content-hub

KTG content marketing pipeline. Takes a written blog post and runs the full publishing workflow: repurpose for all platforms, generate hero image, SEO and AI citation optimisation, then pause for green-light before publishing to all channels via Composio. Local-first: uses Ollama for text tasks where quality allows, cloud for image gen and live data. Use when user says "hub", "/hub", "publish this", "run the pipeline", "post this everywhere".

KTG content marketing pipeline — SWARM MODE. Orchestrates 7 plugins via parallel agent dispatch. Drop a post, get it published everywhere with maximum parallelism. Local-first: Ollama for text, cloud for images and live data. Agents run simultaneously, not sequentially.

KTG content marketing pipeline — SWARM MODE v2. Concrete 11-agent parallel pipeline using the Agent tool. Local-first: Ollama for text, cloud for images and publish. Drop a post, spawn agents, publish everywhere.

Browser SDK for connecting to the iii engine from web applications via WebSocket. Use when building browser-based clients that register functions, invoke triggers, or consume streams from the frontend.

Binary streaming between workers via channels. Use when building data pipelines, file transfers, streaming responses, or any pattern requiring binary data transfer between functions.

Registers cron triggers with 7-field expressions to run functions on recurring schedules. Use when scheduling periodic jobs, timed automation, crontab replacements, cleanup routines, report generation, batch processing, or calendar-based work that is genuinely time-driven.

Builds custom trigger types for events iii does not handle natively. Use when integrating webhooks, file watchers, IoT devices, database CDC, or any external event source.

Configures the iii engine via iii-config.yaml — workers, adapters, queue configs, ports, and environment variables. Use when deploying, tuning, or customizing the engine.

Handle iii engine and SDK errors across Node, Python, Rust, and browser workers. Use when interpreting error codes, retryability, RBAC denial, timeouts, handler failures, or SDK-specific exception surfaces.

Registers functions and triggers on the iii engine across TypeScript, Python, and Rust. Use when creating workers, registering function handlers, binding triggers, or invoking functions across languages.

Install the iii engine, set up your first worker, and get a working backend running. Use when a user wants to start a new iii project, install the SDK, or needs help with initial setup and configuration.

Exposes iii functions as REST API endpoints. Use when building HTTP APIs, webhooks, or inbound request handling where iii owns the route.

Registers external HTTP endpoints as iii functions using registerFunction(id, HttpInvocationConfig). Use when adapting legacy APIs, third-party webhooks, or immutable services into triggerable iii functions, especially when prompts ask for endpoint maps like { path, id } iterated into registerFunction calls.

Registers engine-level middleware functions that run before HTTP handlers. Use when adding authentication, request logging, rate limiting, or any pre-handler logic to HTTP endpoints.

Node.js/TypeScript SDK for the iii engine. Use when building workers, registering functions, or invoking triggers in TypeScript or JavaScript.

Integrates OpenTelemetry tracing, metrics, and logging into iii workers. Use when setting up distributed tracing, Prometheus metrics, custom spans, or connecting to observability backends.

Broadcast fire-and-forget events through the iii-pubsub worker. Use when publishing topic events to multiple subscribers without queue persistence, retries, FIFO ordering, or dead-letter handling.

Python SDK for the iii engine. Use when building workers, registering functions, or invoking triggers in Python.

Uses `TriggerAction.Enqueue({ queue })` and named queues for reliable background work. Use when a request should hand off slow work and return quickly, a task must retry on failure, jobs need concurrency limits or FIFO ordering, or a workflow needs durable async processing, backoff, and dead-letter handling.

Builds reactive real-time backends where functions react automatically to state changes and stream events. Use when requirements say "after create/update do this", "keep views/metrics/cache in sync", "notify clients when data changes", "push live updates", or "avoid polling"; combine state triggers, stream updates, pub/sub, and queued work instead of imperative follow-up calls.

Pushes live updates to connected WebSocket clients via streams. Use when building real-time dashboards, live feeds, or collaborative features.

Rust SDK for the iii engine. Use when building high-performance workers, registering functions, or invoking triggers in Rust.

