New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Slop Gate

by huytieu in huytieu/COG-second-brain

Deterministic pre-publish scan that refuses AI-slop tells in anything about to be written, published, or sent: files, artifacts, slide titles, table headers, diagram labels, chat messages, commit…

MITAuto-check passedDevelopment

Install Slop Gate

skills CLI
$ npx skills add huytieu/COG-second-brain --skill slop-gate -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install huytieu/COG-second-brain slop-gate --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/huytieu/COG-second-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/slop-gate .claude/skills/slop-gate && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
slop-gate
GitHub stars
1.3k
Token cost
~1.6k tokens
SKILL.md length
854 words
Files
3 (incl. scripts)
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

Deterministic pre-publish scan that refuses AI-slop tells in anything about to be written, published, or sent: files, artifacts, slide titles, table headers, diagram labels, chat messages, commit…

  • Tasks that involve Slides and decks
  • SKILL.md covers Why a gate and not a rule, Run it, Wire it as a hook (Claude… and What fails on one hit, plus 4 more sections
  • Runs Python scripts from its folder; calls python3
  • Tasks that involve Hooks and plugins

What it does

Slop Gate is an agent skill from huytieu/COG-second-brain. Deterministic pre-publish scan that refuses AI-slop tells in anything about to be written, published, or sent: files, artifacts, slide titles, table headers, diagram labels, chat messages, commit messages. Use before publishing or sending any deliverable, in CI, or wired as a Claude Code hook so the check runs without being remembered. The editorial counterpart is no-ai-slop, which rewrites; this one blocks.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/model_compare.py` and `scripts/scan.py`).

It sits in Development, covering Slides and decks, Hooks and plugins and Commit messages. The repository describes itself as: Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework… The licence is MIT.

When your agent uses it

  • Tasks that involve Slides and decks
  • Tasks that involve Hooks and plugins
  • Tasks that involve Commit messages

Example prompts

  • “/slop-gate”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 36ac9d7. 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

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

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

  • Network

    No URLs in SKILL.md.

    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

Slop Gate loads about 1.6k tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 854 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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); the scripts in this folder are not scanned.

SKILL.md

The full file from huytieu/COG-second-brain at commit 36ac9d7, republished under its MIT licence (© huytieu). 854 words, ~1,641 tokens.

Download SKILL.mdSave it as .claude/skills/slop-gate/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
slop-gate
description
Deterministic pre-publish scan that refuses AI-slop tells in anything about to be written, published, or sent: files, artifacts, slide titles, table headers, diagram labels, chat messages, commit messages. Use before publishing or sending any deliverable, in CI, or wired as a Claude Code hook so the check runs without being remembered. The editorial counterpart is no-ai-slop, which rewrites; this one blocks.
<!-- slop-ok: this skill quotes the tells it blocks -->

slop-gate

no-ai-slop is an editor you invoke. This is a gate that runs whether or not anyone remembers it. It scans outgoing text, refuses on a tell, and returns the hit list so the rewrite is targeted.

Two rules make it usable rather than annoying: hard tells fail on a single hit, and words that are decoration at volume but legitimate once are counted rather than banned. Text inside quotes or backticks is stripped before scanning, so a piece that quotes a tell as an exhibit does not fail on its own examples.

Why a gate and not a rule

A rules file is advisory, and advisory rules fail in a specific, repeatable way: they fire in the step the model thinks of as writing and not in the steps it thinks of as something else. A deck built by an agent can carry clean paragraphs under headline slide titles, because the titles were produced in a layout step where the writing rules never ran. Every surface nobody named explicitly sits on the unchecked side:

slide titles, kickers          table headers, row keys       commit messages
tile and card labels           diagram node and edge labels  code comments
chart titles and legends       button copy, subtitles        memory files
alt text, image captions       Slack, email, issue bodies    PR descriptions

The gate closes that by scanning the text on its way out, whatever produced it.

Run it

bash
python3 scripts/scan.py DRAFT.md              # one file
python3 scripts/scan.py content/**/*.md       # many
cat draft.md | python3 scripts/scan.py -      # stdin

Exit code 0 is clear, 1 is tells found, so it drops into CI or a pre-commit hook unchanged. Every hit prints its label and the surrounding text.

Wire it as a hook (Claude Code, optional)

COG ships no hooks by default. If you want the check enforced rather than remembered, add this to .claude/settings.json yourself. --hook reads the hook payload on stdin and answers with a permission decision.

json
{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Write|Edit|mcp__.*slack.*send.*|mcp__atlassian__(create|update)Confluence.*",
        "hooks": [{ "type": "command",
                    "command": "python3 \"$CLAUDE_PROJECT_DIR/.claude/skills/slop-gate/scripts/scan.py\" --hook" }]
      }
    ],
    "Stop": [
      { "hooks": [{ "type": "command",
                    "command": "python3 \"$CLAUDE_PROJECT_DIR/.claude/skills/slop-gate/scripts/scan.py\" --hook" }] }
    ]
  }
}

The Stop entry scans the agent's own reply, which is where most of these land in a working session. Expect it to fire on you within the hour; that is the point of it.

