Packages

Indexes Claude Code session JSONL files from ~/.claude/projects/ into a local SQLite database (with FTS5) to enable fast full-text search, retrieval of conversation excerpts, analytics over usage, and cross-session synthesis (optionally using the Anthropic SDK for standalone synthesize). It can also capture live “topics” during sessions via Claude Code hooks and runs background indexing to keep the index up to date.

A Claude Code skill that generates Mermaid (.mmd) diagrams from user requests, validates Mermaid syntax before export, and exports to PNG/SVG/PDF using either local mermaid-cli (mmdc) or a fallback Kroki API endpoint.

application-skills provides a large catalog of app-specific “skills” (one per integration) for AI agents to perform actions (e.g., Gmail/Slack/HubSpot/Salesforce) using the Membrane platform and the Agent Skills specification. Skills describe each app’s structure, available actions, and how to invoke them via compatible agent CLIs/hosts.

Only one skill in the public repo (for now):

strategic-partner is a Claude Code “advisory skill” that separates planning/advising from implementation execution. It asks clarifying questions, challenges premises, proposes alternative solution paths, then generates scoped, self-contained prompts for fresh executor sessions. It maintains persistent decision context via Claude/Serena/memory handoffs while keeping execution context disposable; it also supports optional cross-model review via Codex CLI for high-stakes changes.

A Claude Code skill that guides a 10-step pipeline to extract and render vertical short-form videos from a long input video. It transcribes with word-level timestamps (faster-whisper), has Claude score and select candidate segments, snaps cut boundaries to word/sentence/audio silences, then uses Remotion to render animated caption styles and exports platform-optimized encodings (e.g., YouTube Shorts/TikTok/Instagram Reels).

claude-skills is a marketplace-style repository of many standalone “skills” (each with SKILL.md, plugin.json, templates, scripts, references) intended to be installed into Claude Code to help the agent build modern web apps using common patterns and integrations (notably Cloudflare, React, Tailwind v4, and AI tooling).

Provides an “Agent Skills open format” skill containing Core Data best-practice guidance: decision trees and reference documents covering persistence setup, concurrency/thread safety, fetch/performance, schema migration, and CloudKit integration.

Memoh is a self-hosted, always-on AI agent platform that runs multiple independent bot instances in containers with persistent long-term memory. It provides a web UI and integrates with multiple messaging channels (e.g., Telegram/Discord/Feishu/Matrix/WeChat/Email), supports tool use including MCP, and includes capabilities like browser automation and scheduled tasks.

<p align="center">

A Claude Code skill that optimizes oversized CLAUDE.md files using progressive disclosure. Analyzes content tiers, detects encryption constraints, creates sub-documents, and rewrites the main file — with zero information loss.

**Publish articles to DEV.to** from Claude Code — using AppleScript to control your real Chrome browser and DEV.to's internal CSRF API.

[](https://raw.githubusercontent.com/tanveerkhan2005/custom-agent-with-skills/main/skills/research_assistant/agent-skills-custom-with-v2.2.zip)

A Claude Code skill that provides complete DataForSEO API integration for SEO data and analysis.

[](#license)

Edict is an OpenClaw-based multi-agent orchestration system that routes tasks through a structured approval/dispatch workflow (modeled as “three provinces and six ministries”) and provides a real-time dashboard/kanban with sessions, memorials (archive), model configuration, skills management (including remote skills), and controls to pause/cancel/resume tasks.

**Author:** Rohit Chigatapu

Magentic-UI is a human-centered, research/prototype web agent UI that automates web tasks with a browser-based workflow. It exposes step-by-step plans, uses action guards requiring explicit user approval for sensitive operations, supports file upload, and can integrate additional capabilities via MCP servers. It is built with AutoGen and typically runs via Docker; models are configured through environment variables or a YAML config (OpenAI/Azure/Ollama/vLLM).