Development plugins

Claude Code and Codex plugins their authors filed under "development". All categories.

Skills for installing, choosing, migrating to, and receiving from @napolab/texture-bridge APIs (forwardSharedTexture / forwardFrames / shared-texture receivers)

8 skills

naporin0624/electron-texture-bridge 12

Box Kite

claude

One React component that takes CSS properties as typed props and generates atomic CSS at runtime — no CSS files, no build step, renders in a Server Component.

5 skills · 2 MCP servers

box-kite/box-kite 12

dev

claude

AI-assisted development workflow — PR reviews, plan-implement loops, and expert consultation.

5 skills · hooks

basecamp/claude-plugins 12

jj

claude

Jujutsu (jj) version control skills for committing, pushing, opening PRs, and rebasing

3 skills · 3 commands

jeffh/claude-plugins 12

dev

claude

AI-assisted development workflow — PR reviews, plan-implement loops, and expert consultation.

5 skills · hooks

basecamp/plugins 12

Realsee skills for Claude Code: Argus panorama reconstruction and local editable Blender space modeling.

3 skills

realsee-developer/skills 12

ai

claude

AI skill development — crafting agent skills and writing install documentation for autonomous execution.

3 skills

basecamp/claude-plugins 12

codex

claude

Delegate implement, review, and computer-use tasks to a Codex (GPT) subagent, with support for choosing the GPT model

3 skills

jeffh/claude-plugins 12

Checks Salesforce metadata changes before they ship, and traces production errors to the change that caused them.

1 skill · 1 MCP server · hooks

visparashar/sf-preflight 12

ai

claude

AI skill development — crafting agent skills and writing install documentation for autonomous execution.

3 skills

basecamp/plugins 12

gore

claudecodex

Author Gothic 1 Remake mods or safely import, enable, order, analyze, preflight, apply, check status, recover, remove and reset GORE or external mods.

1 skill · 1 MCP server

dh0er/gore 12

Integrate the Channel3 API for product search (text, image, semantic, and agentic), similar-products recommendations, multi-merchant offer comparison, URL lookup, conversational shopping agents, live price and availability webhooks (product subscriptions), price history, click/transaction reporting, and affiliate commissions across TypeScript, Python, and REST — plus a React component library (shadcn registry) for storefront UIs

2 skills

channel3-ai/skills 12

Expert Swift and SwiftUI guidance for state management, navigation, testing, dependency injection, performance optimization, and code quality patterns.

1 skill

efremidze/swift-patterns-skill 12

gdb-mcp

claudecodex

Multi-session GDB and gdbserver debugging through MCP.

1 MCP server

BeaCox/gdb-mcp 12

Rainskills

claudecodex

Install the complete Rainskills AI deployment skill suite as one product.

1 skill

goodrain/rainskills 12

Strict HTML/CSS scenes rebuilt from a reference clip, with timestamp-exact browser comparison, negative controls and runtime controls

1 skill

gokayfem/video-to-css 12

awsh

claude

An `aw` subagent answered by the local awsh harness daemon, plus Aither World skills, the aither output style, brick MCP servers and portable brick hooks.

115 skills · 1 agent · 4 MCP servers

Aitherium/awdk 11

[PowerShell] Навыки для разработки на 1С:Предприятие 8.3 — абстракции над XML-форматами и CLI конфигуратора, плюс глаза и руки для тестирования через веб-клиент.

77 skills

akim-kaneyev/1c-erp-diagnostics 11

[Python] Навыки для разработки на 1С:Предприятие 8.3 — абстракции над XML-форматами и CLI конфигуратора, плюс глаза и руки для тестирования через веб-клиент.

77 skills

akim-kaneyev/1c-erp-diagnostics 11

xenodot

claude

Agents (design → build → verify pipeline), godot-* skills, verification tools and safety hooks for building Godot / Redot / Blazium games with Claude Code.

50 skills · 19 agents · hooks

arthur0n/xenodot-forge 11

Async-offload companion. Delegate reviews, audits, validations, research, summarization, and bulk RAG ingest to vornik-managed agents over MCP; results re-enter Claude's context via a SessionStart digest hook. Per-repo scoping (migration 75) so one project's RAG cleanly serves multiple repos. Also bundles operator lifecycle skills — configure-vornik, validate-install, troubleshoot-vornik, and report-problem — so your assistant drives Vornik's own tooling (config validate/reload, the published reference architecture, the doctor, the failure-class playbook, and the anonymized problem reporter) instead of improvising.