What fails on one hit

TellSpecimen
Em dashany —
Honesty framing"honestly", "the honest part:", "if I'm being honest"
"not X, it's Y""It's not about speed, it's about trust"
"X, not Y" (trailing form)"a test, not a permission", "machinery, not memory"
Rhetorical heading"Why this matters", "The bottom line", "What comes next"
"The <Noun>" heading"The Wedge", "The Shot", "The Gamechanger"
Verdict kicker"That is the point.", "That is all a title is for."
Fake-profound closer"let that sink in", "this changes everything"
Throat-clearing"Here's the thing", "It's worth noting", "At the end of the day"
Sycophancy"Great question", "You were right to push back", "That's on me"
Recap endinga final paragraph opening "In conclusion" or "Ultimately"
Emoji heading## 🚀 Results

What is counted, not banned

robust, seamless, leverage, utilize, delve, empower, streamline, genuinely, quietly, load-bearing, deep dive, clean, plain, simple, elegant, powerful, lightweight, tapestry, game-changer, paradigm shift, cutting-edge

Three or more in one piece fails, on the reading that density means decoration. One is a word choice. The test for any single use: remove the adjective, and if the reader would do nothing differently, it was decoration. "A robust retry" fails that test; "a retry that survives a mail-slot timeout" passes, because it names the behaviour. Keep the word when it is the term of art ("robust statistics").

Show full SKILL.md (298 more words)Show less

Exhibits

A piece that must quote a tell (a style guide, a post about slop, a test fixture) carries slop-ok: <reason> anywhere in the file, usually as an HTML comment or a front-matter key. Quoted and backticked spans are already exempt, so the marker is only needed when a tell appears in the author's own voice on purpose.

Never add the marker to get past a gate you disagree with. Rewrite instead, or change the pattern list and say why.

What it cannot see

The gate is regular expressions, so it catches surface and near-surface tells. It is blind to the structural ones: a declared count that the source does not contain, a framework invented to organise two paragraphs, uniform sentence rhythm, a paragraph that restates the previous one. Those need a reader. Use no-ai-slop in detect mode, and prefer a reviewer from a different model family than the author, because a same-family reviewer shares the author's sense of what a finished answer looks like and waves through the same shapes.

For the tics that are yours rather than universal, measure them: voice-baseline.

Comparing models against the gate

scripts/model_compare.py replays your own Claude Code transcripts through scan.py and reports, per model, the share of chat replies and Markdown writes the gate would have refused and the hit rate per rule. It also reports workload per human prompt (tool calls, active minutes, tool error rate, subagent spawns) and punctuation per 10k words. When a hook refuses a reply, the transcript keeps the refused attempt as well as the rewrite, so the counts include what the model wrote before the gate saw it.

bash
python3 scripts/model_compare.py --since 2026-09-15T00:00:00+00:00 --rules

Pick a window in which the rules file and hook did not change. A rule that tightened mid-window makes the earlier model look worse than it was.

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

Files

SKILL.md and 2 other files (scripts) in skills/slop-gate of huytieu/COG-second-brain.

  • SKILL.md
  • scripts/model_compare.py
  • scripts/scan.py

Open the folder on GitHubat commit 36ac9d7

Compare with similar skills

Slop Gate next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Slop Gate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Slop Gate this skillhuytieu/COG-second-brain1.3k—~1.6kAutomated safety check: PassMIT
Plain Writingdocwriter-org/plain-writing-skill462—~3.6kAutomated safety check: PassMIT
Create Opencode PluginIgorWarzocha/Opencode-Workflows122—~2.4kAutomated safety check: PassNone
Ckeditor5 Plugin DevelopmentTriliumNext/Trilium38k—~4.9kAutomated safety check: PassAGPL-3.0
Debug Hooksparcadei/Continuous-Claude-v33.9k1 repos~863Automated safety check: NotesMIT
CodFlow Change Workflowbighadj22/codflow354—~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • Plain Writing

    docwriter-org/plain-writing-skill

    Writes and edits prose in a plain and boring style: simple everyday words, complete sentences, no dashes, no jargon, and no analogies.

    462 GitHub stars~3.6k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Create Opencode Plugin

    IgorWarzocha/Opencode-Workflows

    Create OpenCode plugins using the @opencode-ai/plugin SDK. An agent skill from IgorWarzocha/Opencode-Workflows.

    122 GitHub stars~2.4k tokensUpdated 8 mo ago
    DevelopmentAuto-check passed

  • Ckeditor5 Plugin Development

    TriliumNext/Trilium

    Write, extend, and review CKEditor 5 plugins in the Trilium (TriliumNext Notes) monorepo — the rich-text-note editor under packages/ckeditor5, whose plugins live in src/plugins/.

