Active Directory pentest methodology for Claude Code: skills, agents and slash commands for internal AD red-team work (Kerberoasting, ADCS ESC1-17, DCSync, ACL abuse, NTLM relay, delegation), with per-technique OPSEC/telemetry notes. Drives netexec, impacket, certipy, bloodyAD, BloodHound CE.

Best Motion graphics and video editing skill for Claude Code, Codex and Cursor. Plan, animate, edit, caption and sound-design complete videos, rendered locally without After Effects.

Local-first cross-session long-term memory for DeepSeek Harness: dual-scope SQLite stores, hybrid FTS5 + local-vector retrieval with RRF, an evidence gate, provenance audit and SM-2 spaced repetition. 23 narrow tools, zero external services, zero API keys

Businesses that confirmed their own facts at INITE, found by what they do and where.

政务办事指南巡检插件 — 检测漏项/语义/逻辑/格式错误，输出合规审计报告，516测试全通过，v3.8.1新城市白名单补全+网办深度枚举配置化+表格下载实质内容豁免

Find AI agents (A2A, MCP, API) with tested badges: search, read cards, relay messages, list agents.

Verified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay.

推荐组件（非必须）：DeepSeek Harness 运行时注入器；已随 dsh-routing-suite 单仓库化保留，本仓库继续维护/发布。

RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB, RuLake, SPARC + 21 building blocks. Grounds Claude in real source via one MCP tool (search_ruvnet), so it builds with the stack instead of drifting off it.

DSH 环境自检：让读者看到自己电脑装了什么 —— 系统/CLI/DSH 插件/秘钥是否存在

Shared project memory for people and AI agents: workspaces, documents, ERD, diagrams and boards.

Record demos of your web app from one sentence and turn its product map into help articles and more.

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Local SQLite + Markdown mirrors, autoDream consolidation, 4-way recall (keyword/vector/BM25/entity), and a memory panel. 10 model tools, MCP server, CLI.

Semantic code search plugin for Claude Code using hybrid vector search + BM25. 98% accuracy, 5x faster than grep.

MCP Playbooks for AI agents

Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.

Self-hosted memory service for AI agents that work in teams, written in Rust: layered L0→L3 memory, async LLM distillation, hybrid BM25 + vector recall, and department/team/member isolation. SQLite or Postgres, any OpenAI-compatible LLM.

Query the dshbase plugin directory from inside DeepSeek Harness — search, list, and get install commands for 1700+ plugins.

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

Enables AI apps to query a user's Google Health data—such as sleep, heart rate, HRV, activity, and paired devices—through read-only tools deployed privately in the user's own Firebase project.

Enables MCP clients to inspect PDF structure and extract object-level data such as characters, words, tables, images, fonts, and metadata, with JSON/CSV export and image retrieval.

A code repository indexing tool to supercharge your LLM experience.

Restaurants and bars in 10 cities: hours, menus, dietary tags, events and booking; destinations.

Record demos of your web app from one sentence and turn its product map into help articles and more.