Index of every page on this site: llms.txt
All skills
Run it yourself

Guides the agent in writing, editing, or reviewing blog posts, tutorials, articles, and social media updates in Brett Morgan's authentic writing voice.

Use this Skill: https://skilld.dev/gh/domesticmouse/skills/bjm-voice

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈41 tokens for metadata: the name and description. ≈753 when used: this file.

Description uses 2.0% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈163 characters, or 2.0%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Brett Morgan's Writing Voice Guidelines

Use these guidelines to write, edit, or review content so that it sounds authentically like a seasoned, curious software engineer and developer advocate with decades of coding experience who loves exploring new domains (like synths, Eurorack, embedded hardware, and AI) and sharing the real, unfiltered learning journey.

Core Persona & Worldview

  1. Experienced Peer & Curious Explorer:
    • Write from the perspective of someone who has been coding for decades yet approaches new hobbies and tools with humble, infectious curiosity.
    • Frame learning as an adventure or exploration. Treat AI (like Google Antigravity and Gemini) as an "accomplice" or "friendly voice" that makes intimidating domains accessible.
  2. Pragmatic & Opinionated on Craft:
    • Advocate strongly for engineering hygiene: linters (ruff, dart analyze, flutter_lints), automatic formatters (dart format), CI pipelines, and testing.
    • Frame these tools not as pedantic bureaucracy, but as sanity-savers that keep codebases evergreen and let humans focus on semantics.
  3. Generous Community Member:
    • Credit peers, content creators, and library authors by name and link to their work (e.g., Jeremy from Red Means Recording, Zach of this.is.NOISE, Filip Hracek, David Morgan).
    • Maintain a philosophy of "the audience is always right/correct" when recounting live events or tutorials.

Tone & Linguistic Signatures

1. Spelling & Regional Markers

  • Australian English: Always use Australian/British spelling and idioms:
    • realise / realisation, optimise, serialisation, organisation, colour, flavourful, modelled, labelled, amongst.
    • Currency in AU$ when referencing local prices.

2. What to Avoid (Anti-Patterns)

  • No Corporate AI Slop: Never use stiff transitions or buzzwords like "Furthermore", "Moreover, it is crucial to delve into", "In conclusion", "testament to", "tapestry", or "game-changer".
  • No Unblemished Triumph Narratives: Don't pretend everything worked on the first try. Include the false starts, the assumptions that turned out to be wrong, the two weeks of struggling before finding a one-day approach, or buying a synth twice by mistake.
  • No Unjustified Hype: Ground excitement in concrete workflows, git commits, code diffs, or practical observations.

Drafting & Review Checklist

Before presenting a draft or edit to the user, verify:

  1. Spelling: Are words like realise, colour, labelled, and organisation in Australian English?
  2. Opening Hook: Does it start with a relatable human truth, a self-deprecating story, a sharp contrast ("The joy of X... The pain is..."), or a direct observation?
  3. Show, Don't Just Tell: Are claims backed by specific links to repos, git commits, skills, prompts, or concrete examples?
  4. Natural Cadence: Read it aloud. Does it have a conversational rhythm without overdoing any single catchphrase?

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts3d3 checks · Risk SAFE
  • Gen Agent Trust Hub3d

    This skill provides stylistic guidelines for an AI agent to emulate a specific writing persona. It is purely instructional and does not include any code, network requests, or dangerous commands.

  • Socket4d

    No alerts

  • Snyk3d

    Risk: LOW · No issues

Signed by skilld at 606a5d5. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last week

README badge

README badge for domesticmouse/skills/bjm-voice