Developer Tools plugins

Focused tools for software engineers to size up a change before making it: scope, impact, tradeoffs, decision points, and a first-principles pass on your own read of the problem — plus cheap subagents for the mechanical work. In your language.

City Life for AI agents. Move into 1F3D9, choose a name, build and own things, talk with neighbors, and make agreements within approved permissions.

Synced lyrics in Claude Code, word by word, with Adlib's dancing mascot. A Claude Code mod for macOS.

A self-bootstrapping, self-healing agent engineering skill for any repository. Context-drift detection, guardrails & an Implement → Review → QA pipeline for AI coding agents.

Claude Code plugin that routes coding subtasks to the cheapest capable model — the main session (Opus) plans, reviews and verifies; codex/claude executors write the code.

Moveo.AI plugin for Claude Code: build, test and operate Moveo.AI agents

Cost-aware sub-agent tiers for Claude Code - daily-drive a cheap Lead, buy the strong models per call. Guard hooks hard-stop force-pushes and secrets before they run. Plain files + POSIX shell, no server.

Hear your coding agent. claude-tts speaks a curated, filtered stream of a Claude Code agent's work — the status pivots, the errors, the final answers — and stays quiet through the noise.

Creator operating system for AI-native workflows: skills, commands, agents, and plugins for Codex, Claude Code, Cursor, Grok and Antigravity Gemini.

Orchestration plugin for Claude Code. Seven skills, smart model routing, parallel git worktrees, code + design review built in.

Claude Code plugin for AgentLint — real-time quality guardrails for AI coding agents

DevOps discipline for AI coding agents: shape the work, track it as a graph, and get each change judged by a context that didn't write it.

Claude Code plugin for Google's Antigravity (agy) CLI — job tracking, background execution, code review, and a stop-time review gate for Antigravity workflows. Built from scratch by Vit129.

Hire Google's Antigravity CLI (agy) as a fast Gemini staffer for Claude Code and OpenAI Codex.

Build and run a personal AI team in Claude Code: an Overmind that designs your specialists, dispatches missions, and keeps every session in sync.

Art and animation, written as code. Illustrations, loops, interactive web art, launch-videos and scored films in dozens of styles, identical on every render.

Claude Code plugin: run the Antigravity CLI (Gemini) as a collaborating sub-agent with intelligent model routing across the SDLC. Community project; not affiliated with Google/Anthropic.

Permission-first rules, agents, skills and workflows for AI coding agents. One source → native CLAUDE.md, AGENTS.md and GEMINI.md for Claude Code, OpenAI Codex and Google Antigravity. Claude Code plugin + one-line install.

Arcgram — an interactive diagram engine for human–AI collaboration: an AI agent draws its reasoning as an auditable node-and-edge flow and self-audits it, delivered as one standalone HTML file. (Arcgram the AI diagram tool — not Archigram.)

Your agent draws the architecture. Editable Draw.io and Excalidraw diagrams - cloud architectures, system designs, data pipelines and flows - for Claude Code, Codex, Cursor, OpenCode, Copilot, Antigravity and Pi.

Astromesh Leia — Claude Code plugin for agent operations in plain English: create, deploy and monitor WhatsApp and multi-channel agents on Astromesh Nexus without touching Kubernetes.

The craftsman's framework for AI-built software - done-state loop engineering, design law, clean-code enforcement, auto model routing, SQLite knowledge graph, self-learning. One install.

Make your agents talk human. ADHD-friendly output styles for Claude Code, Codex, and others. So you can pay attention, not tokens.

Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.

BA skills for the Plausible BA

Don’t grill your brain. A browser UI for Claude Code grilling sessions.

Plugin for Claude Code: sends each coding task to the cheapest model that can do it right, keeps your main chat lean, reviews every diff. Debates, plus Codex, Gemini, Kimi, Qwen or Ollama as second opinions.

