dept-agents

Build and publish a website. Use whenever the user asks to make, create, build, or publish a website, landing page, dashboard, status page, one-pager, or anything else a human will load in a browser. Covers both the publish recipe (no tunnels, no third-party hosts) and the design discipline that keeps the result from looking like generic AI slop.

Use for Clemson GC curriculum content questions — what a specific course teaches, what skills or projects it includes, what assignments are used, where a topic or learning outcome is covered, and how courses relate to each other pedagogically. This is about course *content*, not degree rules or credit requirements (use gc-advisor for those).

Use for ANY Clemson procurement or purchasing question — what's allowed or required, policy, rules, P-card, requisitions, purchase orders, suppliers, approvals, spending limits, bids/quotes. Use the procurement tools; never answer Clemson procurement from your own knowledge.

Use for Clemson class schedules and instructor scheduling — finding course sections, what an instructor is teaching, section details (time/seats/location), room availability, and academic terms. Use these tools, not your own knowledge.

Use for questions about Clemson Graphic Communications alumni outcomes — where graduates work now, first-job placement, career trajectories, AI exposure of GC occupations, industry/occupation distribution, grad-school rates, and outcome trends by graduation cohort. Data comes from the gc-alumni MCP server (read-only SQLite). For degree rules or course content use gc-advisor or clemson-curriculum instead.

Use for Clemson GC degree rules and academic requirements — degree audit (which requirements has a student met?), credit counts, gen-ed rules, specialty-area rules, prerequisite checking, course planning, and academic regulation lookups. This is about *rules and requirements*, not course content or pedagogy (use clemson-curriculum for what a course teaches, its skills/projects/assignments). Always pulls from the pinned catalog database — never from memory or the live website.

Install one or more host-side Telegram admin tools (/auth, /model, /provider) into the running NanoClaw instance. Trunk ships without them so the base codebase stays lean; operators opt in via this skill. Triggers on "add admin tools", "install admin commands", "add /model", "add /auth", "add /provider".

Read an image file's basic facts — format, dimensions, aspect ratio, orientation, file size, megapixels. Use when the user attaches an image and asks about its size, dimensions, resolution, or whether it fits a format (e.g. a square logo, a banner aspect ratio).

Look at what's actually in an image — describe the scene, subjects, colors, mood, text, composition. Use when the user attaches a photo and asks what's in it, to critique it, or anything that requires seeing the picture content (not just its file facts).

Get current weather for any city using the free Open-Meteo API (no API key needed). Use whenever the user asks about weather, temperature, or conditions somewhere.

Generate time-limited single-use HTTP URLs that bundle everything needed to clone this NanoClaw install onto a new machine. Replaces the hand-rolled _migrate-<token>/ + python -m http.server pattern. Triggers on "install handoff", "clone install", "migrate to new machine", "setup handoff URL".

Switch from Docker to Apple Container for macOS-native container isolation. Use when the user wants Apple Container instead of Docker, or is setting up on macOS and prefers the native runtime. Triggers on "apple container", "convert to apple container", "switch to apple container", or "use apple container".

Add an embedded HTTP + WebSocket chat server with PWA frontend. Provides a web chat interface for talking to NanoClaw agents from the browser, with bearer / tailscale / proxy-header auth and Web Push.

Use OpenCode as an agent provider (AGENT_PROVIDER=opencode). OpenRouter, OpenAI, Google, DeepSeek, etc. via OpenCode config — not the Anthropic Agent SDK. Per-session and per-group via agent_provider; host passes OPENCODE_* and XDG mount when spawning containers.

Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, Codex-owned context management, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).

Add Signal channel integration via signal-cli TCP daemon. Native adapter — no Chat SDK bridge.

Add a persistent wiki knowledge base to a NanoClaw group. Based on Karpathy's LLM Wiki pattern. Triggers on "add wiki", "wiki", "knowledge base", "llm wiki", "karpathy wiki".

Install and initialize OneCLI Agent Vault. Migrates existing .env credentials to the vault. Use after /update-nanoclaw brings in OneCLI as a breaking change, or for first-time OneCLI setup.

Add persistent graph-based memory via mnemon. Agents recall past context before responding and remember insights after each turn.

Maintain the persistent course-content wiki for this group. Use whenever the user adds a source (article URL, PDF, image, voice note, screenshot, transcript), asks a question whose answer should be filed back into the wiki, or asks for a wiki health-check. Implements Karpathy's LLM Wiki pattern.

Add the Agent Playground — a web workbench for iterating on agent personas, skills, and provider settings before applying them to a live agent group. Triggered by /playground on Telegram (lazy-start), magic-link auth, idle-timeout protected.

Generate images with OpenAI's gpt-image models. Use when the user asks you to create, draw, make, design, or generate a picture, image, illustration, logo, diagram, or artwork. Saves the result to the group workspace and delivers it via send_file.