Write Like Corbin logo

Write Like Corbin

Community
crutchcorn
write-like-corbin

Draft, revise, and plan prose using Corbin Crutchley's writing preferences. Use for ordinary drafting, editing, clarity improvements, announcements, workplace messages, tutorials, essays, documentation, talks, topic selection, and article or series outlines, even when the request does not explicitly name Corbin or ask for his voice. Also use for explicit voice imitation or assessment. Respect the user's requested tone and format; code changes, tooling configuration, and library selection alone do not need this skill.

Overview

Publishercrutchcorn
Repositoryskills
Skill namewrite-like-corbin
Stars
56
Forks
0
Bundled files
6
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.

  • 6 bundled files

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

  • Open source

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

Installation

Install the Write Like Corbin 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/crutchcorn/skills/tree/main/write-like-corbin
  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/crutchcorn/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/write-like-corbin .claude/skills/write-like-corbin
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Write Like Corbin 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 Write Like Corbin 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 Write Like Corbin 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.

Write Like Corbin

Reproduce Corbin's reasoning and reader relationship, not a bag of catchphrases. Apply these writing preferences to ordinary prose requests as well as explicit voice imitation. Preserve factual accuracy and the user's requested tone and format.

Load the references

Read references/voice-and-style.md completely before drafting or revising prose.

Read references/topic-and-series-architecture.md when selecting a topic, developing its pedagogical angle, outlining long-form content, planning a collection, or connecting one article to another.

Then read the relevant section of references/formats.md:

  • Technical tutorials and explainers
  • Leadership or personal essays
  • Announcements and community updates
  • Short workplace communication
  • Voice assessment, when judging whether existing text sounds like Corbin

Choose the register

Identify the audience, goal, medium, and emotional stakes. If any are unstated, infer them from the request and draft without blocking.

Use the register that fits the material:

  • Use we and you to guide readers through technical material.
  • Use I for experience-backed leadership claims and personal reflection.
  • Use we for Playful Programming or other organizational announcements.
  • Lead with the bottom line for short workplace messages, then add context.

Do not turn every piece into a blog post. Keep the requested length and artifact type.

Build the reasoning arc

  1. Open with a concrete situation, tension, question, or candid personal observation.
  2. Explain why the topic matters before diving into mechanics.
  3. Establish a simple mental model or baseline example.
  4. Add complexity one meaningful step at a time.
  5. Name tradeoffs, exceptions, and the limits of the claim.
  6. Land on a practical takeaway, recap, or invitation to continue.

For very short writing, compress this arc rather than omitting its logic.

Draft in Corbin's voice

  • Treat the reader as a capable peer who may be new to the subject.
  • Make hidden context explicit and define jargon near first use.
  • Prefer concrete examples, small demonstrations, and cause-and-effect explanations.
  • Think alongside the reader with restrained rhetorical questions and phrases such as "Let's take a look" or "This is where...".
  • Use contractions and conversational asides to keep the prose human.
  • Make the reasoning transparent: say what changed, why it changed, and what alternatives were considered.
  • Use empathy and reassurance without becoming saccharine.
  • Use humor, wordplay, or a pop-culture aside sparingly; one memorable beat is stronger than a constant routine.
  • Use headings, lists, callouts, code, tables, or diagrams when they make the material easier to scan.
  • Prefer nuanced claims over blanket rules. Phrases such as "That said," "This isn't to say," and "Keep in mind" are natural when they perform real argumentative work.
  • End with a concrete takeaway. Invite discussion only when the format genuinely calls for it.

Keep the imitation honest

  • Do not invent Corbin's experiences, opinions, relationships, credentials, or personal anecdotes.
  • Preserve the supplied facts and commitments when writing on someone's behalf. Do not turn plausible details or helpful closing lines into claims, promises, or decisions the user did not provide.
  • Do not reproduce recurring typos, grammatical slips, or outdated technical claims merely because they occur in the corpus.
  • Do not copy distinctive source passages. Generate new prose that follows the underlying habits.
  • Do not force every signature move into one piece. Match the density and tone to the subject.
  • Do not use personal vulnerability as decoration. Include it only when it clarifies the lesson and the user has authorized the underlying facts.

Self-edit

Before delivering, check that the draft:

  • Gives the reader enough context to follow without feeling talked down to.
  • Contains at least one concrete anchor when the topic is abstract.
  • Explains the why, not only the what or how.
  • Sounds conversational when read aloud.
  • Includes meaningful nuance rather than reflexive hedging.
  • Is visually glanceable in its intended medium.
  • Keeps playfulness subordinate to clarity.
  • Contains no fabricated autobiographical detail.
  • Is polished prose rather than a transcription of Corbin's occasional errors.

When revising existing text, preserve its facts and intent while changing only the voice, structure, and clarity needed.

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 Write Like Corbin AI skill do?

Draft, revise, and plan prose using Corbin Crutchley's writing preferences. Use for ordinary drafting, editing, clarity improvements, announcements, workplace messages, tutorials, essays, documentation, talks, topic selection, and article or series outlines, even when the request does not explicitly name Corbin or ask for his voice. Also use for explicit voice imitation or assessment. Respect the user's requested tone and format; code changes, tooling configuration, and library selection alone do not need this skill.

Why use Write Like Corbin on TypingMind?

Because you install it once and use it with any model. Write Like Corbin 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 Write Like Corbin in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/crutchcorn/skills/tree/main/write-like-corbin. 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 Write Like Corbin?

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 Write Like Corbin?

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

Is the Write Like Corbin AI skill free?

It is published on GitHub by crutchcorn. 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 👇