Protocole de travail multi-agents pour Claude Code : PO, Manager, Dev, Designer sur un backlog GitHub

Orchestrate high-performance AI development using Fred Brooks' Surgical Team model. This plugin maps specialized agent roles—chief programmer, scribe, and support—to your workflow, keeping the lead focused on critical work. Compatible with, Claude Code, OpenAI Codex, xAI Grok Build, GitHub Copilot CLI, OpenCode, Hermes Agent, and Pi.

AI code reviews grounded in 12 classic engineering books — decay risk diagnostics with book citations, severity labels, and 6 analysis modes including full-sweep auto-fix

Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.

CHA (Cyclic Hostile Adversarial Harnessing) — Cross-checking LLM pipeline for deep code debugging

Phased planning and execution for Claude Code. Roadmap, plans, and progress live in files that survive a /clear.

A polished CLI toolkit that analyzes local Claude Code sessions and Git history to deliver rich analytics, insights, streaks, leaderboards, and productivity metrics—all offline.

🚢 Run Claude Code's ⚙️ Dynamic Workflows, 👥 Agent Teams & ⚡ Subagents on any third-party model — DeepSeek · GLM · Kimi · Qwen … or your Codex subscription. No Anthropic subscription needed. ｜ 🚢 让 Claude Code 的 ⚙️ Dynamic Workflow、👥 Agent Team、⚡ Subagent 用上任意第三方模型 — DeepSeek · GLM · Kimi · Qwen…… 或你的 Codex 订阅,无需 Claude 订阅

Stop Claude Code before your plan usage runs out. Halts at a percentage you choose and waits for you to decide.

Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps, published benchmarks including the runs it loses.

ESP for AI Coding — Agent skills on the philosophy on software design, grounded in decades of engineering experience.

Claude Code skills for construction professionals.

Claude Code plugin that QA-tests your whole app with a team of AI agents: maps every feature, tests each one in parallel, lists the bugs for your approval, fixes them in isolated git worktrees and has a fresh agent verify every fix — cycle after cycle. Android, iOS, web.

Automatically captures what you do in Claude Code and turns it into a daily worklog, without you having to ask for it.

Comprehensive Agents, Commands, Hooks, and Skills for homelab service management - media automation, infrastructure monitoring, document management, and more

Guard hooks, context injection, and review skills for Claude Code

Kurtlar Konseyi: zor kararları 7 bağımsız yapay zekâ üyesine tartıştıran Claude Code eklentisi. Başkan Karahanlı (Fable) görev dağıtır, güven yüzdeli hüküm verir. Ölçümlü, GPL-3.0.

Two Claude Code skills that separate deciding from doing: /planfirst investigates read-only and stops; /proceed executes only what was approved.

PostEverywhere for Claude, Cursor, Gemini CLI, Codex and Copilot: write, schedule and publish social posts to 12 platforms, with 15 skills. No API key, nothing to install.

Two Claude Code loops that keep reviewing and researching until they reach a fixed point: the implementer and the grader are held in separate contexts, and the machine may only ever declare failure, never convergence. Japanese only for now.

Claude Code efficiency and hygiene toolkit — token spend analysis across the 5h / 7d / Sonnet-7d billing windows plus configuration overlap auditing. Ships as a Claude Code plugin with three skills (usage-analysis, usage-dashboard, claude-audit) backed by a Python CLI.

Claude Code plugin and standalone CLI that deep-scans git repositories for secrets, PII, code vulnerabilities, git-history leaks, and dependency CVEs. Secrets are redacted in all output; --ci mode fails the build on HIGH/CRITICAL findings.

Claude Code Plugin for session import, export and migration between profiles, containers, and machines

Six Claude Code skills + an unattended build loop, each measured with and without the plugin. 19/19 evals passing.

Hear your coding agent. claude-tts speaks a curated, filtered stream of a Claude Code agent's work — the status pivots, the errors, the final answers — and stays quiet through the noise.

Claude Code plugin that reads Claude's responses aloud, fully local (pyttsx3, no API keys), with per-session on/off and a macOS menu bar app.

Portable Claude Code and Codex configuration: slash commands, subagents, hooks, skills, and a transcript-to-lessons pipeline. Installable as a plugin.

