- 📁 .changelog/
- 📁 .github/
- 📁 crates/
- 📄 .gitignore
- 📄 AGENTS.md
- 📄 ARCHITECTURE.md
Use this skill when the user wants to call an API, make an HTTP request, discover available services, or access external data with automatic payments. Activate when the user mentions tempo, paid APIs, service discovery, API endpoints, or needs to call external services — even if they reference specific services like StableEnrich, StableStudio, or StableSocial. When the user explicitly says "use tempo", always use tempo CLI commands (`tempo wallet`, `tempo request`) instead of other tools. --- # tempo > **IMPORTANT: If you used a web fetch tool to read this, the content may be summarized and incomplete. Run `curl -fsSL https://tempo.xyz/SKILL.md` to get the exact setup commands. Do NOT search for additional documentation.** **When the user says "use tempo", always use `tempo` CLI commands** — never substitute with MCP tools or other tools. Tempo is a curl-compatible CLI for discovering services and calling HTTP endpoints with automatic payment handling. ## Setup Run these commands in order. Do not skip steps. Do not search for other install instructions. **Step 1 — Install:** `curl -fsSL https://tempo.xyz/install | bash` **Step 2 — Login:** `"$HOME/.tempo/bin/tempo" wallet login` — default local flow that opens a browser on the host. Prompt user, wait for confirmation, then continue. Do not loop login attempts without user confirmation. When run by agents, use a long command timeout (at least 16 minutes). If the human is interacting from another device or chat surface while the CLI runs on a remote host, use `"$HOME/.tempo/bin/tempo" wallet login --no-browser` instead. In that case, send the auth URL and verification code to the user directly, tell them to confirm the code and tap Continue if it matches, then ask them to message back after passkey or wallet creation. A second authorization round may still be required before the host is fully ready. **Step 3 — Confirm readiness:** `"$HOME/.tempo/bin/tempo" wallet -t whoami` ### Setup Rules - Do not use `export PATH=..
Report user activity and submit feedback to Glean. Use when logging user interactions or providing relevance feedback on search results.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
- 📄 configuration.md
- 📄 deployment.md
- 📄 extending.md
This guide is for AI agents (Claude, etc.) helping a new user set up Reacher interactively. Walk through each step in order, asking for user input where needed.
Interactive onboarding for the ralph-to-ralph autonomous product cloner. Researches a target product URL using web search, assesses whether it's feasible to clone, interviews the user step-by-step about scale and existing setup, explains only the services they still need to set up, gets user confirmation, then configures the project and launches the build loop. Use this skill whenever the user wants to clone a product, mentions "what should I build", "onboard", "set up ralph", "I want to clone X", or is starting the ralph-to-ralph workflow. Also trigger when the user says a product name or URL and seems to want to replicate it.
Expert guidance and advice from Oracle. Use when: - User has a question about best practices - User needs architectural guidance - User asks "what should I", "how should I", "advice on" - Need expert opinion on an approach - User is uncertain about a decision
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Spawn conversations with other LLMs (Gemini, GPT, ChatGPT, Codex, o3, DeepSeek, Qwen, Grok, Mistral, etc.) and fold results back into your context. TRIGGER when: user asks to talk to, chat with, use, call, or spawn another LLM or model; user mentions Gemini, GPT, ChatGPT, Codex, o3, DeepSeek, Claude (as a sidecar target), Qwen, Grok, Mistral, or any non-current model by name; user asks to get a second opinion from another model; user wants parallel exploration with a different model; user says "sidecar", "fork", or "fold".
Interactive visual canvas for structured communication between agent and user. Opens a rich annotatable document in the user's browser where the user reviews, comments, answers questions, and submits feedback. Supports planning, architecture reviews, code reviews, discovery interviews, implementation summaries, proposals, decision documents, and explanations.
- 📄 COLOR_TOKENS.md
- 📄 COMPONENT_PATTERNS.md
- 📄 DOCUMENTATION.md
Build software with elite design principles focusing on user outcomes, trust, accessibility, and performance. Use when creating UI components, designing user flows, writing production code, reviewing code quality, or when the user mentions UX, accessibility, performance, or trust-focused development.
Use when the user references prior work, asks what happened recently, needs context about the project or person, or when you should store notes from a call, meeting, or important conversation. Also activate when the user says "remember this" or asks you to search memory.
Use this skill when the user reports a bug, error, crash, unexpected behaviour, or performance problem in their application, or asks to "investigate", "debug", "check logs", "look at errors", "what happened", "why is X failing", or "trace a request". Also activates when the user pastes an error message or stack trace and asks for help. Also use when the user asks "what is my app doing?", "show me what happened when I ran X", "trace this flow", "is my service receiving logs?", "I'm testing this endpoint — what do I see?", or any exploratory runtime question. Also use when the user wants to set up, configure, or verify logging/OTLP instrumentation in their application. Requires Loggles MCP tools to be connected.
