agentleFS
wtsi-hgiwtsi-hgi/agentskills/skills/unslop/SKILL.md

unslop

Skill1 starsChanged 41 days agoMITView on GitHub

Remove AI tells and enforce repository Markdown mechanics in specs, phase plans, checklists, docs, and READMEs. Use when writing or revising a Markdown file. Do not use for chat responses; final-response owns those.

197 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use principle-never-block-on-the-human, greploop-apps and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • jaydubya818Skill

    principle-never-block-on-the-human

    Apply when safe reversible implementation details can proceed inside scope.

    Also in 45 projects that use this

  • jaydubya818Skill

    greploop-apps

    Run greploop through @greptile-apps when the normal trigger rejects a large PR. Use only with the companion greploop skill.

    Also in 5 projects that use this

  • ianclearySkill

    principle-explain-the-number

    Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 30 projects that use this

  • bnemaSkill

    setup-pstack

    Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.

    Also in 26 projects that use this

  • ianclearySkill

    poteto-help

    Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

    Also in 15 projects that use this

  • +7 more from jaydubya818

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 193 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write it clean. A cleanup pass afterwards catches less than not generating the sentence in the first place.

    line 17
  2. Distinctive:

    Before delivering, apply every prose-principles rule to the sentences, then the Formatting and Mechanics rules below to the file.

    line 19
  3. Very specific:

    Plain characters: No em dash, en dash, curly quote, or ellipsis character: typography is the clearest tell there is.

    line 26
  4. Distinctive:

    Bold sparingly: Not on every proper noun. A bold label that names an item and is followed by new detail is fine.

    line 33
  5. Distinctive:

    Every markdown file this repo writes:

    line 40

“Common” is measured: kept by at least 6 in 10 of the 193 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Unslop Skill

Apply to Markdown you create or revise. Read and follow prose-principles for the sentences, then apply the document rules below.

Out of scope: code, code comments, test names, quoted text, and text you were not asked to change. Structure, pointers, and completion criteria in agent-facing documents belong to writing-for-agents.

Process

  1. Write it clean. A cleanup pass afterwards catches less than not generating the sentence in the first place.
  2. Before delivering, apply every prose-principles rule to the sentences, then the Formatting and Mechanics rules below to the file.
  3. Match the surrounding document: its heading case, its terminology, its formality. Local consistency beats this skill's preferences.

Formatting

  • Plain characters. No em dash, en dash, curly quote, or ellipsis character: typography is the clearest tell there is. Write -, straight quotes, ..., and -> for an arrow. Reaching for parentheses in place of an em dash trades one tell for another, so end the sentence or use a comma. A section mark in a cross-reference (agent-conduct § Git Safety) is fine.
  • Colons. Fine before a list or an example. Not as a mid-sentence connector.
  • Bold sparingly. Not on every proper noun. A bold label that names an item and is followed by new detail is fine. A label that restates the line after it is the tell.
  • No decorative emoji.

Mechanics

Every markdown file this repo writes:

  • Wraps Markdown prose at 80 columns. Code blocks and frontmatter are exempt. Apply writing-for-agents when editing skill frontmatter.
  • Carries no placeholder text: no TODO, no TBD, no unfinished section.
  • Has no trailing whitespace and no consecutive blank lines.
  • Names a language on every fenced code block.
  • Has one h1, no skipped heading levels, and internal references that resolve.

Append-only workflow ledgers, such as .docs/bugfixes/*.md, may consist of checklist entries without an h1. All other mechanics still apply.

Specs and phase plans are stricter still: ASCII only, per spec-author.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.