Tell your agent you know nothing. It becomes the only reviewer in the room: safe defaults, unasked questions answered, irreversible steps flagged. Claude Code / Codex / Cursor / AGENTS.md.

🥋 Claude Code plugin that teaches programming while you vibecode — contextual explanations, micro-quizzes, and belt progression. Free & open source by Dojo Coding.

On-demand coding-conventions catalog for Claude Code — captures reusable patterns at checkpoints and scaffolds a project-local convention catalog in any repo.

Claude Code plugin that gets to the point: answer-first replies, depth on request, safety steps never cut. Opus replies 71% shorter, 30% cheaper (benchmarked).

Codebase Understanding for Claude Code

A long session makes Claude Code dumber: compaction keeps what happened and throws away why, so it retries the path you already dropped. This kit keeps a session ledger, the one file where each decision keeps its reason and its proof, and brings project state and memory current with it before every /compact. /brief shows you where things stand.

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

A context manager for new and legacy codebases — indexes a repo, reports what is missing, and writes the context layer agents actually read. Installable as a Claude plugin.

A Claude Code plugin that acts as an intelligent harness for your development workflow: your codebase is read-only by default, every change passes through a Write Gate as planned and approved work, and craft tracks your project's history, design tokens, and decisions locally so Claude learns your taste and architectural preferences over time.

Production-ready Claude Code skills, agents, and project templates for Craft CMS 5 development

Spec-driven development skills for AI coding agents: 10 human-gated steps from idea to docs. Claude Code plugin + SKILL.md for Codex, Cursor, Gemini CLI, OpenCode

A collection of skills for an AI agent that helps writing texts

Design Mastery plugin for Claude Code - Learn from Saul Bass, Dieter Rams, and other masters. Build professional brand identities with systematic workflows.

AI development team as a Claude Code plugin -- TDD workflow, security audit, and phase-boundary compaction.

Turns a short feature/bug description into a reviewed, on-device-verified implementation — parallel subagents, cross-model review, GitHub reconcile, and a doctor/learn loop that benchmarks and improves the pipeline itself. Built on superpowers.

Dex is the agent-native analytics engineering toolkit. Point it at your warehouse and your dbt project. It learns the landscape, authors your transformations, and tells you exactly what to fix when the schema drifts. Built for analytics engineers and data engineers who want more out of their coding agent.

Reusable Claude Code dev harness plugin — agents, commands, skills, hooks, opt-in stack modules

Skills, a review subagent and a fast lint hook for Drupal 10, 11 and 12 development with Claude Code: modules, theming, configuration, security, testing, upgrades, performance, migrations and JSON:API.

Check Agent Skills before reuse: find missing local resources in browser or CI, review pinned examples, and serve skills through DeepSeek Harness or MCP.

Elnora CLI — command-line interface for the Elnora bioprotocol platform

Linear workspace for Claude Code — search, bulk edit, agents, and a config-driven curator. The repo IS a Claude Code plugin marketplace.

Merit Aktiva accounting + Merit Palk payroll API — CLI and Claude Code plugin. Universal, config-driven.

WhatsApp for Claude Code — read, search, and send WhatsApp messages from your own paired account, 100% local. Automated setup, hardened defaults, keep-alive service.

Scan any codebase for EU AI Act (Regulation 2024/1689) compliance evidence and gaps. 14 analyzers, Claude Code plugin + library + CLI. Local-only static analysis.

EU AI Act compliance from Claude Code. Classification, DPIAs, vendor assessments, evidence packs. DACH-first, by Lexbeam Software.

Claude Code plugin: fail-closed eval release gates + an evidence-gated 27-step build ledger. NaN and stale baselines BLOCK; placeholder evidence is refused. /eval-init installs it into any repo.

Claude Code plugin: one engineering process, skills that take turns, and agents that keep discovery off the main context.

Animated product explainer videos with voiceover, music & synced SFX — an interactive Claude Code skill/plugin.

