Unslop

What it does

When your agent uses it

• The user says unslop
• After drafting any user-facing page

Example prompts

• “unslop”
• “这读起来像 AI 写的”
• “/unslop”

Requirements

• Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Em dashes in prose. By far the biggest. Resolve each one per sentence
2. 2Inline-header lists. - Label — restatement of the label becomes
3. 3Curly quotes → straight.
4. 4Filler. "simply", "in order to", "it is important to note that".
5. 5Fancy ways to say "is" — "serves as", "stands as", "boasts".
6. 6Title-case headings → sentence case. Proper nouns and defined product
7. 7Sentences that say nothing specific to this project. If the line could

What it can do on your machine

Read from SKILL.md and the folder at commit 6b3ec31. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • node
  • bun
  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Unslop loads about 1.3k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 533 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~77

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Sma1lboy/rove at commit 6b3ec31, republished under its MIT licence (© Sma1lboy). 533 words, ~1,311 tokens.

name

unslop

description

Strip AI writing tells from Rove's user-facing prose — README, the docs/ pages that sync to docs.rove.run, landing copy, and release notes. Use when the user says "unslop", "洗一下文案", "这读起来像 AI 写的", or after drafting any user-facing page. Adapted for this repo from cursor/plugins pstack/skills/unslop.

metadata.internal

true

python3 - <<'PY'
import sys
for p in sys.argv[1:]:
    lines = open(p, encoding='utf-8').read().split('\n')
    for i in range(len(lines) - 1):
        a, b = lines[i], lines[i + 1]
        if a.rstrip().endswith('.') and b[:1].islower() and b.strip() \
           and not b.startswith(('|', '-', '*', '`', '#', ' ')):
            print(f"{p}:{i+1}: {a[-50:]} || {b[:50]}")
PY

node --check packages/rove-landing/index.js
node --check packages/rove-landing/themes.js

bun run lint
bun run --filter @sma1lboy/rove-docs build   # the docs-site CI gate
node --check packages/rove-landing/*.js

grep -rn "—" README.md docs/*.md packages/rove-landing/*.html

node -e '
const s = require("fs").readFileSync("packages/rove-landing/index.js", "utf8")
const keys = (b) => new Set([...b.matchAll(/'"'"'([a-zA-Z0-9._]+)'"'"':/g)].map(m => m[1]))
const zh = keys(s.split("var en =")[0].split("var zh =")[1])
const en = keys(s.split("var en =")[1].split("var dicts")[0])
console.log("zh only:", [...zh].filter(k => !en.has(k)))
console.log("en only:", [...en].filter(k => !zh.has(k)))
'

© Sma1lboy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/unslop of Sma1lboy/rove.

Open the folder on GitHubat commit 6b3ec31