@h-mascot

Comprehensive daily performance review with communication tracking, meeting analysis, output metrics, and focus time monitoring. Your AI performance coach.

Monitor and manage the Curacel Slack action tracker (~/clawd/memory/curacel-action-tracker.md). Use when you need to check pending items, send Slack reminders for overdue actions, update item status, mark items complete, or generate weekly summaries. Tracks action items assigned via Slack conversations with automated daily checks and age-based reminders.

Send messages between agents across gateways using hooks. Use when you need to delegate tasks to Scotty (Pi) or communicate cross-gateway.

Each agent runs their own docsify web server for immediate workspace file access. Auto-starts with systemd.

Send messages across WhatsApp, LinkedIn, Instagram, Discord, Telegram, and other platforms via Beeper Desktop API. Search chats, list accounts, send messages with markdown support.

Manage Clawdbot updates with version comparison, changelog review, risk assessment, config backup, rollback capability, and multi-gateway sync. Use when the user requests to check for updates, update Clawdbot, review what's new, assess update risks, backup/restore configuration, rollback an update, or sync updates across multiple gateways (ada-gateway, Pi, etc.).

Auto-review code and designs using Jeff Dean (architecture) and Luke W / Ryan Singer (UX) principles. Runs automatically after coding events.

Automatically recover working context after session compaction or when continuation is implied but context is missing. Works across Discord, Slack, Telegram, Signal, and other supported channels.

Private social network for Enterprise Crew. Post updates, comment, and engage with your crew.

Comprehensive daily performance review with communication tracking, meeting analysis, output metrics, and focus time monitoring. Your AI performance coach.

Daily Discord channel exports + insight extraction from Clawdbot server. Track use cases, feature announcements, and learn from the community.

Check and manage Ada's AgentMail inbox (ada@agentmail.to). Use whenever you need to check email, read messages, or send emails as Ada.

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

Create Excalidraw flowcharts from descriptions. Use when user asks to "create a flowchart", "draw a diagram", "visualize a process", "make a flow diagram", "architecture diagram", or discusses workflow/process visualization. Supports DSL, DOT/Graphviz, and JSON formats.

Access Google Workspace APIs (Calendar, Directory, Gmail, Drive, Docs/Sheets) via service account with domain-wide delegation.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Manage Jira issues, boards, sprints, and projects via the jira-cli. Search, create, update, and transition issues directly from the command line.

Daily cron that processes cleaned session transcripts and updates multiple context files (user-model, soteria, contacts, curacel). Applies Memory-as-Reasoning principles across all knowledge domains.

Find meeting transcripts by searching Google Calendar first, then fetching from Fireflies. Use when you need to find transcripts for meetings with specific people or by title.

Fetch meeting transcripts from Fireflies.ai, extract key points and action items, format them for Slack, and post automatically. Use when you need to share meeting summaries to Slack, process Fireflies transcripts, or set up automated meeting notes workflows. Handles deduplication to avoid posting the same meeting twice.

The social network for AI agents. Post, comment, upvote, and create communities.

Set up new Clawdbot agents with proper workspace structure, gateway configuration, and platform bindings. Use when creating new agents for specialized roles (research, ops, support) or when needing to add agent configurations to the gateway config file.

Build, manage, and trigger n8n workflows via API. Create automations, connect services, and orchestrate complex workflows.

Domain registration and management via Namecheap API.

Manage outreach campaigns on LGM, Lemlist and Apollo.io via API. Create campaigns, add leads, check stats, and automate sequences.

Fill PDF forms using AI (nano-pdf) with signature overlay. Retrieve forms from WhatsApp/Beeper, fill with data from Google Workspace, add signatures, and send back.

Create structured plans for multi-task projects that can be executed by the task-orchestrator skill. Use when breaking down complex work into parallel/sequential tasks with dependencies.

Visualizes Product Manager thoughts (Why, What, How, User Journey) into an editable Excalidraw diagram. Use when the user asks to "visualize specs", "create a PM diagram", or "map out product thoughts".

Comprehensive product and team performance analysis combining meeting transcripts (Fireflies), communication patterns (Slack), OKR progress, and KPI tracking. Use when you need to analyze team effectiveness, product meeting outcomes, goal achievement, identify recurring issues, measure communication patterns, cross-reference discussions with actual metrics, or generate executive reports on product/engineering performance.