A lightweight engineering methodology for engineers and AI agents to turn requests into verified results.

Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.

8 agent skills for real Figma files, for Claude Code, Codex, Copilot CLI and Gemini CLI: 90 Plugin API gotchas, checks before and after every write, a handoff gate.

Rules and checks that make Claude Code look around a change, not just at the lines it writes: ten questions before code, a reviewer that didn't write it, proof before done, bugs fixed as a class.

Claude Code steers, cheap DeepSeek Flash workers do the reading and typing. Each job runs in a disposable copy of your repo and returns a git patch.

🫕 One pot, everyone brings a fork, no double-dipping. A team of AI agents that plan, build and review each other's work, with you as the team lead. Spec-driven development and bug hunting for Claude Code.

A tight senior-engineer toolkit for Claude Code: five skills, plus a hook that speaks up when a diff outgrows its task or production code lands without a test.

12-stage gated SDLC orchestrator for Claude Code — deterministic gates, REQ-ID traceability, cost-capped background agents, brownfield adoption

Claude Code plugin that catches the bugs your agent shrugs at — enforced by hooks, auto-closed on merge.

CLI over the freehire job API for agents

Agent skills for shipping mobile games: in-app purchases, ads, auth, store listings and release pipelines for Google Play and the App Store.

Game Studios multi-agent game-development framework as a single Claude Code plugin: 50+ agents, 70+ skills, guarded hooks, rules, docs, mcps — host-neutral (Claude Code /Codex/ ZCode)

Ultimate Opus 5 builder. Creates and transforms any setup into the ultimate setup for generation 5 models.

Your coding agent says "done." Godmode checks. A local, tamper-evident record of what your agent ran, changed and proved: risky commands stopped before they run, claims downgraded until a real check backs them. Zero dependencies, nothing leaves your machine. Claude Code · Codex · Grok · OpenCode · Antigravity.

A Claude Code plugin that takes a change from idea to merged PR on autopilot, scaling the rigor to the risk.

Grandpa makes AI coding agents work smarter, not harder. Zero-bloat architecture, 8 skills, CLI scanner, and benchmark harness for 25+ AI agents.

You already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 70 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether it ships.

A spellbook of agent skills for AI. Cast wisely.

Free Claude Code plugin: blocks destructive commands and secrets edits before they run, prints an OK / WARN / SKIPPED session report of what loaded, and lints CLAUDE.md.

A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.

Claude Code · Codex 한글 에이전트 스킬 플러그인 — 아이디어 → PRD → 설계 → 태스크 → 검증 하네스 → 자율 개발 루프 / Korean agent skills: idea to autonomous dev loop

Verification gates for AI coding agents — nothing ships unproven. Falsifiable oracle gates, team wall, receipts. Works with Claude Code today; Cursor, Codex, Gemini CLI & every git repo next.

A /human-review skill for Claude Code: assembles one page that lets a human review a change set fast — diagram deltas, Code City, a feature video, complexity delta, and deep-linked snippets.

Claude Code plugin: Claude builds, Codex critiques — a gated research → plan → review → ship pipeline, with autonomous multi-agent revise loops that self-converge.

Turn your Grok Bot into a 7-agent Hyperliquid trading desk. Roles, system prompts and skills your Bots use to research, size, execute and review.

Claude Code plugin: grades every plan Claude writes against 14 Hemingway rules and rewrites docs to an A.

Claude Code plugin for spec-driven development alongside Interpretable Context Methodology (ICM).

Playwright MCP server undetected by anti-bots and captchas: AI agent browses the web on anti-detect stealth Firefox, Python, undetected browser automation, scraping, computer use.

ISO 24495 Plain Language skills and plugin

Turn a list of GitHub issues into one reviewed pull request, unattended: a Claude Code plugin with a deterministic context-clearing plan, on-disk run state, and a usage-window guard.

A Claude Code plugin that keeps your AI agents honest. Claude plans tasks as phases with checks, and when it tries to stop, Jevflow runs them and asks Jev if the work is really done. Many agents, one plan, with a live viewer to watch it all.

