with one click
Corellis
Corellis contains 18 collected skills from CorellisOrg, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
AI team intelligence and fleet management for OpenClaw. Spawn, monitor, and orchestrate a fleet of AI lobster assistants in Docker — with proactive bottleneck detection, peer-to-peer knowledge sharing, health checks, rolling upgrades, and owner notifications.
Distributed goal orchestration system. Decomposes big goals into sub-goals, distributes to lobsters, monitors progress via event-driven + patrol fallback, and verifies completion. Integrates with task boards (Notion/Linear/GitHub) and messaging (Slack/Discord).
Structured workflow for collaborating with ACP coding agents (Claude Code, Codex, Cursor, etc). Confidence-based routing, structured prompts, output verification, and session management. Ensures code changes are correct, tested, and reviewed before merging.
Proactive task discovery engine. Periodically scans task boards (OKR, GitHub Issues, Notion, Linear) for items the lobster can pick up, generates structured approval requests with confidence scoring. Turns lobsters from reactive responders into self-driving agents.
Automatic task decomposition and execution planning. Receives a high-level task, breaks it into subtasks, classifies each (code/research/design/ops), estimates effort, identifies dependencies, and generates a structured plan for owner approval. Works standalone or as part of goal-ops workflows.
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Automatically learn from corrections, errors, and reflections. Triggers when you're corrected, make mistakes, discover better approaches, or complete important tasks. Uses semantic detection — not keyword matching.
Universal approval flow framework — receives structured proposals, sends to Slack channel/DM/thread, parses human approval commands (execute/partial execute/skip/reject), callbacks to execution chain. All scenario SKILLs requiring human approval should call this atomic capability, don't implement approval logic yourself.
Use the local Chrome browser via CDP (Chrome DevTools Protocol) for any task requiring web authentication, cookies, or browser sessions. ALWAYS prefer this over manual cookie env vars. Trigger when: need to access authenticated websites (ASC, Gmail, Notion, etc.), fetch data from sites requiring login, check if user has logged in, or user mentions 'browser', 'noVNC', 'cookie', 'login session'.
Transparent relay/proxy between user and Claude Code (CC) via -p + --resume mode. Activate when user says 'ccp', 'ccp start', or wants to chat directly with CC in multi-turn mode. Agent becomes a pure message forwarder — no thinking, no commentary, no modification. Just relay. Trigger: ccp (not cc relay, to avoid conflict with ACP cc).
Multi-model deep research — supports Claude/Gemini/OpenAI routing, parallel search, cross-validation, with referenced reports
Comprehensive GitHub CLI (gh) reference. Covers repos, issues, PRs, Actions, releases, gists, search, projects v2, API, secrets/variables, labels, codespaces, extensions, auth, and advanced GraphQL patterns.
Goal collaboration participant protocol. Automatically triggered when you are @mentioned in Slack channels/threads with messages containing [SG-X], Goal ID, or goal-meta tags. Defines standard processes for task reception, execution reporting, cross-lobster coordination, and task board synchronization.
Avoid long waits that block the session. Any operation requiring wait times exceeding 10 seconds (monitoring PRs, waiting for CI, waiting for approval, waiting for issue generation, etc.) must use subagent or cron for asynchronous processing, immediately returning control to the user. Use when: any scenario requiring polling/waiting/monitoring.
Read and write Slack Canvas content via API. Use when user mentions 'canvas', 'Slack Canvas', asks to read/edit/create a canvas, or shares a canvas link (slack.com/docs/...). NOT for general drawing/diagram tools — this is Slack-specific.
Guide cross-team multi-person solution alignment discussions, transforming loose conversations into structured decision processes. Trigger scenarios: (1) User says "help me organize a discussion/solution alignment" (2) User provides documents + participant list and requests multi-person confirmation (3) User says "create a thread to confirm issues one by one" (4) Cross-team sign-off / technical solution review (5) User says "structured decision" or "decision alignment". Not applicable: 1-on-1 simple Q&A, decisions that don't require multi-person participation, pure information notifications.
Unified task management — sprint planning, task breakdown, board CRUD, proactive scanning, and TODO extraction. Backend-agnostic: works with Notion, Linear, GitHub Projects, or plain markdown. Trigger words: sprint planning, task breakdown, task board, what to do today, extract TODOs, autopilot.
Search group chat memory — semantic search across Slack channel history. Use when you need to find what was discussed, look up decisions/conclusions, find context about a topic not in your MEMORY.md, or answer questions about team conversations.