8 skills · 20 commands · 1 MCP server · hooks

EaseIT-cz/vornik 11

add

claude

Agent Driven Development (ADD) — AI-native SDLC methodology. Coordinated agent teams: test-writers, implementers, reviewers, deployers. Spec-driven TDD, trust-but-verify orchestration, maturity lifecycle, away mode, cross-project learning. Multi-runtime (Claude Code + Codex CLI). Pure markdown + JSON on the agent side; jq required for hook scripts (see docs/runtime-dependencies.md).

28 skills · hooks

MountainUnicorn/add 11

abapsmith

claude

MCP server for SAP ABAP development via ADT — read, write, activate, run, debug, and undo via a local write journal (writes opt-in, package allowlist)

18 skills · 1 MCP server

Freight-Art/abapsmith 11

jaiskills

claudecodex

12 personal skills: motion-design (videos people are proud to share), image-to-frontend, insistir (agents checking agents), goal-loop, second-opinion (GPT-6 Astra as advisor, adversarial reviewer or judge, read-only), remote-agents (SSH), agent-sdk-wizard, managed-agents-wizard, metaprompt, askcodex, compound-knowledge, file-todos

12 skills · 4 agents · hooks

JairoTorregrosa/jaiskills 11

juspay

claude

Nix, writing, and tooling skills for coding agents

17 skills

juspay/skills 11

Event Modeling skills for brainstorming, designing, slicing, and validating software systems following the Event Modeling methodology

16 skills

TrogonStack/agentskills 11

Hands Claude Code's work to DeepSeek, Gemini (Antigravity), OpenAI Codex, OpenCode, GitHub Copilot and a local Ollama model as worker CLIs: git-worktree isolation, your verify command, a compact verdict.

1 skill · 12 commands · 1 agent · hooks

rbinar/cli-dispatch 11

Opinionated orchestration of work through two delegation surfaces: dispatched workers (Codex CLI (GPT-6) and Claude subagents) via a task-strategy workflow with model and reasoning-effort routing, fenced write scopes, and independent two-worker verification; and sibling Claude Code sessions via a distribution workflow with session enumeration, mandatory dispatch-message blocks, and explicit stand-down closure. Ships 11 duty agent definitions that pin no model or effort; the routing table sets model and reasoning effort per checkpoint type at spawn time. Both skills are extendable at five workflow positions and via recognized named configuration values; the plugin ships hooks that deliver a project's per-skill extension files (.claude/extensions/work-orchestrator/) wrapped in a structural envelope.

2 skills · 11 agents · hooks

it-bens/ai-tools 11

Skills for writing and reviewing Product Requirements Documents (PRDs) and Feature Requirements Documents (FRDs)

14 skills

TrogonStack/agentskills 11

0.45.8: the recall hint after a failed test run names the exact recall tool and says to call it now, the wording that was followed in every measured Claude Code run (the advisory text was followed in none). 0.45.7: the hint hooks' git-options group is disjoint (a -C or -c value cannot start with a dash), the rule the Hermes plugin now uses; bash's regex was already fast, so this is for parity. 0.45.6: the hint hooks match a git commit after variable assignments with disjoint value pieces, the rule the Hermes plugin now uses (its old rule backtracked exponentially; grep -E never did). 0.45.5: the hint and recall-nudge hooks claim their state with an exclusive file create (bash noclobber, O_EXCL) instead of mkdir, which uutils coreutils on Ubuntu 26.04 does not make exclusive, so a hint fires once, a session's outcomes upload once, and each read takes its own nudge slot (GitHub #687). 0.45.4: the User-Agent hints.sh sends names 0.45.4; the shared hint script is unchanged otherwise, and hooks/hints_cases.json in the Claude Code bundle now holds the hint rules to the same cases as the Hermes plugin's Python port (GitHub #686). 0.45.3: the design-edit hint matches a design document whatever the case of its name, so https://docs.vornik.io counts (GitHub #682). 0.45.2: the recall nudge keeps its state only in the plugin's data directory, or in the per-user runtime directory when the user owns it, never in a shared temp path, and refuses a state directory that is a symlink or that another user owns (GitHub #651). 0.45.1: the design-edit hint also sees a design document written through a shell command (a heredoc, a redirection, tee, sed -i, cp or mv), read from the command text and never run (GitHub #653). 0.45.0: just-in-time hints (GitHub #634). hooks/hints.sh, shared with the Claude Code bundle, prints a short hint from the project's catalogue when it applies: after a commit (send the diff for review), after a design document is patched (ingest it), after a test run whose

10 skills · 1 MCP server · hooks

EaseIT-cz/vornik 11