A Claude Code and Codex plugin that scaffolds AI-native development practices into new projects. jig adds a repeatable spec, implementation, review, and memory workflow to AI-assisted software projects.

AI-assisted skills for a practical job search — resume tailoring, cover letters, company research, interview prep, LinkedIn, and proof assets. Installs as a Claude Code/Cowork plugin.

Ticket-workflow skills and guardrail hooks for Claude Code and other coding agents: start the ticket, test first, commit, and deliver for a person to accept, on a Juscribe board.

A governed development method as a Claude Code plugin: deterministic Definition-of-Ready gates and a required blind pre-mortem keep multi-PR, agent-built work coherent.

🌐 Build modern full-stack web applications easily with the Claude Code plugin, featuring 81 commands and 12 AI agents for efficient development.

Install engineering discipline into any AI coding assistant. Composable skills for design, implementation, review, and team standards. Better process, not just better prompts.

Test-first workflow for coding agents, without the spec ceremony. The tests are the spec.

GEO-first SEO for Claude Code — optimize websites for AI search engines (ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews). 12 specialized skills for citability scoring, llms.txt, schema markup, technical SEO, content quality, and platform-specific optimization.

Deploy a coordinated team of AI engineers to any codebase. A Claude Code plugin with structured workflow, two-stage code review, autonomous BLOCKED recovery, and a research gate that verifies external APIs against current docs before specs get written.

A Claude Code plugin that turns the words you reach for while working into your own study material. Instead of someone else's word list, you learn the language your real projects speak, and you review it right where you work. Everything stays on your computer. Build your own Quizlet or Duolingo out of your own data.

Luciazero — make coding agents prove their work. Verification-first discipline for Claude Code + Codex CLI: 9-rule doctrine, 13 skills, risk-routed reviewer, fail-open hooks.

maddog: an advisor-executor agent universe for Claude Code — judgment-tiered executor family, product-engineering pipeline, gated authoring and session-mining skills

Brainstorm → plan → execute development workflow plugin for Claude Code

Matt Pocock 技能集扩展：dev-prep 开发准备路由器 + relay 接力开发（强模型规划、弱模型执行，到 strong zone 自动停下）

MCP Plugin that provides common skills for Datadash MCP tools

Engineering discipline and reliability for frontier coding agents: durable responsibility, adversarial verification, continuity, and autonomous completion.

Claude Code plugin: Metica agents for Unity SDK integration and runtime ad-log monitoring

The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into Claude Code and Codex with your own primitives: hook-enforced guardrails, usage telemetry, cost postures and model tiering, under any rules library or orchestration layer.

Self-improving multi-agent harness for Claude Code. A Technical Lead plans, Full-stack builds, QA verifies, and retros turn lessons into rules that fit your project. Stack-agnostic.

Multi-agent orchestration pipeline for Claude Code: DELIVER (build), AUDIT (review), DIAGNOSE (investigate). Conducts 14 specialist subagents through research, plan, review, implement, verify, document with live narration.

Vellum - a working novelist daily tool for Claude Code: three hard gates, a deterministic continuity engine, and a series-aware library layer. Authored by FiredMosquito831.

Claude skills plugin for quiet senior dev

OBJECTION! A skill and plugin for AI coding agents (Claude Code, Codex, Cursor, Gemini): accusers, a defender and a judge review the PR, and a gate blocks it until APPROVED.

A discipline layer for Claude Code: terse register, evidence gates on the model's own output, a stop before it builds the wrong thing. Four agents, six skills, one advisory hook — ~2,998 tokens of static context, everything else fires on demand.

Plain-language agent skills for Claude Code, Codex, Cursor and Gemini CLI: honest session reports, straight verdicts, steps you can follow. MIT.

Claude Opus 5.5 directs and renders films in JavaScript: brief → sound (file, YouTube, generated, or AI voiceover) → director's treatment → frame-exact MP4. A Claude Code skill + plugin.

