feature-workflow
claudecodex功能開發工作流 — 整合 Notion 與 Claude Code,涵蓋需求分析、規格設計、DB 設計、架構設計、程式碼骨架產生、品質審查到結案的完整生命週期管理
18 skills · 5 agents · hooks
Claude Code and Codex plugins their authors filed under "productivity". All categories.
功能開發工作流 — 整合 Notion 與 Claude Code,涵蓋需求分析、規格設計、DB 設計、架構設計、程式碼骨架產生、品質審查到結案的完整生命週期管理
18 skills · 5 agents · hooks
Automated code review enforcement. Runs autofix, architecture verification, and conversation review -- and blocks sessions from finishing until they pass.
19 skills · 4 agents · hooks
Set up a standardized Claude Code harness for any project. One guided interview configures CLAUDE.md, permissions, hooks, MCP servers, agents, and SSOT docs. Three tiers: Essential (5 min), Standard (15 min), Full (30 min).
13 skills · 4 commands · 2 agents
The whole set in one install - all fifteen skills, namespaced /voidharbor:<name>. Install this bundle, or pick skills a la carte below.
1 skill · 17 commands · hooks
DStack workflows for shaping intent into approved plans, specs, and task lists.
19 skills
Work with your Relewise configuration, analytics and optimization using AI.
15 skills · 1 MCP server
All Xsolla workflow skills in one plugin: shop-setup (coded shop), nocode-shop-setup (Shop Builder), merchant-setup, catalog-design, login-setup, login-styling, headless-checkout-integration, webhooks-impl, production, and quest-setup for Quest Platform quests, rewards, Web Shop modules and Shop Builder Quests block operations. In preview, the Shop Builder path includes description-to-shop, shop-builder-assembly, game-web-portal, shopbuilder-translate and xla-pages (XLA Pages on x.la).
15 skills · 1 MCP server
Paddle Billing skills and MCP servers for Claude Code.
12 skills · 3 MCP servers
요구 구체화부터 구현·검증·복구까지, 사전 합의 안에서 자율 진행하는 한국어 Claude Code·Codex 스킬 13개. 큰 흐름과 반드시 지킬 검증만 정하고 방법은 에이전트에게 맡긴다. / Korean agent skills for Claude Code & Codex: idea → PRD/TRD → architecture → plan → verification harness → autonomous loop, with up-front agreement, ordered quality gates and independent validation.
13 skills
Guardrail-first Spring Boot + JPA toolkit. Just-in-time hooks catch missing @Version, broken @Transactional proxies, entity-in-controller leaks, N+1, and query injection as you write them; scaffold skills generate correct-by-default entities, endpoints, and migrations; a tuned reviewer agent shares one ruleset with the hooks.
11 skills · 1 agent
Bug 文件工作流 — 整合 Notion 與 Claude Code,自動化 Bug 生命週期管理(建立、調查、結案、搜尋、復發處理)
10 skills · 1 agent · hooks
Shared hooks, agents, commands, skills across projects
5 skills · 5 commands · 1 agent · hooks
Self-learning memory system that observes interactions, learns preferences, and makes AI Agents understand you better over time
3 skills · 5 commands · 2 agents · hooks
Cut your Claude token bill 40–90% on verbose/repetitive tool output (less on prose). Automatic compression for Claude Code via hooks, and on-demand compression for Claude Desktop via a bundled MCP server. Compresses prompts, tool outputs, and file reads with mask-union safety for API keys and UUIDs. Part of the AgentOne platform.
1 skill · 8 commands · 1 MCP server · hooks
Chantier→spec→plan→unattended run workflow for Claude Code: cut an initiative into an ordered just-in-time backlog (/goal:tickets), settle the functional contract of any source — Jira US (via MCP), GitHub issue, spec file or inline — with a grilled, observable Definition of Done (/goal:spec), lock the executable plan into gate-blocked iterations (/goal:plan), then let the runner execute it unattended, each slice judged by a program (goal-gate.ts) that runs the declared command and is the only thing allowed to commit — watched to the end by /goal:supervise, with /goal:next as the checkpoint between two iterations. GitHub, commit and PR are all opt-in, never forced.
6 skills · 5 agents
Hooks preserve shared Claude Code and Codex history; /remember recalls it and /turbo keeps the index warm so recall answers in about 0.3 s instead of about 12 s, for both agents
9 skills · 1 MCP server · hooks
Operate Duvo from Claude: debug failed Runs, audit Agents and Queues, doctor Connections, and write AOPs — with the Duvo MCP connector wired in.
10 skills · 1 MCP server
A pack of 11 skills: a conductor plus contract, trace, rca, research, plan, build, review, qa, ship and learn. Each stage does one job and writes to a shared task folder; a ledger script decides when the work is verified.
11 skills
Elf Claude-Skills für deine Steuererklärung (DE und AT): Belege, Kontoauszug, Pendeln, Homeoffice, Werbungskosten, Haushalt, Familie, Rückblick, Formular, Bescheid und Fristen.
11 skills
AutoMode for Claude Code picks the model and the effort for each prompt, runs a plan, build, verify and review workflow, and shows a bar with the prompt-cache countdown.
2 skills · 2 commands · 7 agents
Cross-project semantic memory — harvests sibling-plugin artifacts into reusable memory cards (rule-based plus LLM distillation) and surfaces task-specific briefs, with opt-in cross-runtime hook capture and multi-pass redaction.
7 skills · 1 agent · 1 MCP server · hooks
Read-only access to your Slice cap table, securities, ownership, compliance, workflows, valuations, and equity plans via the Slice MCP server.
8 skills · 1 MCP server
AIBlueprint by Melvynx : agents spécialisés, workflows autonomes (Ralph Loop), hooks sécurité, skills Git/Meta/Utils
7 skills · 2 agents
Claude Code skills for the Builder OS pipeline (PRD → journeys → design → brand → prototype → Blueprint → ship): write and gate PRDs against confidence-tag discipline, map user journeys, prompt Google Stitch for the visual design, write and gate the Blueprint (merged engineering spec + technical reference + step-by-step build plan) before code, drive the mode-aware build sessions with checkpoints enforced, and visualize brand guides.
9 skills
The superagnt base skills: external data in one call, a workspace Postgres, recurring automations, shareable dashboards. On Claude, add the superagnt MCP server as a connector (https://mcp.superagnt.com/mcp); the consent screen doubles as signup.
8 skills · 1 command
Intelligent multi-agent system for delegating analysis, code review, and complex reasoning tasks to local ollama models. Saves 70%+ of Claude's context budget with automatic model selection and parallel processing.
5 commands · 3 agents
[DEPRECATED - Use code-review instead] Comprehensive PR review agents. All functionality has been merged into the code-review plugin with automatic change detection.
1 skill · 1 command · 6 agents
Create, edit, and analyze Microsoft Office documents (Word, Excel, PowerPoint) and PDFs. Includes professional document workflows with tracked changes, form filling, formula validation, and HTML-to-PPTX conversion.
4 skills · 4 commands
DStack workflows for memory, session continuity, decision records, and retrospectives.
8 skills
DStack workflows for teaching, explaining, drilling, and onboarding.
8 skills