claudecodex

unslop

Post-generation engineering quality. Codesavers removes avoidable complexity from changed code; Specsavers authors and reviews technical software specifications for precision, information density, and decision completeness.

2 on GitHubby timbov0.4.1MITupdated 22 days agocode-quality
/

Plugin unslop from marketplace kiln in timbrinded/kiln. Commands read from the repo's manifest — 21 days ago.

What it installs

Skills (2)

  • codesaver

    This skill should be used when the user asks for "Codesavers", "use Codesavers", "clean up", "remove slop", "simplify", "unslop", "reduce complexity", "tighten up", "cleanup before PR", "review for unnecessary complexity", "too verbose", "over-engineered", "remove unnecessary code", "AI generated me

  • specsaver

    Review, rewrite, or author software specifications for technical completeness and readability. Use for Specsavers requests, design documents, RFCs, requirements, API or protocol contracts, migration plans, and ADR judgements. Review existing documents by default; rewrite only when asked. Do not subs

Subagents (3)

  • codesaver-reviewer

    Use this agent for a dedicated review of changed code for AI-generated verbosity, unnecessary complexity, defensive coding, redundant dependency tests, and other Codesavers directives. Use it when the user asks for "Codesavers", to "unslop", "simplify this branch", "remove unnecessary code", "review

  • specsaver-readability-reviewer

    Use when the Specsavers parent delegates structure and readability review or verification of one coherent specification group. Assess the whole explanation, return concrete findings, remain read-only, and do not delegate.

  • specsaver-technical-reviewer

    Use when the Specsavers parent delegates technical review or semantic verification of one coherent specification group. Return source-grounded findings to the parent; remain read-only and do not delegate further.

View source on GitHub

More from timbrinded/kiln

All 9 plugins →

swift-design

claudecodex

Review and generate SwiftUI views for design quality, HIG compliance, accessibility, and modern API usage. 40 enforceable rules, letter grading, visual screenshot review, and design token references for iOS design excellence.

1 skill · 2 commands · 1 agent

2

ui-refactor

claudecodex

UI design reviewer distilled from Refactoring UI principles. Reviews screenshots, code, and descriptions for hierarchy, spacing, typography, color, depth, and polish — with concrete CSS fixes and named anti-patterns.

1 skill · 1 command · 1 agent

2

idea-space

claudecodex

Generate verifiably new ideas in any domain: map everything that exists by meaning, find the empty space, write the idea that would live there, and measure how far it lands from its closest existing twin.

1 skill

2

infographic

claudecodex

Generate copy-paste-ready infographic prompts from repository documentation, and call an attached image generation tool when the user explicitly asks for an actual image.

1 skill

2

lottie-animation

claudecodex

Create, refine, and verify production-ready Lottie animations, including large-but-renderable JSON assets and seamless loops.

1 skill

2

Language-agnostic performance optimization skill distilled from Google's Abseil performance wisdom. Covers measurement methodology, optimization techniques, and cross-language patterns for C++, Rust, and TypeScript.

1 skill

2

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.

2 commands

alibaba/open-code-review 50,068

agent-teams

claudecodex

Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams

6 skills · 7 commands · 4 agents

wshobson/agents 42,461

codex

claude

Use Codex from Claude Code to review code or delegate tasks.

3 skills · 8 commands · 1 agent · hooks

openai/codex-plugin-cc 35,098

lancedb

claudecodex

Write, review, debug, and document LanceDB pipelines in Python and TypeScript that work with both LanceDB Embedded and LanceDB Enterprise.

lancedb/lancedb 11,887

Maintain unslop?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins9 plugins