Claude Code plugin: from a circuit idea to a manufacturable KiCad PCB

Claude Cowork skill kit for Italian criminal defense lawyers: 9 skills for defense strategy, filings, deadlines, custody measures and case law research, grounded on a verified jurisprudence database with anchored citations. · Kit di skill per l'avvocato penalista italiano, con fonti verificate e citazioni ancorate.

Use Codex pet in agent tools that support Claude plugin.

Agent engineering harness that joins automation and human-in-the-loop for well crafted software.

Skill/Plugin for building multimodal AI applications with Pixeltable. Tables, computed columns, embedding search, UDFs, and 30+ AI provider integrations.

A platform engineering handbook covering Kubernetes, OpenShift, Argo CD, Flux CD, AWS, Azure, Terraform, and GitHub Actions — with an optional Claude plugin layer for interactive guidance.

Stop uncertain data becoming confident-looking results. plumb-line carries provenance, confidence and mock-taint with values through JavaScript and Python, and its review-time checks and GitHub Action catch uncertainty laundered into a claim in AI-assisted code.

Interactive AI agent skill to build responsive, bilingual portfolio websites ready for search and AI answer engines

Claude Code plugin: from a one-line idea to a published Power Apps Canvas + Power Automate app, one guided /pp-en:* command per stage. SQL Server or Dataverse, specialist subagents, ready-to-paste components and validators. Also in Brazilian Portuguese (/pp:*).

Claude Code Plugin for Critical Thinking and Analysis

PumpGTM plugin and MCP server: find buyers and run LinkedIn, email and X outreach from Claude, ChatGPT, Codex or any AI agent.

Push notifications + human-in-the-loop for AI agents. Approve from your lock screen. Claude Code, Claude Cowork, Codex, Cursor, Gemini.

QA (Web, API & AQA) Agents Team Claude Harness Plugin

Questions → Research → Spec → Plan → Implement: a phase-gated Claude Code plugin that keeps a coding agent under 40% context by writing one artifact to disk per phase.

Scaffolding skill + always-on conventions (CLAUDE.md/AGENTS.md) for Quarkus + LangChain4j agentic AI apps: AI services, multi-agent workflows, and RAG. Installable in Claude Code, Codex, Copilot, Cursor, and any Agent Skills-compatible agent.

The control plane for game-dev agents — close the loop with verified compile, test, and cross-model review across Unity, Godot, Unreal, and S&box. Lifecycle-aware /qq:go routing, 26 /qq:* slash commands. Claude Code-first, agent-agnostic via HTTP and MCP.

Token cost quotes and usage-limit budgeting for Claude Code: see what an AI job will cost before you start it, pick a level in a choice window, get the real cost after, and split big jobs into daily installments that respect your 5-hour and weekly limits.

A opiniated skills toolkit for Rails applications

Order anything from Rappi through AI conversation — restaurants, groceries, pharmacies, liquor. Works on Claude Code, Desktop, Cowork, and OpenClaw.

Plan-first coding for Claude Code: a spec you approve, a hook that blocks edits until you do, and small skills to build, finalize, diagnose and review.

Xcode release automation from Claude Code: SemVer bumps and tags, changelogs and TestFlight notes for iOS/macOS apps, plus iOS Simulator builds

Claude Code plugin that streams your sessions to Rius as OpenTelemetry traces: prompts, model calls, tokens, tool calls and subagents.

レビューを、組織の判断資産へ。Review Judgment as Code for AI-assisted development — codify your team's review standards as repo-owned skills and run them across the SDLC.

Audit-first agent skills for safer React Native maintenance

Russian text quality for AI agents — neuroslop cleanup, typography, information style, editorial standards, UX writing, business correspondence. Scores text 0–10. 2,000+ linguistic atoms.

Build a complete, secure SaaS end to end with your CLI agent: 22 lifecycle skills, prevention-first security, RLS audit, real payments — and field notes from production apps that passed every test. Pairs with Superpowers.

Spec-driven multi-agent orchestration plugin for Claude Code — 13 agents, 35 skills, per-phase model tiers, opt-in lifecycle hooks, and optional cross-device semantic memory.

