iblai
OrganizationDeveloper toolkit for vibe coding AI apps on the ibl.ai platform. Scaffold a production-ready Next.js app with iblai-app-cli and the @iblai/iblai-js SDK: SSO auth, AI chat, profiles, notifications, and analytics wired up out of the box. Pre-built components, Claude Code skills, and a hosted backend at iblai.app. Deploy in minutes.
Categories
Indexed Skills (125)
iblai-api-agent-access
Manage role-based access to an ibl.ai agent via the platform API — list role policies, search users/groups, and grant/revoke editor, chat, or analytics_viewer roles for users, groups, and emails. Use when controlling who can edit, chat with, or view analytics for an agent.
iblai-api-agent-chat
Set up live chat with a deployed ibl.ai agent by wiring the hosted iblai-api-agent-chat MCP server into the project (.mcp.json / claude mcp add) using the .env Api-Token and a chosen agent's unique id. Use to enable runtime conversations with an agent. The actual chatting then happens through the MCP server's tools.
iblai-api-agent-create
Create a new ibl.ai agent from a template via the platform API — set name, display name, description, system prompt, and LLM provider; returns the new agent's unique id. Use when creating an agent from scratch, then configure it with the other /iblai-api-agent-* skills.
iblai-api-agent-dataset
Manage an ibl.ai agent's training datasets (RAG) via the platform API — list training docs, add resources (file, URL, YouTube, Blackboard, website crawl, GitHub), train/untrain, set visibility and retrain schedule, and delete. Use when feeding an agent knowledge.
iblai-api-agent-disclaimer
Manage an ibl.ai agent's disclaimers via the platform API — the Advisory text (saved through the agent settings endpoint) and the User Agreement (create/update/activate). Use when adding legal or advisory notices users must see or accept.
iblai-api-agent-embed
Configure an ibl.ai agent's embed/widget settings via the platform API — anonymous access, custom CSS/JS, mode, voice/attachment toggles, starter prompts, SSO, share links, and redirect tokens. Use when embedding an agent on an external website.
iblai-api-agent-eval
Measure and improve agent quality via the platform API — evaluation datasets, dataset items (JSON, CSV upload, or from chat traces), experiment runs, LLM-as-Judge and human-annotation scoring, score configs, and CSV export. Use to test an agent against a dataset and grade the results.
iblai-api-agent-history
Read an ibl.ai agent's conversation history and summaries via the platform API — list conversations with sentiment/topic/user/date filters, get general summaries and per-conversation memory, and export chat history as an async report. Use when reviewing or exporting how users have chatted with an agent.
iblai-api-agent-mcp
MCP connectors for ibl.ai agents, end to end — register MCP servers (featured cross-organization sharing, enable/disable, OAuth service linkage), manage credential connections with the auth_type × scope matrix (org / agent / per-user), wire servers onto an agent, run the OAuth connected-service lifecycle, handle per-user in-chat OAuth (the oauth_required / oauth_connection_resolved chat events), and debug MCP auth failures (401s, missing OAuth prompts, agents ignoring servers). Use when wiring an agent to external MCP servers and tools, or designing/troubleshooting MCP auth.
iblai-api-agent-memory
Manage an ibl.ai agent's memories via the platform API — list and filter agent memories (by category, user, email, date), curate global (cross-agent) memories, curate shared agent knowledge injected into every user's chat, add/edit/delete memories, manage memory categories, and toggle capture/recall settings. Use when inspecting or curating what an agent remembers.
iblai-api-agent-privacy
Configure an ibl.ai agent's Privacy Router via the platform API — enable PII detection, choose redact/mask/block action, select entity types (PERSON, EMAIL_ADDRESS, US_SSN, …), set the privacy response, and toggle output filtering (saved through the agent settings endpoint). Use when controlling how the agent handles personal data.
iblai-api-agent-prompt
Manage an ibl.ai agent's prompts via the platform API — built-in system/proactive/study/guided prompts and greeting settings (saved through the agent settings endpoint), plus full CRUD on suggested prompts. Use when editing what an agent says and suggests.
iblai-api-agent-safety
Configure an ibl.ai agent's moderation and safety systems via the platform API — enable flags, system prompts and responses (saved through the agent settings endpoint) — and review or delete flagged-prompt moderation logs. Use when setting guardrails or auditing flagged content.
iblai-api-agent-sandbox
Connect/disconnect an ibl.ai agent's sandbox (Claw) instance, manage Claw instances, push config, run health/connectivity checks, and set the agent's model — via the platform API. Use when wiring an agent to a sandboxed workspace.
iblai-api-agent-session
Talk to a deployed ibl.ai agent directly over REST/SSE (or WebSocket) and manage its chat sessions — POST a prompt to the agent chat endpoint, attach arbitrary metadata (surfaced later as client_context), and list/read sessions and per-task history exports. The direct-transport counterpart to iblai-api-agent-chat's MCP wiring; use when you want raw streamed chat + session records rather than an MCP server.
iblai-api-agent-setting
Read and write an ibl.ai agent's core settings via the platform API — name, description, category, profile image, visibility, and feature flags (anonymous, featured, LTI, attachments, voice, memory, multi-query RAG, forkable). Also fork/duplicate and delete an agent. Use when configuring an agent's basic identity and capabilities.
iblai-api-agent-skill
Manage an ibl.ai agent's skills via the platform API — browse the org skill catalog, assign/unassign skills to an agent, and create/edit/delete catalog skills. Requires a connected sandbox. Use when giving an agent reusable skill instructions.
