---
title: "dcs"
description: "A deliberately small collection of personal Agent Skills."
canonical: https://agentpluginsdirectory.com/plugins/dcs
last-updated: 2026-09-27
---

# dcs
A deliberately small collection of personal Agent Skills.
- Slug: dcs
- Publisher: The Drunken Coder
- Repository: https://github.com/the-Drunken-coder/DCS
- Manifest: plugin.json
- Version: 0.14.0
- Category (editorial): code-review
- Skills: 23 (anti-ui-slop, architecture-map, ask-antigravity, ask-grok, ask-opus, ask-others, babysit-pr, chatgpt-pr-review, codebase-design, deslop, domain-modeling, file-pr, grill-with-docs, grilling, improve-codebase-architecture, pstack, review-to-problems, thermo-nuclear-code-quality-review, thermo-nuclear-review, thermos, unslop, wait, writing-for-agents)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-08-13
- Repository last pushed: 2026-09-10
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/dcs
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What dcs does, in the publisher's words

Drunken Coding Skills: a deliberately small, personal library of the Agent Skills I actually use.

The repository root is a skill-only Agent Plugins 1.0 package. Its root plugin.json declares the portable format, and clients discover skills from skills/ by convention. There is intentionally no legacy client-specific plugin manifest.

The package contains six maintainer-owned skills:

- file-pr opens a focused pull request for the current branch.
- babysit-pr monitors an existing pull request through reviews and CI.
- ask-opus gets a second opinion from Opus through claude -p.
- chatgpt-pr-review runs an explicit ChatGPT Pro review, waits for its final response, and applies locally verified findings.
- wait pauses for work that may need more time and checks again when useful.
- review-to-problems investigates review findings with one subagent per issue and writes checked repository-native problem reports.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/the-Drunken-coder/DCS/HEAD/README.md

## Skills

- anti-ui-slop: Stop coding agents from shipping generic UI. Use UIZZE's 800,000+ real web and iOS screens to build product-specific interfaces, define a design contract, cover required states, and run a hard finish gate. Use for web or iOS UI design, implementation, redesign, critique, and pre-ship review in Code…
- architecture-map: Build or update an interactive isometric map of a repository's architecture, buildings sized by real measurements, neighborhoods by subsystem, animated flows tracing actual call paths, and a drift counter that fails CI when the map falls behind the code. Use when someone wants to see, explain, or…
- ask-antigravity
- ask-grok
- ask-opus: Get a second opinion from Opus with `claude -p`. Use when the user asks Codex to ask Opus, get Opus's second opinion, consult Opus, or explicitly invokes `$ask-opus`.
- ask-others
- babysit-pr: Trigger this skill when the user asks to monitor, watch, or babysit an existing pull request, or to handle CI checks, auto-rebasing, and PR review comments.
- chatgpt-pr-review: Run a ChatGPT Pro review on a pull request, wait for the completed review, then verify and address valid findings locally. Use when the user asks for a ChatGPT Pro review of a PR. Do not trigger for an ordinary local or GitHub PR review.
- codebase-design: Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
- deslop: Remove AI-generated code slop and clean up code style
- domain-modeling: Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
- file-pr: Trigger this skill when the user asks to file, open, or create a new pull request. Do NOT use this skill for monitoring or updating an existing PR.
- grill-with-docs: A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
- grilling: Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
- improve-codebase-architecture: Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
- pstack
- review-to-problems
- thermo-nuclear-code-quality-review
- thermo-nuclear-review
- thermos
- unslop
- wait
- writing-for-agents

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.