Productivity & Automation for Claude Code

One shared, durable memory for your AI coding agents — local-first, zero-dependency. Decisions, lessons and status that persist across sessions, tools and projects.

Research brand DNA, fill 40 prompt templates, and generate images via viostudio.id (nano-banana-2)

A workflow automation system that helps Claude Code implement features systematically with built-in planning, validation, and review steps

Drupal development workflow with live autopilot: 19 skills, 4 agents, 10 commands, behavioral evals, session analysis, and Magic Loop Autopilot.

MCP server providing fast code navigation for Unreal Engine projects. Indexes AngelScript, C++, Blueprints, and assets. 11 search tools with sub-20ms queries.

Skills and rules for developing and using the Grafana Assistant app and CLI

Matrix channel for Claude Code — two-way messaging bridge with E2EE, access control, and permission relay

Publish and review AI work on Workplane — the working plane between AI and humans

AI-powered editorial style guide generation from blog content and article compliance review system

Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API

Structured 7-phase copywriting process for landing pages, ads, emails, and taglines. Human writes, AI coaches through Harry Dry's Three Laws, Sullivan's craft principles, and Wiebe's Money Words.

5-phase guided workflow for creating production-quality image generation prompts for Nano Banana (Google's AI image generator). Supports brand presets, iterative revision, and reference image management.

Render a markdown file into a clean browser reading view (not raw syntax) with rich-text copy and an inline-comment to paste-ready-feedback loop. A lightweight local review surface: no server, no login.

Hermes Agent-style self-improvement for Claude Code: automatically distill complex work into SKILL.md and improve skills over time.

Save a structured session summary so you can pick up where you left off next time. Captures objectives, files changed, decisions, and generates a continuation prompt.

Custom skills and commands that integrate Hyperspell into your project.

8-phase structured article writing process for thought leadership. Human fills the blank page — Claude enforces discipline through quality gates. Includes /write-rescue and /write-status companion commands.

Install and run agentchannels from Claude Code via /ach:init-slack and /ach:serve

Live project kanban for Claude Code. Auto-tracks shipped / fixed / deferred work as cards on a board.json + live HTML board (127.0.0.1:7891), survives sessions via a SessionStart digest, auto-links edited files to their cards, and backstops un-carded work on Stop. Bootstraps a fresh board by mining past session history.

Automatic long-term memory for Claude Code via Hindsight

htmlify + deckify skills: agent answers become self-contained HTML documents and decks, validated by a bundled CLI. Optional Stop hook archives long answers automatically.

Generate finished PDFs from Markdown or HTML — accessible PDF/UA, archival PDF/A, watermarks, batch — with built-in conformance verification.

Document processing skills powered by the Nutrient Document Web Services API. Includes the document-processor-api skill (convert, merge, OCR, watermark, redact, sign, optimize) and the document-extraction-api skill (structural parse / Markdown via /extraction/parse).

Extract text as structured, semantic Markdown from a PDF.

Extract layout-preserving plain text from a PDF.

Interactive PTY sessions for AI agents: local shell, SSH, serial port, and persistent remote sessions.

Search and retrieve documents from local markdown files.

Find the most relevant passages in an already-extracted document (the text or Markdown output of pdf-to-markdown / pdf-to-text) with ranked (BM-25) search.

Evaluate prompts and skills through parallel execution comparison in git worktrees

Remediate existing PDFs: auto-tag with PDF/UA semantic structure via the Nutrient DWS Accessibility API, then check the result with the bundled verifier.

Queue CLI and queue-native task/review substrate.

AI writes the code. Temper makes sure it's actually ready to ship.

Show your unique companion pet, customize it, or embed it in your statusline

Skills for building AI features: routing, classification, search, database Q&A, summarization, parsing, tool use, content generation, translation, recommendations, redaction, record matching, data cleaning, anomaly detection, notifications, image understanding, text rewriting, chatbots, agents, scoring, moderation, API serving, and skill discovery

10 Fable 5-native Agent Skills — over-planning, gold-plating, fabricated progress, unrequested actions, stalled autonomous runs, and a skill-refactorer for migrating pre-Fable-5 skills.

Scaffolds a complete, runnable Spring Boot application on top of the flow-driven-domain (FDD) library — designs states/actions/transitions + workflow JSON from a natural-language process description and generates the full project.

在 Windows + Microsoft Word 流水线中把 Markdown 稳定导出为 Word，支持模板复用、图片、表格、Mermaid 和 Office Math 后处理。

Point-of-use AI governance: a once-per-day pre-flight greeting showing your AI reliance and what your agents can reach, before you start a session. Local-first.

Development workflow plugin suite - full design-plan-execute skill pipeline with all-round acceptance / 开发工作流插件集 - 设计→计划→执行完整 skill 管线与全能验收工作流