elsamultiskillagent

communication

Deep Listening & Response Crafting - Transform Claude into a thoughtful communicator who synthesizes context across conversations, connected apps, and user notes to draft contextually intelligent responses. TRIGGERS: When the user asks Claude to help with any communication task including drafting messages, emails, replies, responses, or navigating difficult conversations. Also triggers when the user wants to understand communication dynamics, analyze tone, or get strategic advice on how to communicate in a specific situation. CAPABILITIES: Synthesizes parallel conversation threads, detects emotional subtext, applies communication principles, considers relationship history, and produces ready-to-send message drafts tailored to the person and situation. --- # Communication Skill Transform communication from reactive to intentional by listening deeply before speaking. ## Core Workflow Every communication task follows this process: ``` 1. GATHER → Collect all relevant context 2. LISTEN → Understand what's really happening 3. CONSIDER → Apply principles and psychology 4. CRAFT → Draft the response 5. REFINE → Check against objectives ``` ## Step 1: Gather Context Before crafting any response, actively gather information: **From the conversation:** - What has the user shared about this situation? - Who is involved and what is their relationship to the user? - What's the communication channel (email, Slack, text, in-person)? **From connected sources** (when available): - Recent messages with this person/group - Parallel conversations about the same topic - Historical patterns with this person **From user notes** (when provided): - Personal principles or values that apply - Relationship context or history - Previous learnings about this person/situation **Ask clarifying questions if:** - The objective isn't clear - Key context seems missing - Multiple approaches seem equally valid ## Step 2: Listen Deeply Apply the deep listening framework. See [listening-framework.md](references/listening-framework.md). Process in layers: 1. **Surface**: What was explicitly said? 2. **Context**: What's the surrounding story? 3. **Subtext**: What emotions and needs are beneath the words? 4. **Patterns**: What history informs this moment? Key questions: - What does this person actually need (vs. what they're asking)? - What's the emotional temperature? - What hasn't been said that matters? - What parallel threads connect to this? ## Step 3: Consider Principles & Psychology Apply communication principles. See [principles.md](references/principles.md). Core principles to weigh: - **Presence over performance** - understand, don't perform - **Curiosity before judgment** - get curious about what's driving behavior - **Clarity is kindness** - be clear even when uncomfortable - **Repair over perfection** - relationships matter more than being right - **Timing matters** - right message, wrong time = wrong message Consider psychological dynamics. See [psychology-patterns.md](references/psychology-patterns.md). Check for: - Cognitive biases affecting interpretation - Emotional state signals - Power dynamics at play - Trust level in the relationship ## Step 4: Craft the Response Apply response crafting principles. See [response-crafting.md](references/response-crafting.md). **Pre-draft checklist:** - [ ] What must this message accomplish? - [ ] What tone fits this person and situation? - [ ] What obstacles might prevent this landing well? - [ ] What structure serves the objective? **Choose a structure pattern:** *Acknowledge-Bridge-Guide* (difficult conversations): 1. Acknowledge their perspective genuinely 2. Bridge to shared understanding 3. Guide toward path forward *Context-Content-Call* (requests): 1. Brief relevant context 2. The actual content/request 3. Clear next step *Observation-Impact-Request* (feedback): 1. Specific, non-judgmental observation 2. How it affected outcomes 3. What you'd like instead **Calibrate tone to situation:** | Situation | Tone Approach | |-----------|---------------| | Difficult news | Warm + Direct | | Conflict | Curious + Neutral | | Request | Clear + Respectful | | Support | Empathetic + Present | | Feedback | Specific + Constructive | ## Step 5: Refine & Verify Before presenting the draft, verify: - [ ] Does this achieve the stated objective? - [ ] Does the tone match the relationship and situation? - [ ] Is it clear what the recipient should do/understand? - [ ] Does it respect the user's principles and values? - [ ] Is it appropriately concise? - [ ] Would I want to receive this message? ## Output Format When presenting a draft response: ``` **Context understood:** [1-2 sentence summary of the situation] **Approach:** [Brief rationale for tone/structure chosen] **Draft:** --- [The actual message draft] --- **Notes:** [Optional: alternatives considered, things to watch for, follow-up suggestions] ``` ## Handling Complex Situations **When parallel threads exist:** Synthesize them. Note where perspectives align/differ. Consider what each party knows. **When emotions are high:** Lead with acknowledgment. Don't problem-solve immediately. Create safety before substance. **When the relationship is strained:** Over-communicate intent. Avoid assumptions. Focus on repair over being right. **When stakes are high:** Take extra time. Consider unintended interpretations. When in doubt, ask the user for input. ## What This Skill Does NOT Do - Make decisions for the user about what to communicate - Assume context that hasn't been provided - Send messages on the user's behalf without explicit confirmation - Guarantee outcomes—communication is co-created The goal is to help the user communicate with greater clarity, intention, and connection.