Creates scoped key-value stores, reads and writes state entries, lists keys, and performs partial updates across functions. Use when persisting data between invocations, managing user sessions, caching computed values, storing feature flags, sharing state between workers, or building a KV data layer as an alternative to Redis or DynamoDB.

Registers reactive state triggers that automatically fire functions when key-value state is created, updated, or deleted. Use whenever a requirement says "when X changes, do Y", "after a record is created/updated/deleted", keep derived data in sync, notify users, invalidate caches, write audit logs, or run downstream work from data changes without polling or explicit calls.

Selects how functions are invoked: synchronous result-returning calls, fire-and-forget void dispatches, or durable `TriggerAction.Enqueue({ queue })` background jobs. Use whenever a handler should not block the caller, work should run later or reliably with retries, a request should return quickly, or an agent must choose between inline RPC, optional side effects, and queued async processing.

Registers a boolean condition function and attaches it to triggers via condition_function_id so handlers only fire when the condition passes. Use when gating triggers on business rules, checking user permissions, validating data before processing, filtering high-value orders, rate-limiting events, or conditionally skipping handlers based on payload content.

Canonical built-in iii trigger config and call payload shapes. Use when generating or validating HTTP, cron, queue, pubsub, state, stream, or log trigger registrations and handler input types.

Discover, choose, install, and learn iii workers from the worker registry. Use when the task needs a worker-backed capability such as harness, shell, sandbox, database, storage, MCP, ACP, image processing, or future workers published to workers.iii.dev.

Manage iii workers with the iii worker CLI. Use when adding, removing, starting, stopping, updating, inspecting, logging, executing into, or scaffolding registry, binary, OCI, or local managed workers.

Reproduce registry-managed iii worker installs with iii.lock. Use when working on CI, teams, deployments, worker pinning, sync, frozen installs, verification, or config.yaml and lockfile consistency.

Configure worker RBAC, filtered discovery, FORBIDDEN errors, registration hooks, auth functions, and safe browser/public worker-manager listeners in iii. Use when configuring permissions, tenant isolation, exposed functions, browser-safe worker access, or denied invocation behavior.

Orchestrates durable multi-step workflow pipelines on the iii engine. Use when building order fulfillment, data pipelines, task orchestration, or any sequential process requiring retries, backoff, step tracking, scheduled cleanup, or dead letter queue (DLQ) handling.

Transform files and folders into learning materials using NotebookLM. Actions: transform, convert, generate, create from files. Outputs: audio podcast, video explainer, slide deck, study guide, quiz, flashcards, infographic, mind map, briefing doc, report. Sources: PDF, text files, URLs, folders, subfolders. Features: batch processing, watermark removal, progress tracking, configurable granularity.

Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships

Use before a non-trivial multi-file diff, before a multi-slice agent run, or when auditing a major change in Codex, Claude Code, or any agent harness. Loads the six-cut kernel.

Multi-platform paid advertising audit and optimization. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, Apple, and Amazon Ads. 250+ checks with scoring, parallel agents, industry templates, AI creative generation, attribution and server-side tracking deep dives. 22 sub-skills available.

Full-lifecycle blog engine with 21 commands, 12 content templates, 5-category 100-point scoring, and 4 specialized agents. Optimized for Google rankings (E-E-A-T) and AI citations (GEO/AEO). Writes, rewrites, analyzes, outlines, audits, and repurposes blog content.

Comprehensive SEO analysis for any website or business type. Full site audits, single-page analysis, technical SEO (crawlability, indexability, Core Web Vitals with INP), schema markup, content quality (E-E-A-T), image optimization, sitemap analysis, and GEO for AI Overviews/ChatGPT/Perplexity. Industry detection for SaaS, e-commerce, local, publishers, agencies. Triggers on: SEO, audit, schema, Core Web Vitals, sitemap, E-E-A-T, AI Overviews, GEO, technical SEO, content quality, page speed, structured data.

Conversational AI-first interface with minimal controls, clear outcomes, and delegated task flows for agentic workflows.

Structured, enterprise-focused design system emphasizing clarity, consistency, and efficiency for data-dense web applications.