claudecodex

llm-essentials

Code-formatting skills (Python/SQL/DBML/Markdown), emoji-conventional git commits, and multi-phase Python and SQL development agent suites.

0 on GitHubby Debmalya Pramanikv2.0.0MITupdated 14 days agodevelopment
/

Plugin llm-essentials from marketplace polyskills in PyUtility/polyskills. Commands read from the repo's manifest — 13 days ago.

What it installs

Skills (10)

  • code-modification-rule

    Adds dated modification annotations - `refactor`, `..versionadded::`, and `..versionchanged::` - to the header of a changed file, in the comment syntax of any programming language. Explicit-invoke only: apply it only when the user calls it (the /code-modification-rule command) or asks for it by name

  • dbml-code-format

    Governs all DBML schema diagram creation, editing, reviews, and modification from scratch for *.dbml files. Always read the file in full before writing or modifying DBML. Use this skill when a user asks to "create/edit/update/review a DBML file" or any database schema diagram in a project that refer

  • extend-init

    Builds, migrates, or repairs a routed Claude Code context for a repository: a short `CLAUDE.md` that sends each task to one document in a docs directory (default `.claude/docs/`), one document per component in directories that mirror the code, and an optional project memory file (default `.claude/ME

  • flaunt-product

    Rewrites or drafts business prose so a product, project or result lands with senior executives as a bold, polished, high-impact story. It names deliverables like products, opens on the gap they close, leads with one headline number, lifts the vocabulary with current AI and industry terms, binds ever

  • git-commiter

    Governs every git commit message produced in this repository. Always invoked. Every commit subject **must** start with one or more emoji glyphs (e.g. `✨`, `🐛`, `🛠️`, `💣`, `📝`, `🧪`, `🤖`, `📜`, `⭐️`, `🚧`, `💡`) followed by an optional Conventional Commit type/scope and a concise imperative summ

  • god-mode

    Explicitly-invoked maximum-rigor protocol for high-stakes, genuinely hard tasks. Runs a structured

  • humanize-text

    Governs the writing quality of natural-language prose generated in this repository, and runs on

  • markdown-format

    Governs all Markdown file creation, editing, reviews, and modification. Always read the file in full before writing or modifying any Markdown content, even for a small change. The skill applies the exact conventions visible throughout this repository: `<div align = "center">` title banners, `<div al

  • python-code-format

    Governs all Python code formatting, editing, reviews, modification, and creation from scratch. Always read the file in full before writing or modifying Python code, even for a small change. Use this skill when a user asks to create, edit, update, review or modify any content of a '*.py' file, or any

  • sql-code-format

    Governs all SQL code formatting, editing, reviews, modification, and creation of `*.sql` files from scratch for PostgreSQL, MS-SQL (SQL Server), and MySQL. Always read the target file in full before writing or modifying any SQL, and confirm the database flavor and version with the user when they are

Subagents (1)

  • README
View source on GitHub pypi.org

Problems found in this repo's manifests

  • .agents/plugins/marketplace.json has no "name" — nobody can install from it

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

obsidian

claude

Claude Skills for Obsidian

6 skills

kepano/obsidian-skills 51,587

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

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

Maintain llm-essentials?

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 pluginslisted