agentleFS
Sign inStart free
ku5icku5ic/claude-kit/skills/unslop/SKILL.md

unslop

Skill2 starsChanged 8 days agoMITView on GitHub

Find and rewrite AI tells and filler in a file, a diff, or pasted text, then show what changed. Use when the user asks to unslop, clean up, or de-AI a piece of text.

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

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 193 edited versions we read keep these.

  • 0

    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. Very specific:

    Default: a copy at the path kit scratch-dir unslop <slug> prints, one per file.

    line 37

“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

Procedure

  1. Load slop-patterns. It says how to rewrite; this skill only says what to run on.
<!-- chat: skip -->
  1. Resolve the target from the arguments:
    • Files: each path.
    • diff: the files git diff --name-only lists. kit slop scans whole files, so keep only the hits on lines git diff -U0 <file> adds, and rewrite nothing else.
    • - or no argument: ask for the text, then treat it as one file.
  2. Scan: kit slop <files>. For pasted text, kit slop --surface <file|commit|pr|chat|ui> - with the text on stdin, ui for UI code; ask which surface when it isn't obvious.
<!-- chat: end --><!-- chat: only In claude.ai chat, the target is the text in the user's message. If there's none, ask for it. Run the scan before judging anything yourself: save the text to a file, then from this skill's folder run `sh scripts/scan.sh <file|commit|pr|chat|ui> < <that file>`, with `ui` for UI code, asking which surface when it isn't obvious. Exit 0 means nothing blocks and 1 means hits; both print what they found. In claude.ai chat, any other exit, or no way to run it, means the scan didn't happen. Your next action is then to read `reference/lexicon.md` in this skill's folder. Take every hit and tier from that file, never from memory, and say in the reply that these are a hand read. -->
  1. Rewrite every tier 1 and 2 hit, and every passage the scan reports as dense, per slop-patterns reference/rewrite.md. Then read the whole text once for what no regexp sees: sentences that carry nothing, sections that restate others (slop-patterns reference/principles.md). For UI files, also walk slop-patterns reference/design.md section 12.
<!-- chat: skip -->
  1. Write the result:
    • Default: a copy at the path kit scratch-dir unslop <slug> prints, one per file.
    • in place in the arguments: edit the file itself.
  2. Re-scan the result with kit slop. A hit left on purpose gets a line in the reply saying why.

Output

Per rules/output.md section 3: the path of each result, hits before and after per tier, and git diff --no-index <original> <result> for a copy. Nothing else.

Arguments: $ARGUMENTS

<!-- chat: end --><!-- chat: only In claude.ai chat, scan the result the same way, then reply with the rewritten text, the hits before and after per tier, and a line for any hit left on purpose saying why. Nothing else. -->

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.

Check your setup, free