AGENT SKILL

unslop

Post-process AI-generated text through the unslop CLI to strip AI writing patterns before publishing

License 许可
MIT
最近更新
2026-06-13
Stars
★ 0
Forks
0

01 前言 Front Matter

name
unslop
risk
safe
tags
[ "writing", "content-quality", "ai-writing", "text-processing", "cli", "publishing" ]
tools
[ "claude-code", "cursor", "gemini-cli", "codex-cli", "antigravity" ]
author
MohamedAbdallah-14
source
community
license
MIT
category
writing
date_added
2026-04-25
description
Post-process AI-generated text through the unslop CLI to strip AI writing patterns before publishing
source_repo
MohamedAbdallah-14/unslop
source_type
community
license_source
https://github.com/MohamedAbdallah-14/unslop/blob/main/LICENSE

03 SKILL.md 正文

unslop — Strip AI Writing Patterns via CLI

Overview

unslop is a CLI tool that post-processes text to remove AI writing patterns programmatically. Unlike skills that ask the agent to avoid AI-isms, unslop runs as a deterministic pipeline step: pipe text in, get clean text out. Use it as a final pass before committing docs, publishing posts, or sending any AI-generated content to production.

The --deterministic flag makes output reproducible — same input always produces same output. The --stdin flag reads from stdin, enabling shell pipeline composition.

When to Use This Skill

  • When you have AI-generated text ready to publish and want a final cleanup pass
  • When working in a shell pipeline where text quality needs to be enforced automatically
  • When writing commit hooks or CI steps that validate content before it ships
  • When you need reproducible text normalization across multiple runs

Setup

Install once:

pipx install unslop
# or
uv tool install unslop

Verify:

unslop --version

How It Works

Step 1: Pipe Text Through unslop

Standard cleanup (may vary slightly between runs):

echo "This leverages cutting-edge AI to deliver robust solutions." | unslop --stdin

Deterministic cleanup (same input → same output every run):

echo "This leverages cutting-edge AI to deliver robust solutions." | unslop --stdin --deterministic

Step 2: Use in Shell Pipelines

Pipe the output of any command through unslop:

cat draft.md | unslop --stdin --deterministic > clean.md

Or chain with other tools:

cat draft.md | unslop --stdin --deterministic | pbcopy   # macOS: copy clean text to clipboard

Step 3: Integrate into Commit Hooks or CI

Add to a pre-commit hook or CI step to enforce quality gates on any generated content before it ships:

# In .git/hooks/pre-commit or a CI script
CONTENT=$(cat docs/changelog.md)
CLEANED=$(echo "$CONTENT" | unslop --stdin --deterministic)
if [ "$CONTENT" != "$CLEANED" ]; then
  echo "Changelog contains AI writing patterns. Run: cat docs/changelog.md | unslop --stdin --deterministic > docs/changelog.md"
  exit 1
fi

Examples

Example 1: Clean a Draft Document

cat blog-post-draft.md | unslop --stdin --deterministic > blog-post-final.md

Example 2: Inline Cleanup During Writing

# Write content, pipe through unslop, write result back
cat README.md | unslop --stdin > README.clean.md && mv README.clean.md README.md

Example 3: Validate Before Submitting a PR

# Check if any generated docs need cleanup
for f in docs/*.md; do
  ORIGINAL=$(cat "$f")
  CLEANED=$(echo "$ORIGINAL" | unslop --stdin --deterministic)
  [ "$ORIGINAL" != "$CLEANED" ] && echo "Needs cleanup: $f"
done

Best Practices

  • ✅ Use --deterministic in CI and automation to ensure reproducible output
  • ✅ Run on the final draft, not intermediate iterations
  • ✅ Combine with the avoid-ai-writing skill for both generation-time guidance and post-processing
  • ❌ Don't run on code files — unslop targets prose, not source code
  • ❌ Don't skip review after unslop: automated cleanup can occasionally change meaning; read the output

Limitations

  • Processes prose only — not code, JSON, or structured data
  • Does not catch factual errors or substantive writing issues
  • Some replacements may not fit every context; review the output before publishing
  • Requires Python tooling such as pipx or uv for standalone CLI installation

Security & Safety Notes

  • unslop reads from stdin and writes to stdout — no file system side effects by default
  • --deterministic mode is local and does not make LLM API calls
  • Default LLM mode may use ANTHROPIC_API_KEY or the Claude CLI; use --deterministic for sensitive local files and CI gates
  • Safe to run in CI pipelines and commit hooks when pinned to deterministic mode

04 同仓库更多 Skills

haresh-sai06
haresh-sai06/SapSynk-AI

youtube-full

Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private/age-restricted videos.

★ 0
haresh-sai06
haresh-sai06/SapSynk-AI

x-twitter-growth

X/Twitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X/Twitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.

★ 0
haresh-sai06
haresh-sai06/SapSynk-AI

write-a-skill

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.

★ 0
haresh-sai06
haresh-sai06/SapSynk-AI

workflow-builder

Design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.

★ 0
haresh-sai06
haresh-sai06/SapSynk-AI

webinar-marketing

When the user wants to plan, promote, run, or improve a webinar or virtual event to generate and convert demand. Use when the user mentions 'webinar,' 'virtual event,' 'online event,' 'live demo,' 'virtual summit,' 'workshop,' 'masterclass,' 'fireside chat,' 'roundtable,' 'registration funnel,' 'show-up rate,' 'attendance rate,' 'webinar promotion,' 'webinar follow-up,' or 'on-demand webinar.' Also use when they have a webinar that isn't converting — low registrations, low show-up, or attendees who don't buy — and want to diagnose and fix it. Covers the full funnel: registration, promotion, show-up, live engagement, live-to-close, and post-event nurture. Distinct from launch-strategy (full product launches) and email-sequence (lifecycle nurture) — this is the end-to-end webinar/event motion. NOT for in-person field events logistics, and NOT for generic lifecycle email (use email-sequence).

★ 0
haresh-sai06
haresh-sai06/SapSynk-AI

vpe-advisor

VP of Engineering advisory for startups: delivery throughput (DORA 4 metrics + bottleneck identification), engineering hiring funnel (sourcing → screen → onsite → offer conversion + time-to-fill + pipeline gap), engineering team structure (squad/tribe/chapter design + tech-lead manager-trigger thresholds), and production discipline (on-call, deployment cadence, postmortem culture). Use when sprint velocity is dropping, eng hiring is broken, team structure is unclear, or deciding when to add a tech-lead manager. NOT a CTO skill (which owns architecture) — VPE owns delivery operations and how the team ships.

★ 0