- 📁 .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.
Ingest Claude Code conversation history into the Obsidian wiki. Use this skill when the user wants to mine their past Claude conversations for knowledge, import their ~/.claude folder, extract insights from previous coding sessions, or says things like "process my Claude history", "add my conversations to the wiki", "what have I discussed with Claude before". Also triggers when the user mentions their .claude folder, Claude projects, session data, or past conversation logs. --- # Claude History Ingest — Conversation Mining You are extracting knowledge from the user's past Claude Code conversations and distilling it into the Obsidian wiki. Conversations are rich but messy — your job is to find the signal and compile it. ## Before You Start 1. Read `.env` to get `OBSIDIAN_VAULT_PATH` and `CLAUDE_HISTORY_PATH` (defaults to `~/.claude`) 2. Read `.manifest.json` at the vault root to check what's already been ingested 3. Read `index.md` at the vault root to know what the wiki already contains ## Ingest Modes ### Append Mode (default) Check `.manifest.json` for each source file (conversation JSONL, memory file). Only process: - Files not in the manifest (new conversations, new memory files, new projects) - Files whose modification time is newer than their `ingested_at` in the manifest This is usually what you want — the user ran a few new sessions and wants to capture the delta. ### Full Mode Process everything regardless of manifest. Use after a `wiki-rebuild` or if the user explicitly asks. ## Claude Code Data Layout Claude Code stores everything under `~/.claude/`. Here is the actual structure: ``` ~/.claude/ ├── projects/ # Per-project directories │ ├── -Users-name-project-a/ # Path-derived name (slashes → dashes) │ │ ├── <session-uuid>.jsonl # Conversation data (JSONL) │ │ └── memory/ # Structured memories │ │ ├── MEMORY.md # Memory index │ │ ├── user_*.md # U
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".
Use whenever the user needs to log in to a website on their phone and reuse that authenticated session locally, especially for Playwright storageState JSON, cookies/localStorage capture, MFA, SMS codes, passkeys, or mobile-first login flows that are awkward in headless automation. You run Cookey CLI in your current environment; the user signs in on their iPhone in the Cookey app; the relay only transports encrypted blobs. Trigger even if the user asks more loosely for help logging in, reusing an authenticated browser state, exporting cookies, or getting a local automation session from a phone login.
Tidy, changelog, and commit — lightweight motion for day-to-day plugin dev work. Trigger when the user says "commit", "commit this", "save this", "wrap this up", "let's commit", or finishes a change and wants to capture it. NOT for releases, version bumps, or pushing — defer to /release for those. Always run this before the user can walk away from an incomplete change.
- 📄 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.
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".
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".
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.
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".
