Skills for Real Engineers. Straight from my .agents directory.
slop-gate
Agent skill fromhuytieu/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.
How to install slop-gate
npx skills add huytieu/COG-second-brain# or add only this skill to Claude Code: copy the folder
skills/slop-gate/
# into
~/.claude/skills/slop-gate/ (all projects)
.claude/skills/slop-gate/ (one project)
1<!-- slop-ok: this skill quotes the tells it blocks -->23# slop-gate45`no-ai-slop` is an editor you invoke. This is a gate that runs whether or not anyone6remembers it. It scans outgoing text, refuses on a tell, and returns the hit list so7the rewrite is targeted.89Two rules make it usable rather than annoying: hard tells fail on a single hit, and10words that are decoration at volume but legitimate once are counted rather than11banned. Text inside quotes or backticks is stripped before scanning, so a piece that12quotes a tell as an exhibit does not fail on its own examples.1314## Why a gate and not a rule1516A rules file is advisory, and advisory rules fail in a specific, repeatable way: they17fire in the step the model thinks of as writing and not in the steps it thinks of as18something else. A deck built by an agent can carry clean paragraphs under headline19slide titles, because the titles were produced in a layout step where the writing20rules never ran. Every surface nobody named explicitly sits on the unchecked side:2122 slide titles, kickers table headers, row keys commit messages23 tile and card labels diagram node and edge labels code comments24 chart titles and legends button copy, subtitles memory files25 alt text, image captions Slack, email, issue bodies PR descriptions2627The gate closes that by scanning the text on its way out, whatever produced it.2829## Run it3031```bash32…
Excerpt shown under the repository's MIT license.
More skills in COG-second-brain
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