    38k GitHub stars~4.9k tokensUpdated today
    DevelopmentAuto-check passed

  • Debug Hooks

    parcadei/Continuous-Claude-v3

    Systematic hook debugging workflow. An agent skill from parcadei/Continuous-Claude-v3.

    3.9k GitHub starsUsed in 1 repo~863 tokens
    DevelopmentAuto-check: notes

  • CodFlow Change Workflow

    bighadj22/codflow

    A step-by-step workflow for changing the CodFlow repository: read the AGENTS.md contract, respect package boundaries, verify before claiming done and keep PRs small.

    354 GitHub stars~1.1k tokensUpdated 4 days ago
    DevelopmentAuto-check passed

  • Plugin Workbench

    openvetta/open-vetta

    Create, implement, build, pack, install, reload, and manage Vetta desktop plugins for non-developers.

    290 GitHub stars~1.9k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from huytieu/COG-second-brain

All 37 skills in this repo

  • Voice Baseline

    huytieu/COG-second-brain

    Measure your own writing corpus for the words and sentence shapes you over-use, so an agent writing in your voice stops amplifying your tics into a style.

    1.3k GitHub stars~957 tokensUpdated 8 days ago
    Auto-check passed

  • Daily Journal

    huytieu/COG-second-brain

    A passive daily work journal that Claude keeps FOR you so you never have to write it yourself.

    1.3k GitHub stars~1.3k tokensUpdated 8 days ago
    Auto-check passed

  • Editorial Illustrations

    huytieu/COG-second-brain

    Generate meaning-carrying editorial data-illustrations in the monotykamary / Linear aesthetic (near-black grayscale, Inter display + mono labels, hairline framed figures) with a single coral accent.

    1.3k GitHub stars~2.4k tokensUpdated 8 days ago
    Auto-check passed

  • Loop Engineering

    huytieu/COG-second-brain

    Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns.

    1.3k GitHub stars~1.5k tokensUpdated 8 days ago
    Auto-check passed

  • Release Video

    huytieu/COG-second-brain

    Turn a product release (the list of shipped items plus real screen recordings) into a motion recap video and one explained demo per feature, with sound effects tied to on-screen motion and a…

    1.3k GitHub stars~1.7k tokensUpdated 8 days ago
    Auto-check passed

  • Onboarding

    huytieu/COG-second-brain

    Personalize COG for your workflow - creates profile, interests, and watchlist files with guided setup (run this first!)

    1.3k GitHub starsUsed in 1 repo~3.1k tokens
    Auto-check passed

Categories

Questions about Slop Gate

What does Slop Gate do?

Deterministic pre-publish scan that refuses AI-slop tells in anything about to be written, published, or sent: files, artifacts, slide titles, table headers, diagram labels, chat messages, commit…. Slop Gate is an agent skill from huytieu/COG-second-brain. Deterministic pre-publish scan that refuses AI-slop tells in anything about to be written, published, or sent: files, artifacts, slide titles, table headers, diagram labels, chat messages, commit messages.

When should I use Slop Gate?

Slop Gate fits situations like: tasks that involve Slides and decks; tasks that involve Hooks and plugins; tasks that involve Commit messages.

How do I install Slop Gate in Claude Code?

Run `npx skills add huytieu/COG-second-brain --skill slop-gate -a claude-code`. Or copy the skill folder (skills/slop-gate in huytieu/COG-second-brain) into .claude/skills/slop-gate in your project. Claude Code loads it when a task matches its description.

How do I install Slop Gate in Codex?

Run `npx skills add huytieu/COG-second-brain --skill slop-gate -a codex`. Or copy the skill folder (skills/slop-gate in huytieu/COG-second-brain) into .agents/skills/slop-gate in your project. Codex loads it when a task matches its description.

Can I use Slop Gate in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huytieu/COG-second-brain --skill slop-gate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/slop-gate, .gemini/skills/slop-gate, .github/skills/slop-gate and .opencode/skills/slop-gate in your project.

What does Slop Gate need to run?

Going by SKILL.md and its folder, Slop Gate needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Slop Gate access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Slop Gate safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Slop Gate use?

Slop Gate is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Slop Gate use?

About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Slop Gate?

Skills that share tags, products or a category with Slop Gate: Plain Writing (docwriter-org/plain-writing-skill, 462 stars), Create Opencode Plugin (IgorWarzocha/Opencode-Workflows, 122 stars), Ckeditor5 Plugin Development (TriliumNext/Trilium, 38k stars) and Debug Hooks (parcadei/Continuous-Claude-v3, 3.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Slop Gate?

huytieu (a GitHub user) maintains it in huytieu/COG-second-brain, which has 1,268 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 2, 2026.

Source: huytieu/COG-second-brain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.