solid or gradient)
  • Centre face at 60 to 70% of frame
  • Work when cropped to a circle
  • Add brand colour border if appropriate

Asset 3: Featured Section Tile 1 (552 x 368 pixels)

  • Title text from Featured Item 1 as focal point
  • Brand colours matching the banner
  • Simple clickable visual cue (arrow icon)
  • Clean, minimal, no subtitle or body text
  • No photo needed

Asset 4: Featured Section Tile 2 (552 x 368 pixels)

  • Title text from Featured Item 2 as focal point
  • Visually distinct from Tile 1 (swap primary/secondary colour usage)
  • No photo needed

After all 4 prompts, say:

Copy each prompt into a new Gemini chat one at a time. For the banner and profile picture, attach your headshot alongside the prompt. The featured tiles do not need a photo.

Rules

  • Always read about-me.md if it exists and pre-fill inputs from it.
  • All profile copy (headline, about, experience) must go in code blocks.
  • Write full sentences. Do not force line breaks mid-sentence. LinkedIn handles wrapping.
  • No job titles in headlines.
  • No block paragraphs anywhere.
  • Each image prompt must be fully self-contained.
  • Never use em dashes.
  • British English throughout.
  • Do NOT offer to write a launch post or engagement strategy after the design brief. End at the design brief.

Frequently asked questions

What does the Profile Optimizer AI skill do?

Rebuild a LinkedIn profile for maximum conversions. Produces new headline options, about section, experience section, featured section strategy, and 4 image generation prompts (banner, profile picture, 2 featured tiles). Use this skill whenever the user says "optimize my profile", "fix my LinkedIn", "rewrite my headline", "profile review", "LinkedIn audit", "rebuild my profile", or wants help with any part of their LinkedIn profile. Also trigger when the user uploads a LinkedIn profile PDF or screenshot for review.

Why use Profile Optimizer on TypingMind?

Because you install it once and use it with any model. Profile Optimizer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Profile Optimizer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/charlie947/social-media-skills/tree/main/skills/profile-optimizer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Profile Optimizer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Profile Optimizer?

As many as you like. As long as a model supports skills, you can use Profile Optimizer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Profile Optimizer AI skill free?

Yes. It is published on GitHub by charlie947 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