Prompts, Context & Memory

End-of-session ritual that turns sessions into institutional memory via Zengram. Detects repeatable workflows worth capturing as skills AND mistakes/corrections worth capturing as CLAUDE.md rules. Reflects honestly, stores to Zengram, updates local memory, spots workflow patterns, and proposes rule updates. Use when the user types /sessionend, says they're done, wrapping up, signing off, 'that's it for today', 'end session', 'let's wrap up', 'save and close', or any signal that the session is ending. Also triggers on 'session summary', 'what did we do', or 'capture this session'. This is the closing ritual — if a session is ending, start here.

Make AI-generated prose sound human.

Clarity gate for prompts: intercepts unclear requests and forces AI to restate intent to align with the user, then diagnose the root cause and reuse the domain's mature, established practices before proceeding.

Add Microsoft Teams as a channel. Can replace WhatsApp entirely or run alongside it. Uses the Azure Bot Service (Bot Framework) and requires a public HTTPS messaging endpoint.

Personal AI that remembers your conversations and gets better over time.

Local-first memory layer for AI agents - MCP server

Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

Add Gmail integration to Deus. Can be configured as a tool (agent reads/sends emails when triggered from WhatsApp) or as a full channel (emails can trigger the agent, schedule tasks, and receive replies). Guides through GCP OAuth setup and implements the integration.

Next-gen AI memory layer with hierarchical memory, importance scoring, and temporal retrieval

Install a global hotkey that triggers deus listen from anywhere on the OS. Also installs sox, whisper-cli, and a whisper model.

Add Asana project management MCP integration to Deus. Gives host-side Claude Code sessions read/write access to Asana tasks, projects, sections, and tags via @roychri/mcp-server-asana.

Business Analyst Skill. Triggered when users ask about business analysis, industry research, competitive analysis, product analysis, business model analysis, business opportunity discovery, market entry strategy, investment decisions, strategic planning, due diligence, and other strategic topics. Delivers in-depth, decision-grade HTML research reports through a seven-stage workflow (Briefing → Framing → Planning → Research → Insights → Report → Iteration).

Add Outlook (Microsoft 365 email) integration to Deus. Can be configured as a tool (agent reads/sends mail when triggered) or as a full channel that polls the inbox. Uses the Microsoft Graph API and Azure AD OAuth.

[DEPRECATED] Replaced by scripts/code_search.py (native sqlite-vec + Ollama). Do not use.

A framework for defining, managing, and applying prompt decorators to enhance interactions with LLMs

Container-side agent runner for Deus

Add Telegram as a channel. Can replace WhatsApp entirely or run alongside it. Also configurable as a control-only channel (triggers actions) or passive channel (receives notifications only).

情圣 — 中文男性社交与恋爱私教（中文恋爱 AI · 恋爱话术生成器 · 微信聊天助手 · 高情商回复 · 情感咨询替代）。帮兄弟读懂女生发的消息、看懂聊天/朋友圈截图、判断对方是不是对自己有意思、想清楚下一步该回什么 / 该不该回 / 该怎么约。覆盖微信、探探、Soul、Bumble、青藤之恋、陌陌、Tinder 等平台，提供开场话术、暧昧期推进、约会邀约、冷启动挽回、朋友圈展示面诊断、PUA 课程替代方案、恋爱阶段判断、多目标档案管理。当用户问「她这话什么意思」「我该怎么回」「帮我看看这段聊天」「这截图你给我分析一下」「她对我有意思吗」「该约她了吗」「冷场了怎么破」「这条要不要回」「被已读不回怎么办」「朋友圈怎么评论」之类的问题时，务必使用本 skill。即使用户没明说「教练」「分析」也应触发——只要话题是和某个具体女生的互动就用。

Install and verify a local llama.cpp server for optional Deus local-generation experiments. Keeps Ollama as the required default for embeddings and judge work.

Add Google Calendar integration to Deus. Agents can list, create, update, and delete calendar events. Guides through GCP OAuth setup, token generation, keep-alive timer, and CLI command installation.

remember this and that

Install the Understand-Anything plugin so the agent gains /understand, /understand-chat, /understand-dashboard and related codebase-analysis skills (interactive knowledge graphs, guided tours, deep-dive explanations). Claude Code backend only — adds the plugin from its GitHub marketplace end-to-end; non–Claude-Code backends use the upstream install.sh fallback.

Add PDF reading to Deus agents. Extracts text from PDFs via pdftotext CLI. Handles WhatsApp attachments, URLs, and local files.

Convert long AI conversations into portable conversation state graphs for LLM handoffs.

Add Parallel AI MCP integration to Deus for advanced web research capabilities.

Wire Deus's memory + evolution layers into an external code editor (Zed and other ACP/MCP clients) so the editor's own agent gains Deus's vault recall and self-improving reflexion loop. Configuration only — no new code. Triggers on "add editor", "use Deus in my editor", "zed integration", "editor integration", "wire Deus into Zed", or ACP/MCP editor setup requests.

改写中文学术论文中被知网AIGC检测器标为"红色显著"的段落，目标是将AI率落出红色区间且不改变事实/数字/术语/引用。基于实战将20.6%降至10.1%（净降10.5个百分点）的工作流提炼。使用场景：用户提到"知网AIGC""降AI率""红色显著""降重"或贴出AIGC检测报告片段时触发。

Add /compact command for manual context compaction. Solves context rot in long sessions by forwarding the SDK's built-in /compact slash command. Main-group or trusted sender only.

Add image vision to Deus agents. Resizes and processes WhatsApp image attachments, then sends them to Claude as multimodal content blocks.

Persistent memory for Claude Code agents with an agent-audit-ritual architecture. User only talks; the agent captures, audits, proposes promotions, and writes. Memory lives in layers — a hot cache (MEMORY.md) held under three size caps, per-session handoffs (context/handoffs/), topical knowledge articles (knowledge/concepts/), and canonical rules (.claude/rules/) — plus multi-project isolation via projects/<name>/ and an experiments/ sandbox. /close-session runs the end-of-session audit ritual. Zero external dependencies.

Add WhatsApp emoji reaction support — receive, send, store, and search reactions.

End-of-session ritual — audit today's patterns against accumulated memory, propose promotions, refresh MEMORY.md, and write the session handoff. Use when the user says "/close-session", "закрой сессию", "закрываем", "we're done for today", "wrap up".

Interactive walkthrough of the Memory Kit system using the user's actual project files

Expert Prompt Engineer with Context Engineering, Meta-Prompting, Chain-of-Thought, Few-Shot, Agent Design, 50+ Template Library, and A/B Testing

Critique AI-generated strategy, marketing, and positioning prose. Use for framing-level rewrites that surface hidden assumptions and fake polish, not for factual QA, coding, or basic copyediting.

Audits and optimizes Claude-directing artifacts (CLAUDE.md, SKILL.md, subagent, hook, MCP config, system or user prompt, workflow, api_config) against 189 cited Anthropic rules across 11 dimensions, calibrated per model (Opus 4.7, Sonnet 4.6, Opus 4.6, Haiku 4.5). Every finding ships with verbatim quote and source URL; authorial voice is preserved.