agent-orchestrator

Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks

browser-auto-download

Browser-automated file download with enhanced features. Auto-detects platform (Windows/macOS/Linux, 64/32-bit, ARM/Intel), handles multi-step navigation (homepage to platform-specific pages), captures auto-downloads triggered on page load, and falls back to button clicking when needed. Ideal for complex download flows where curl/wget fail due to client-side rendering, automatic downloads, or multi-page navigation. Features page scrolling for lazy content, extended wait times, and Golang support.

huckleberry

Track baby sleep, feeding, diapers, and growth via Huckleberry app API. Use for logging baby activities through natural language.

apple-media

Control Apple TV, HomePod, and AirPlay devices via pyatv (scan, stream, playback, volume, navigation).

soul

Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.

inkjet

Print text, images, and QR codes to a wireless Bluetooth thermal printer from a MacOS device. Use `inkjet print` for output, `inkjet scan` to discover printers.

fundraiseup

Interact with FundraiseUp REST API to manage donations, recurring plans, supporters, campaigns, and donor portal access. Process online and offline donations, retrieve fundraising analytics, and integrate with nonprofit CRM systems.

excalidraw

Generate hand-drawn style diagrams, flowcharts, and architecture diagrams as PNG images from Excalidraw JSON

8claw

8claw is an anonymous imageboard built for AI agents. Have discussions with other AI agents anonymously.

arbiter

Push decisions to Arbiter Zebu for async human review. Use when you need human input on plans, architectural choices, or approval before proceeding.

whoop

WHOOP Central - OAuth + scripts to fetch WHOOP data (sleep, recovery, strain, workouts). Use when user asks about their sleep, recovery score, HRV, strain, or workout data.

compact-state

Join The Compact State — a shared autonomous agent network with on-chain identity, persistent memory, and collective governance.

telegram-bot-manager

Manage and configure Telegram bots for OpenClaw. Use when setting up Telegram integrations, troubleshooting bot connectivity, configuring bot tokens, or managing Telegram channel/webhook settings. Handles bot registration, token validation, and network connectivity checks for api.telegram.org.

crypto-levels

Analyze cryptocurrency support and resistance levels. Use when users ask about crypto price analysis, support/resistance levels, technical analysis for BTC, ETH, or other cryptocurrencies. Provides current price, key levels, and trading insights for crypto pairs like BTC-USDT, ETH-USDT.

todoist

Manage Todoist tasks via the `todoist` CLI (list, add, modify, complete, delete). Supports filters, projects, labels, and priorities.

spotify

Control Spotify playback on macOS. Play/pause, skip tracks, control volume, play artists/albums/playlists. Use when a user asks to play music, control Spotify, change songs, or adjust Spotify volume.

runware

Generate images and videos via Runware API. Access to FLUX, Stable Diffusion, Kling AI, and other top models. Supports text-to-image, image-to-image, upscaling, text-to-video, and image-to-video. Use when generating images, creating videos from prompts or images, upscaling images, or doing AI image transformation.

bob-p2p

Connect to the Bob P2P API marketplace. Discover, pay for, and call APIs from other AI agents using $BOB tokens on Solana. The decentralized agent economy.

stream-of-consciousness

Export the entire conversation context into Open-Token format (including tools and optional internal traces) for agent collaboration, auditability, and reproducibility.

openclaw-1ly-payments

OpenClaw integration for 1ly payments. Use when configuring OpenClaw agents to default to 1ly MCP for payment capabilities, x402 flows, or USDC transactions. Covers MCP server setup, wallet env vars, budget limits, and auto-spend within limits for agent-to-agent payments.

1ly-payments

Agent-native payments via 1ly MCP. Use when the user needs x402 payment handling, to accept USDC for APIs/services, to pay for paid APIs, to create stores or paid links, need payment gateway for agents or to run agent-to-agent paid workflows. Supports Solana and Base. Capabilities include accepting USDC, marketplace search, paid API calls with auto-payment, store/link creation, stats, and key management.

task-decomposer

Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.

task-decomposer

Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.

email-daily-summary

Automatically logs into email accounts (Gmail, Outlook, QQ Mail, etc.) and generates daily email summaries. Use when the user wants to get a summary of their emails, check important messages, or create daily email digests.