LVTD Skills
codexReusable Agent Skills for Codex, Claude Code, and compatible clients, covering Django, Rust, Cookiecutter, SEO, traction, product marketing, and nonfiction publishing workflows.
200 skills
Three-tier triage (PASS_THROUGH / LIGHT / FULL 4-phase) development workflow for Codex and Claude Code with language auto-detection (Python, Java, TypeScript, Swift, frontend) and a staff-reviewer subagent for fresh-eyes review on every change.
Plugin development-skills in hashgraph-online/awesome-codex-plugins. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
ai-agent-benchUse when the user wants to compare Claude Code and Codex on the same code task, with isolated worktrees, common checks, time, and cost.
align-docsUse at the end of every task, or when the user asks to align or clean repository docs, task records, or the project's local agent memory; --clean runs a full cleanup.
align-standardsUse when the user asks to audit a project against its standards and implement the improvements they select.
best-practicesUse when current practice or outside evidence can change a decision: comparing approaches, libraries, or patterns against the user's constraints.
brainstormingUse when the user asks to build, change, fix, or design something in a project: a feature, a bug fix, a refactor, a data model, or a choice between approaches. Invoke it first, before you explore code or ask questions.
broUse when the user says something was too technical or full of jargon, or asks you to speak and write plainly from now on.
changelogUse when the user asks to add CHANGELOG.md entries, derive them from commits, or cut a Keep a Changelog and SemVer release.
commitUse when the user asks to commit the staged changes as a Conventional Commit.
create-testUse when you must define what done means for a task, design or write acceptance checks, build a regression gate for a refactor or behavior change, or check performance.
evolve-loopAutonomous /goal loop that rethinks a project's design and adds features and improvements that can change its behavior, each change recorded and proven. Start it only when the user names evolve-loop.
explain-diffUse when the user asks to explain, understand, or describe a code change: a branch, pull request, commit, diff, or patch, such as 'explain what branch X does' or 'what does this PR change', even when bro is also active or the diff is pasted inline. Also use it when the user did not understand a repl
handoffUse when the user asks to move the session to a new chat or runs /handoff.
phone-a-friendUse when the user wants a second opinion on a plan or code change from the other CLI, Claude Code or Codex.
plugin-feedbackUse when the user asks to write development-skills feedback from observed work, or to assess a feedback report for useful simplifications.
refactor-loopAutonomous /goal loop that refactors a project on every axis without changing its behavior. Start it only when the user names refactor-loop.
resolve-mergeUse when a merge or rebase has conflicts, including plans and chronicles with colliding names.
rethinkUse when choosing or changing a design, yours or the user's; when the user asks to rethink an approach; or when the user dislikes your proposal.
roast-my-codeUse when the user asks to roast code: a factual staff review told with aggressive humor; --fix applies selected CRITICAL and HIGH fixes.
simplify-stuffUse when the user asks to remove unnecessary content or simplify files while keeping useful behavior and project knowledge.
staff-reviewUse when the user asks for a review of a branch, diff, repository, directory, or file, or when the development loop requires an independent review of finished work.
update-depsUse when the user asks to update Python dependencies or pre-commit hooks, keeping the project's pin and configuration style.
using-development-skillsUse when the development loop is missing from your context, or when a skill names a Claude tool that Codex lacks.
wrap-up-branchUse when the user asks to finish a feature branch: missing regression tests, review fixes, docs, and the merge into dev or the given target.
"${CLAUDE_PLUGIN_ROOT:-${PLUGIN_ROOT}}/hooks/session-start"
"${CLAUDE_PLUGIN_ROOT:-${PLUGIN_ROOT}}/hooks/user-prompt"
"${CLAUDE_PLUGIN_ROOT:-${PLUGIN_ROOT}}/hooks/auto-format"
"${CLAUDE_PLUGIN_ROOT:-${PLUGIN_ROOT}}/hooks/plan-approved"
Reusable Agent Skills for Codex, Claude Code, and compatible clients, covering Django, Rust, Cookiecutter, SEO, traction, product marketing, and nonfiction publishing workflows.
200 skills
280+ Agent Skills that turn Codex, Claude Code, Cursor and other agents into a research co-scientist across the academic research lifecycle: literature and PRISMA reviews, hypotheses, experimental design, data analysis in biology, chemistry, medicine, physics and ML, paper writing, citation verification and peer review.
200 skills
Role-based team delivery framework — Tech Lead-orchestrated 8-role system with 195+ skills, 27 specialist agents, 80+ commands, hooks, and ECC harness for Claude Code, Codex, and OpenCode.
175 skills
Open-source AI marketing plugin for agencies — 154 skills, 25 specialist agents, 12-Part Strategy Flow, AEO/GEO, GSC AI Performance Report, Google Ads API v24, EU AI Act Article 50 / C2PA compliance.
164 skills · hooks
Add real-time chat, voice and video calling to React, Angular, React Native, iOS, Android and Flutter apps, with the CometChat Docs MCP for current docs.
98 skills · 1 MCP server
How to make any AI video: find the skill, the options to show and the steps (no key needed), with the keyless varg how to MCP and the varg MCP for video, image, voice and music generation.
78 skills · 2 MCP servers
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Use Alibaba Open Code Review from local Codex.
2 skills
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows
18 skills
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.