A self-evolving Agent OS — every interaction sharpens how it judges, not just what it knows. Four ideas: self-evolution (mistakes become code gates, not logged lessons), brain-first domain brains that grow and decay, cognition that persists between sessions, and proprioception — it senses and drives its own body. Human directs. AI delivers.
Deploy, update, manage, and monitor Hive cloud instances. Use when the user wants to create a new Hive, update an existing Hive to a new version, check Hive status, start/stop instances, reset passwords, or manage AWS accounts for Hive deployment.
Convert AI-written text to more human-like writing through subtle, targeted edits. TRIGGER: "humanize", "sounds robotic", "AI-written", "make it natural", "too AI". DO NOT USE: for full rewrites or creative writing (just write directly).
Generate images using structured prompts with AI image generation APIs and tools. TRIGGER: "generate image", "create image", "make a picture", "image for social", "thumbnail", "banner", "illustration", "visual content". DO NOT USE: for editing existing images (use image editing tools directly) or for chart/data…
Create, list, edit, pause, resume, and delete scheduled jobs in the Swarm Job System. Jobs run in the background via launchd — independently of chat sessions. Supports agent tasks (headless Claude CLI with MCP tools), signal pipeline jobs, and script execution. User jobs live in user-jobs.yaml; system jobs are…
Ingest URLs, articles, or text from any source into structured knowledge cards. Stores source URL + metadata + briefing (NOT full text). On-demand retrieval from source. TRIGGER: "learn this", "save this article", "read and remember", "ingest this". NOT FOR: deep-research, summarize, persist use cases.
Manage the SwarmAI Library — mount external directories (code or docs) so the agent can recall them, and search the library. Mounting indexes in place at mount time (code → symbol graph, docs → text chunked into the shared Knowledge FTS5); mounts are POINTERS, never copied. TRIGGER: "mount ", "mount this folder", "add…
Guide for building high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Covers Python (FastMCP) and TypeScript (MCP SDK). TRIGGER: "build MCP", "create MCP server", "build MCP tool", "new MCP server". NOT FOR: settings use cases.
Score Salesforce opportunities using the MEDDPICC framework (8 dimensions, 100 points). Pulls data from CRM MCP, scores each dimension against evidence, checks stage gates, detects risk signals, and generates prioritized actions with estimated point impact. TRIGGER: "MEDDPICC", "MEDDPICC analysis", "MEDDPICC score"…
Distill unprocessed DailyActivity files into curated MEMORY.md entries. TRIGGER: auto-triggers when >3 unprocessed DailyActivity files detected at session start. DO NOT USE: manually — this runs silently and automatically.
Send messages to 9 notification channels: Feishu, DingTalk, WeCom, Telegram, Email, ntfy, Bark, Slack, and generic webhooks. Config-driven via /.swarm-ai/notify-channels.yaml. Also callable by other skills and jobs.
Manage Outlook inbox: triage, cleanup, send, and organization via aws-outlook-mcp server. TRIGGER: "check email", "email triage", "clean inbox", "email summary". NOT FOR: google-workspace use cases.
PDF manipulation: extract text/tables, create, merge/split, fill forms. TRIGGER: any request involving PDF files, PDF forms, or PDF generation. DO NOT USE: for reading plain text or markdown documents.
TRIGGER: "screenshot", "click on", "UI automation", "automate app", "screen capture", "what's on screen", "peekaboo" DO NOT USE: for terminal commands (use Bash), web scraping (use WebFetch), or non-macOS platforms.
Persist knowledge to the correct destination — routes to DDD docs (PRODUCT/TECH/IMPROVEMENT/PROJECT), MEMORY.md, Knowledge/Library/ (searchable store), or EVOLUTION.md based on content type. Unified routing for both manual saves and auto hooks. TRIGGER: "remember", "save", "persist", "沉淀", "record this", "save to…
Convert text content into podcast scripts and audio using TTS tools. TRIGGER: "create podcast", "generate podcast", "make a podcast", "turn this into a podcast", "audio content", "podcast script". DO NOT USE: for music generation or sound effects (not supported).
Swarm's media value delivery engine. Transforms messages into optimized media packages (poster, video, narrative, shorts, README) via a 9-stage pipeline (EVALUATE->REFLECT). Message-first, format follows audience. Your message, their attention, the right format. TRIGGER: "pollinate", "make content about", "GTM for"…
Presentation creation, editing, and analysis (.pptx files). TRIGGER: any request involving PowerPoint, presentations, slides, or speaker notes. DO NOT USE: for simple text outlines (just use markdown).
Diff-aware structured QA: scope from git changes, run unit tests, visual test UI changes, fix bugs with atomic commits, halt when fixes get risky. TRIGGER: "run QA", "test my changes", "QA this", "check for regressions". NOT FOR: code-review use cases.
Manage SwarmAI ToDos — add, list, edit, complete, and delete items that appear in the left-nav ToDo card/overlay. Each todo is a self-contained work packet: when dragged into a chat tab, the agent has all context to start executing immediately. Also proactively creates todos from detected action items and blockers.…
Generate AI-Ready artifacts for any codebase — transforms repos into DDD-structured context (AGENTS.md + PRODUCT/TECH/IMPROVEMENT/PROJECT.md + code-intel.json) that makes AI agents truly understand the project. Works on any language, any framework. TRIGGER: "make AI-ready", "ai-ready repo", "generate DDD for repo"…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: