Github Profile logo

Github Profile

Community
jdevalk
github-profile

Audits and optimizes GitHub profile pages — profile README, metadata fields, pinned repositories, stats widgets, and contribution visibility. Use this skill whenever the user asks to improve, create, review, or optimize their GitHub profile, or mentions "profile README", "GitHub bio", "pinned repos", "GitHub stats", "contribution graph", or "GitHub presence". Also trigger when someone says things like "make my GitHub look good", "I want a better GitHub profile", "help me stand out on GitHub", "set up my GitHub page", or "optimize my developer profile". Works for both personal profiles and organization profile pages.

Overview

Publisherjdevalk
Repositoryskills
Skill namegithub-profile
Stars
109
Forks
10
Bundled files
2
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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Github Profile 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.
    https://github.com/jdevalk/skills/tree/main/github-profile
  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/jdevalk/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/github-profile .claude/skills/github-profile
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Github Profile 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 Github Profile 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 Github Profile 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.

GitHub Profile Optimizer

This skill audits a GitHub profile and generates an optimized profile README along with recommendations for metadata, pinned repositories, and stats widgets. A strong GitHub profile is a developer's storefront — it shapes perception before anyone reads a line of code.

Code recipes live in AGENTS.md — read it when you need to implement a specific fix. This file has the workflow and audit checklist.

Workflow

  1. Gather profile context — Understand who this person/org is and what they want to showcase
  2. Audit the current profile — Score every element of the profile's public presence
  3. Generate the profile README — Write a polished, scannable README.md
  4. Recommend metadata and configuration — Advise on bio, pinned repos, settings, and widgets
  5. Verify — Confirm rendering, badge URLs, and summarize next steps

Phase 0: Gather Context

Determine profile type

Ask the user (if not obvious): is this a personal profile or an organization profile? The mechanics differ significantly:

FeaturePersonal profileOrganization profile
README locationusername/username/README.md.github/profile/README.md
Visibility optionsPublic onlyPublic + member-only (via .github-private repo)
Pinned reposUp to 6Up to 6 public + 6 member-only
Contribution graphYesNo
AchievementsYesNo

Collect information

Gather before writing: username, current role/company, primary technologies, what they want to showcase, tone (professional/casual/creative/minimal), and target audience (recruiters/collaborators/investors/OSS community).

If gh is available (gh auth status), pull automatically:

  • gh api user — name, bio, company, location, blog, twitter
  • gh api users/{username}/repos?sort=stars&per_page=10 — top repos for pin recommendations
  • gh repo view {username}/{username} --json name 2>/dev/null — check if magic repo exists

Phase 1: Audit

If the user has an existing profile, audit it. If they're starting fresh, skip to Phase 2. Score four categories (each x/10, total x/40):

Profile README (x/10)

  • Exists? No username/username repo with README.md is the biggest miss.
  • Structure — Ideal flow: greeting/identity → current work → tech stack (badges) → GitHub stats → featured projects → social links → personal touch.
  • Length — 400-800 words. Under 200 feels thin; over 2,000 clutters.
  • Scannability — Gist in 10 seconds? Use <details> for collapsible sections.
  • Freshness — Dynamic content still updating? GitHub stops cron Actions after 60 days of repo inactivity.

Profile Metadata (x/10)

Every empty field is a missed opportunity:

  • Photo — clear headshot, consistent across platforms?
  • Bio — filled in (160 char limit), states role + primary tech + distinguishing trait?
  • Company — linked with @ prefix? Location, Website — filled in?
  • Social accounts — Twitter/X, LinkedIn linked? Cross-linking builds trust.
  • Pronouns — signals inclusivity. Status — shows current work or availability?

Pinned Repositories (x/10)

Up to 6 repos (including contributed-to repos):

  • All 6 slots used? Descriptions filled in? Variety across technologies?
  • Prioritize repos with stars (social proof) that align with career/business goals.
  • Each pinned repo should have a polished README (github-repo skill applies here).

Contribution Activity (x/10)

  • Graph — reasonably active? Completely empty raises questions.
  • Private contributions — "Include private contributions" enabled in settings?
  • Achievements — Starstruck, Pull Shark, Arctic Code Vault Contributor add credibility.

Phase 2: Generate the Profile README

Based on the audit (or from scratch), produce the profile README. Read AGENTS.md for detailed recipes.

The profile README should be scannable, personal, and purposeful — every section should serve the person's goals. Adapt tone and structure to the audience.

AGENTS.md sections: Personal profile README template, Stats widgets, Badges for tech stack and social links, Dynamic auto-updating content, Organization profile README, Profile generators.


Phase 2.5: Metadata and readability pass

  1. metadata-check skill — run on the GitHub bio (160 chars) and any pinned repo descriptions you rewrote. Front-loading, concreteness, active voice, truncation fit (GitHub shows ~100 chars in profile cards).
  2. readability-check skill — run on the profile README body. Profile READMEs are skimmed; one passive or long sentence stands out.

Apply fixes directly. Focus on: (1) bio / opening README line (disproportionate weight); (2) first sentence of each section (skimming entry point); (3) passive voice (flat in first-person content).


Phase 3: Recommendations

Metadata to update

Be specific: "Set your bio to: [text, under 160 chars]", "Add these topics to your top repos: [list]", "Set your status to: [suggestion]".

Pinned repository strategy

Recommend which 6 repos to pin and why — variety across technologies, star count (social proof), README quality, alignment with goals. If pinned repos have weak READMEs, suggest improving those first (github-repo skill).


Phase 4: Verify

  • Confirm the README renders correctly (check markdown syntax, badge URLs, image links)
  • Check that all shields.io badge URLs are valid (correct logo names, hex colors)
  • Verify stats widget URLs use the correct username
  • If generating locally, remind the user to create the magic repo (username/username) if it doesn't exist, and push the README there
  • Summarize next steps: what to commit/push, what to change in GitHub settings manually

Output format

Score table (4 categories, each x/10, total x/40) → Findings grouped by category → Files generated or changed → Next steps (settings changes, repos to pin, manual GitHub config).


Key principles

  • Scannable over comprehensive. A profile is skimmed in 10 seconds. Cut anything that doesn't earn its space.
  • Personality over template. Adapt tone, structure, and content to the person's goals and audience. A creative developer and a startup founder need different profiles.
  • Every field filled. Empty metadata fields, missing pinned repos, and blank descriptions are missed opportunities.
  • Dynamic where it adds value. A stats image (via lowlighter/metrics) and an optional auto-updating blog feed keep a profile fresh — one of each is usually plenty. Avoid third-party-hosted widgets that 502 unpredictably; see AGENTS.md.
  • Cross-link everything. GitHub, LinkedIn, Twitter/X, personal site — each profile should point to the others.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Github Profile AI skill do?

Audits and optimizes GitHub profile pages — profile README, metadata fields, pinned repositories, stats widgets, and contribution visibility. Use this skill whenever the user asks to improve, create, review, or optimize their GitHub profile, or mentions "profile README", "GitHub bio", "pinned repos", "GitHub stats", "contribution graph", or "GitHub presence". Also trigger when someone says things like "make my GitHub look good", "I want a better GitHub profile", "help me stand out on GitHub", "set up my GitHub page", or "optimize my developer profile". Works for both personal profiles and o...

Why use Github Profile on TypingMind?

Because you install it once and use it with any model. Github Profile 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 Github Profile in TypingMind?

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

Which AI models can use Github Profile?

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 Github Profile?

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

Is the Github Profile AI skill free?

Yes. It is published on GitHub by jdevalk 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 👇