Galactic Cv logo

Galactic Cv

Community
GuidoPenta
galactic-cv

Reviews, rewrites and tailors a CV with Guido Penta's Galactic CV guide, and scores it against a job posting like a screener would. Use when the user shares a CV or asks to fix, tailor or rewrite it.

Overview

PublisherGuidoPenta
Repositorythe-candidates-guide-to-the-galaxy
Skill namegalactic-cv
Stars
50
Forks
3
Bundled files
4
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.

  • 4 bundled files

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

  • Open source

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

Installation

Install the Galactic Cv 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/GuidoPenta/the-candidates-guide-to-the-galaxy/tree/main/.claude/skills/galactic-cv
  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/GuidoPenta/the-candidates-guide-to-the-galaxy.git /tmp/the-candidates-guide-to-the-galaxy
mkdir -p .claude/skills
cp -r /tmp/the-candidates-guide-to-the-galaxy/.claude/skills/galactic-cv .claude/skills/galactic-cv
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Galactic Cv 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 Galactic Cv 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 Galactic Cv 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.

Galactic CV

Knowledge:

  • references/cv-guide.md: rules from galactic-CV-guide-for-developers.
  • references/recruiter-rubric.md: how a screener scores a CV against a posting, adapted from cv-review by Matteo Baccan.
  • references/rewrite-guide.md: how to rewrite.
  • references/ats.md: how ATSs really work, myths vs evidence, LinkedIn Easy Apply vs company site. Workspace layout: .claude/skills/galactic-job-search/references/workspace.md.

Source labels

Every rule in the references is tagged: [Guido] (his guide, with §), [cv-review] (Matteo Baccan's screener rubric), [Di Fresco] (typography guidelines), [pack] (this pack's own / general practice).

  • Say "your guide / Guido's guide says…" only for [Guido] items.
  • Present [cv-review] items as "a structured screener (cv-review) may look for…", and [pack] items as general advice.
  • When [Guido] and [cv-review] conflict, [Guido] wins and [cv-review] items are never forced (e.g. never force a numeric result into a bullet: Guido's own sample bullets describe duties).

Input

  • The CV comes from workspace/cv/original/ or a paste. You can read PDF, images (PNG/JPG), Markdown and text directly. For DOCX, ask for a PDF export or pasted text. With a PDF or an image you can also judge layout and typography (Block C). An image CV is fine to review; the only point worth noting is that links in an image aren't clickable.
  • No residence on the CV: never suggest adding the city of residence/domicile or a home address; the guide doesn't ask for it. Location matters only as availability (remote, relocation), and it goes in profile.md, not on the CV.
  • ATS questions ("what is an ATS?", "will my CV pass the ATS?", "LinkedIn or company site?"): answer from references/ats.md, which is sourced and tagged; keep its "documented / varies / anecdotal" nuance and quote Guido's take where relevant. Otherwise say only what references/cv-guide.md says (recruiters read every CV, the ATS is a filtering tool, stars and progress bars may not be recognised, keywords matter). Don't add myths about what ATSs can't read, such as images, PDFs or columns, or promise an "ATS-proof" CV.
  • File names and locations always follow .claude/skills/galactic-job-search/references/workspace.md, even where a reference file suggests a different one.
  • Read workspace/profile.md for target roles and market.

Modes

1. General review (no posting)

Apply every checklist in references/cv-guide.md, plus Blocks B (content) and C (typography) of the rubric. Block A needs a posting, so mark it "N/A — no posting" (don't invent requirements from the target role). Output goes to workspace/cv/reviews/YYYY-MM-DD-review.md, using the rubric's report structure, opening with:

  • Top 3 fixes that would change the outcome most, first.
  • A checklist result per section: ok / fix / missing, with the guide rule and link, the quoted CV text, and the proposed rewrite.
  • Protected data found: for the photo, Guido's guide leaves it to the user (§2, free choice); for the rest (age, date of birth, marital status, nationality…) say only that a structured screener (cv-review) ignores them. Keeping any of it is the user's call.

2. Targeted review (with a posting)

Run the rubric's Block A against the posting in workspace/applications/<app>/posting.md, or a pasted one. Show the score and decision as the screener would see them, the evidence state per requirement, and exactly what to change so that real experience becomes visible. If galactic-application already wrote fit.md, extend it rather than duplicating it.

3. Rewrite

Follow references/rewrite-guide.md (written for the targeted one-page version). Produce Markdown:

  • targeted → workspace/applications/<app>/cv.md, ready to send. Language: posting in Italian → CV in Italian or English, both fine; posting in English → CV necessarily in English (ask which the user prefers);
  • untargeted → workspace/cv/cv-master.md, complete and long. It's a working file, so the rewrite guide's "no placeholders" rule (I2, [cv-review]) doesn't apply: open questions go in a final ## Open questions section. Rewrite notes go to workspace/cv/reviews/YYYY-MM-DD-rewrite-notes.md, never next to the original. Show a diff-style summary of what changed and why. Tell the user how to turn the Markdown into a PDF with the tool of their choice, saving the PDF inside workspace/ (Word/Google Docs paste, a Markdown editor, pandoc). This pack ships no scripts.

4. Build the master CV

When the CV is thin, interview the user one role at a time: what they built, for whom, the scale, the results and numbers, the stack. Write cv-master.md as the long, honest source every targeted CV is cut from.

Hard rules

  • Never invent experience, metrics, titles or dates. When a bullet lacks a result, ask: "do you have a number for this? users, latency, revenue, time saved…". If there is none, write an honest bullet without one.
  • Quote the CV when criticising it, so every judgement is traceable.
  • Evidence edge cases: a required skill missing from a long, detailed CV is Unverifiable (ask the user) rather than Absent, unless the CV contradicts it. A vague certification (no issuer, no year) counts as Inferred at best (undated, so not Verified); ask for issuer and year — the answer makes it Declared.
  • Judge the document, not the person. Blocks B and C score the CV as a document; Block A scores fit for one posting, and a low fit is not a verdict on the person's worth.
  • After a rewrite, suggest aligning LinkedIn (galactic-linkedin).

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 Galactic Cv AI skill do?

Reviews, rewrites and tailors a CV with Guido Penta's Galactic CV guide, and scores it against a job posting like a screener would. Use when the user shares a CV or asks to fix, tailor or rewrite it.

Why use Galactic Cv on TypingMind?

Because you install it once and use it with any model. Galactic Cv 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 Galactic Cv in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/GuidoPenta/the-candidates-guide-to-the-galaxy/tree/main/.claude/skills/galactic-cv. 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 Galactic Cv?

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 Galactic Cv?

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

Is the Galactic Cv AI skill free?

It is published on GitHub by GuidoPenta. Check the repository for licensing terms. 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 👇