An agentic scriptorium for scholarly writing — coordinated AI capabilities for manuscripts, grants, and reviews.

The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.

Evidence-based application security for Claude Code — audit commands that prove their findings, plus skills that make Claude write secure code by default.

Methodology and deterministic evaluation tools for iterative improvement of skills, repositories and agent workflows, with independent review and regression checks.

Evidence-first SEO, AEO, GEO and AI-search workflows for Codex and Claude Code — one router, 27 focused skills.

A repeatable Plan, Go, Close workflow for AI coding sessions. Open source for Claude Code, Codex, Cursor and Pi.

A local video studio for your coding agent. Describe a video in one sentence: your agent directs, your machine renders. Claude Code, Codex, Cursor, Devin and more. No API keys, no uploads.

My Claude Code skills and CLI delegation plugins, in one marketplace: align, tailwind, opencode, snapshot, recall, plus cursor/grok/agy delegation.

Agent Skills for the boot.gs Google Apps Script framework and plain Google Apps Script – Claude Code, Gemini CLI, Cursor, and npx skills compatible.

Carinya Parc Agent Skills

My agent skills for Claude Code and Codex, grouped by category. Installable as a Claude Code plugin.

MetalBear Skills for our users

Two Agent Skills that help an AI agent make an interface clear, consistent, easy to use and scalable, and Russian text clear and correct (English version planned), without the signs of AI-generated work. They work in Claude, Codex, Cursor and other compatible agents.

Turnt Up Technologies株式会社の Claude Code プラグインマーケットプレイス

Agent Skills for the Upbound Platform — Kubernetes control plane fleets, starting with Claude Code. So your agent gets fleet state right instead of confidently wrong.

Reusable Claude Code skills for managing public GitHub repos at commit, push, and release time, plus the generic repo files every project should carry.

Claude skill + plugin that picks the right model and effort for every task: Opus plans, Haiku/Sonnet build, every step is verified, and it escalates only on failure. Save tokens without losing quality.

Lanes, tickets, and a human merge. Runner and telemetry are plugs.

A gated 9-phase SDLC for solo founders shipping with AI: idea to validate to spec to architecture to plan to execute to QA to release. One skill, five adversarial review agents.

sonmat (손맛) — Claude Code plugin that builds verification habits into AI-human collaboration

Specs, sealed — an implement/review agent chain with hook enforcement, an evidence ledger with drift detection, and a tool-agnostic review handoff protocol.

Claude Code plugin to navigate, trace, and debug a fleet of multi-repo Spring Boot microservices

Multi-perspective deep research that writes Wikipedia-style, fully-cited articles. Unofficial native implementation of the Stanford STORM methodology

Agent Skills for end-to-end story writing in markdown, packaged as Codex and Claude Code plugins.

Task coordination for Codex CLI and Claude Code: carry bounded work directly or dispatch Herdr-backed sessions rooted in each app, from single-app repos to monorepos.

Build, govern, and ship Streamlit-in-Snowflake apps with Claude Code

A curated Claude Code plugin with skills for anything Claude can do.

The best of Matt Pocock's Skills, Superpowers, and Compound Engineering. One complete, simple, supercharged SDLC system for your coding agent.

Compound V — a multi-model orchestrator for Claude Code, layered on Superpowers: a deterministic router (Opus for risky work, Sonnet for the mechanical), cross-model review (Claude + Codex), 3 scouts (code · docs · domain), semantic memory, and Epic/Marathon autonomous loop mode. The pill that turns one freelancer into a squad.

Claude Code skills for on-demand engineering work — PR risk review, repo introspection, audits, ownership maps. Published at cdd.dev/skills/swe.

Claude Code & Pi Coding Agent plugin — senior-engineer toolkit: Clean Architecture, DDD, SOLID, TDD, design patterns, security review, and language expertise across Bash, C#, Dart, Go, Java, Kotlin, Python, Ruby, Rust, SQL, Swift, and TypeScript.

