agentsclimarketplace
Sign in

Default business casual pipeline

Skill Brennan-Lewis/writers_voice/skills/default-business-casual-pipeline

Run a two-stage writing revision that removes formulaic AI patterns and then applies a gender-neutral business-casual voice. Use when drafting or polishing professional prose for publication, email, leadership, client, or internal audiences and both naturalness and a consistent voice matter.From its SKILL.md

Install
npx -y skills add Brennan-Lewis/writers_voice --skill default-business-casual-pipeline

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 22 days oldThe repository was created 22 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.6 KB, 478 tokens by cl100k_base, as published. Nobody here has run it

Default Business Casual Pipeline

Run humanize-writing first and default-business-casual second. Keep the stages distinct so the voice pass starts from clean prose rather than decorating formulaic structure.

Required skills

  • humanize-writing
  • default-business-casual

Use the runtime's native skill invocation mechanism. If the runtime cannot invoke one skill from another, load the two named SKILL.md files and follow them in the required order.

Run the pipeline

  1. Capture the source contract.

    • Identify the audience, format, purpose, intended action, and requested tone.
    • Record a fact ledger: names, dates, numbers, commitments, capabilities, causes, constraints, quotations, citations, first-person experiences, and uncertainty.
    • Preserve the original text for final comparison.

  2. Run humanize-writing.

    • Pass the complete source text and the editing context into the skill.
    • Remove formulaic AI-style patterns without applying a branded or personal voice.
    • Return the complete humanized draft and the unchanged fact ledger.

  3. Run default-business-casual.

    • Pass the complete humanized draft, audience, format, purpose, and fact ledger into the skill.
    • Apply the voice to structure, rhythm, vocabulary, and framing.
    • Do not restore inflated language or mechanical patterns removed in the first stage.

  4. Verify against the original.

    • Compare the final draft with the source and fact ledger.
    • Confirm that facts, citations, ownership, commitments, uncertainty, and first-person boundaries survived both stages.
    • Remove any new claim, experience, or certainty that the source does not support.
    • Read the result aloud mentally for rhythm and plausibility.

Do not collapse the stages

  • Do not summarize the draft between stages.
  • Do not run the voice pass first.
  • Do not ask the second skill to "make it more human"; give it the already-humanized draft and ask only for the target voice.
  • Do not optimize for an AI detector or promise that the result is undetectable.

Return the result

Return the final draft first. Add a short change note only when it helps the user review a substantive decision. Keep intermediate drafts private unless the user asks to compare them.

What ships with it: 1 file

261 B alongside SKILL.md

agents/

Keep looking

Skills are one crate of 326,422. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.