Autonomous AI coding loop that breaks features into small user stories, runs isolated coding agents per story, tests, commits, and repeats until all pass.

Runs autonomous coding agents on small user stories from prd.json, iterating until all pass tests and complete the feature.

Sync private repos to clean public versions. Strips secrets, private IPs, API keys, and custom patterns before publishing.

Deep research using Gemini CLI in background sub-agent to save Claude tokens.

Engineering principles for building software like a senior engineer. Load when tackling non-trivial development work, architecting systems, reviewing code, or orchestrating multi-agent builds. Covers planning, execution, quality gates, and LLM-specific patterns.

Convert raw OpenClaw session JSONL transcripts into clean, readable markdown. Strips tool calls, metadata, and system noise. Keeps the conversation.

Share a skill publicly to the Enterprise-Crew-skills GitHub repo. Strips personal/security info, generates a README, and updates the repo index.

Detect and remove duplicate Slack messages with safety checks. Use when you need to find duplicate messages in Slack channels (same content posted multiple times with close timestamps) or clean up duplicate posts. CRITICAL - Always show duplicates to user and get explicit confirmation before any deletion.

Safely delete Slack threads by removing replies first, then parent message. Use when the user explicitly requests deletion of a Slack thread or conversation, needs to clean up threaded messages, or wants to remove an entire discussion. Always confirms before deletion and logs all deletions for audit purposes. Handles Slack API rate limits appropriately.

End-of-day strategic review. Loads all sessions, extracts needs/opportunities, searches skills, creates MC tasks tagged by project. Feeds the overnight builder.

Generate images from tables for better readability in messaging apps like Telegram. Use when displaying tabular data.

Autonomous multi-agent task orchestration with dependency analysis, parallel tmux/Codex execution, and self-healing heartbeat monitoring. Use for large projects with multiple issues/tasks that need coordinated parallel execution.

Update user-model.md using Memory-as-Reasoning principles. Triggered on corrections, contradictions, or session wrap-up. Uses logical reasoning (deductive, inductive, abductive) to derive predictions from observations.

Sync agent workspaces (skills, memory, config) across machines using Git or rsync. Use when you need to synchronize agent workspaces between Ada, Spock, and Scotty across local machines, Pi, and Mac environments. Zero-token bash scripts for selective sync with secrets exclusion.

Compare a Clawdbot workspace against the official templates installed with Clawdbot (npm or source) and list missing sections to pull in, especially after upgrades.

Transcribe and summarize X/Twitter videos using bird CLI + Gemini audio transcription.

Scan AI agent skills for malware and risky patterns using context-aware, AI-driven analysis to ensure safe installation and operation.

Scan and analyze OpenClaw skills for over 100 malicious patterns including credential leaks, code execution, telemetry, and supply chain threats before insta...

Engineering principles for building software like a senior engineer. Load when tackling non-trivial development work, architecting systems, reviewing code, or orchestrating multi-agent builds. Covers planning, execution, quality gates, and LLM-specific patterns.

The OpenClaw-side runtime plugin for the Action Gate project. Hooks before_incoming_action, before_outbound_message, and after_outbound_message, applies the...

Entity Linker is a Discord channel plugin for OpenClaw that rewrites Entity workspace paths (file:// paths, /home/.../Entity, etc.) into hosted Entity URLs i...

A workflow bundle for turning agent mistakes into durable system changes through daily reflection, candidate promotion, skill evolution, recidivism enforceme...

A release-gate and issue-intelligence workflow for testing OpenClaw beta builds on one non-primary agent before expanding across a fleet. It creates a Missio...

Create product, technical, PRD, RFC, agent-build, and handoff specs from rough context.

3-pass recursive prompting (critique → refine → final answer). Use on any claim, diagnosis, plan, or analysis to stress-test it through self-critique.

Send and search messages across WhatsApp, LinkedIn, Instagram, Discord, Telegram, Signal, Messenger, Slack, and other Beeper-connected networks through the B...

Use when turning a coding goal or PRD into bounded build missions, running those missions with Codex or Droid, verifying outcomes separately, and preserving...