Local multi-provider proxy for Claude Code — automatic failover, priority routing, auto-recovery, usage analytics, and a provider catalog

DDD + TDD harness for Claude Code — 5 hooks enforce Domain layer purity, cross-context call rules, and red-green discipline at edit time. Ships 4 skills + project templates.

Claude Code plugin: 17 Claude Skills for LinkedIn bundled with the Taplio MCP. Write, plan, and grow your LinkedIn presence from Claude, on your real voice and analytics.

Interrogate the plan, capture what survived, implement it in any session — a chat-first task plugin for Claude Code.

Your friendly QA beagle — plan-gated agent skills for Claude Code & Codex that run your app locally and sniff out bugs across functional QA, security, accessibility, and performance.

The loop for everything!

23 great minds as agent skills for Claude Code: the working methods of Feynman, Dijkstra, Ohno, Munger, Torvalds and more, plus a council that argues for you. Methods, not voices.

Claude Code plugin: tamper-evident receipts for AI-assisted commits — hash-chained, HMAC-signed, verifiable offline. Auto-receipts every commit via hook.

Open-source financial research desk for Claude Code, Codex and Antigravity. 54 tools for market analysis, scenario simulation, counterexample search and model comparison. A local-first workspace to fork assumptions, trace evidence and score defined outcomes. No broker connections or order execution. MIT licensed.

Orchestrate Claude, Codex, and Gemini with natural language routing, cross-model review, and 38 skills for tri-CLI workflows

Build, audit and fix web interfaces to a bar you can check. Agent Skill + Claude Code plugin: WCAG 2.2 AA, a craft floor, zero AI tells, isolated evaluators, assurance levels L1–L4.

Claude Code and Codex frontend skills for cinematic websites: art direction, WebGL, parallax, three.js, audit.

Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos.

AI-powered vulnerability scanner plugin for Claude Code with 28 agents statically scan web & mobile repos for OWASP Top 10 / Mobile Top 10 vulnerabilities, validate findings, and optionally auto-fix them. No live requests, ever.

Verification Skill for Claude Code

Claude Code plugin that hard-blocks dependency additions, bumps, and downgrades until a fresh, source-cited version check is recorded. Supports npm, pip, Poetry/uv, Cargo, and NuGet.

Salesforce delivery harness for Claude Code: parallel Apex, LWC and metadata agents, documentation-grounded Salesforce and fflib skills, deterministic hooks, local and post-deploy check gates.

Efficient, Evidence-based, Opinionated vibe-coding pipeline for CC / Codex / OpenCode / Antigravity / Pi

⚡ Universal Skill AI Agent Swarm Architecture for Antigravity, Claude Code, Cursor, and Windsurf. Vibe Coding 2.0 with Zero Tech Debt

Claude Code / Codex skills that turn a video into a Chinese narration recap (视频解说): scene detection, ASR, VLM, script, TTS, ffmpeg assembly, optional editable JianYing / CapCut draft export (剪映草稿导出). Local ffmpeg + one MiMo key, no GPU. | 用 Claude Code skills 把视频做成中文解说成片，可选一键导出可编辑剪映草稿。

Development workflow plugin for AI coding agents with structured req/plan/dev/review/fix loops and a lightweight quick-dev entry.

xllm plugin — cross-vendor LLM advisor plugin for agentic CLIs ( Claude Code, Codex, Grok Build). Diverse providers, models, and effort levels — read-only by default.

24 YouTube creator skills, 5 specialist Claude Code subagents and 11 local Python tools for Claude Code, ChatGPT and OpenAI Codex. Plan Shorts and long-form, write scripts, titles, thumbnails and SEO, and analyze your analytics — no API key or uploader. MIT.

Reusable GitHub Actions for deploying to ZAD (Zelfservice voor Applicatie Deployment)

Auto-activating, multi-agent skill ecosystem for Claude Code, Codex, and Cursor. 51 skills, 26 agents, quality gates, knowledge store, adversarial review, content writing & optimization.