iblai-api-agent-support
Manage an ibl.ai agent's human-support tickets via the platform API — list and filter the tickets users raised with an agent (by agent, requester, status, session), read a ticket's conversation thread, reply as the support team, change ticket status, and close or delete tickets. Use when triaging or responding to support requests escalated from agent chats.
iblai-api-inference
Run inference against an ibl.ai deployment through its OpenAI-compatible API — same request/response shape as OpenAI's /v1/chat/completions, routed to any configured provider/model (e.g. openai/gpt-5). List models, then POST OpenAI-format messages for a single completion or a streamed SSE response, with Api-Token auth. Use to generate completions or tool calls directly, without the agent-chat MCP server or agent wiring.
iblai-api-search
Discover agents and learning content in an ibl.ai organization via the platform API — faceted, paginated search over agents and the catalog (courses, programs, pathways, skills), personalized (RAG) recommendations, global/personalized agent search, and seller-facing sellable-items search; plus admin management of the recommendation prompts. Use to find, browse, or get recommended agents/content (mostly read-only; recommendation-prompt endpoints write).
iblai-vibe-design
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Falls back to the ibl.ai BRAND.md design system when the project has none. Not for backend-only or non-UI tasks.
iblai-vibe-agent-create
Create an ibl.ai agent from inside your app — there is no SDK component for creation, so this is the server route (org authority, admin-verified) that calls the platform's mentor-with-settings endpoint, the browser helper that calls it, and the pick-or-create setup screen vibe-starter uses to choose the app's default agent; then hand off to /iblai-vibe-agent-setting and the agent tabs. Use when the user says create an agent, new agent, let admins create agents, agent from a template, or the app has no agent yet. For editing an existing agent see /iblai-vibe-agent; for chatting see /iblai-vibe-agent-chat.
iblai-api-agent-audit
Read an ibl.ai agent's audit log via the platform API — a who-changed-what trail filterable by action, actor email, and date range. Read-only. Use when investigating configuration changes to an agent.
iblai-api-agent-llm
Set an ibl.ai agent's LLM provider and model via the platform API — list available provider/model cards and write the selection through the agent settings endpoint. Use when changing which model an agent runs on.
iblai-api-agent-tool
Enable or disable an ibl.ai agent's tools via the platform API — list toggleable tools, read currently enabled tool slugs, and write the enabled set (saved through the agent settings endpoint). Use when controlling which tools an agent can use.
iblai-vibe-agent-access
Add the agent Access tab (role-based access control for editor and chat roles) to your Next.js app
iblai-vibe-agent-api
Add the agent API tab (API key management) to your Next.js app
iblai-vibe-agent-audit
Add the agent Audit tab (audit log of who changed what and when, with user/date/action filters) to your Next.js app
iblai-vibe-agent-billing
Add the agent Billing tab (LLM spend limits for the agent and per user, with usage bars, block/alert enforcement, and near-limit alert thresholds) to your Next.js app
iblai-vibe-agent-chat-sidebar
Wrap the Chat surface with the SDK's AppSidebar — projects dropdown, pinned/recent messages, and host-supplied content/footer menu items
iblai-vibe-agent-chat
Add the in-process Chat SDK component (full agent surface — message stream, canvas, file attach, voice, prompts) to a Next.js app
iblai-vibe-agent-dataset
Add the agent Datasets tab (searchable dataset table with upload) to your Next.js app
iblai-vibe-agent-disclaimer
Add the agent Disclaimers tab (user agreement and advisory) to your Next.js app
iblai-vibe-agent-embed
Add the agent Embed tab (embed code, custom styling, shareable links) to your Next.js app
iblai-vibe-agent-evals
Add the agent Evals tab (run the agent against benchmarks, score responses with LLM-as-Judge reviews or manual scores, export CSV) to your Next.js app
iblai-vibe-agent-grader
Add the agent Grader tab (rubric-based grading with a grading toggle, grading setup form, criteria table, and grade results with LMS-synced overrides) to your Next.js app
iblai-vibe-agent-history
Add the agent History tab (conversation history with filters and export) to your Next.js app
iblai-vibe-agent-llm
Add the agent LLM tab (model provider selection) to your Next.js app
iblai-vibe-agent-lti
Add the agent LTI tab (LTI 1.3 launch toggle with agent links, signing keys, tools, and platform endpoints) to your Next.js app
iblai-vibe-agent-mcp
Add the agent MCP tab (Model Context Protocol connector management with featured connectors, custom connectors, OAuth, and add/edit dialogs) to your Next.js app
iblai-vibe-agent-memory
Add the agent Memory tab (enable/disable memory and manage memories) to your Next.js app
iblai-vibe-agent-privacy
Add the agent Privacy tab (PII detection and filtering with redact/mask/block actions, entity-type selection, and AI-response filtering) to your Next.js app
iblai-vibe-agent-prompt
Add the agent Prompts tab (system prompts and suggested prompts) to your Next.js app
iblai-vibe-agent-safety
Add the agent Safety tab (moderation prompts and flagged content) to your Next.js app
iblai-vibe-agent-sandbox
Add the agent Sandbox tab (sandbox type selection — Computing Runtime, Virtual Machine Shell, or Claw — plus OpenClaw instance management and agent prompt configuration) to your Next.js app
iblai-vibe-agent-search
Add the agent search/browse page (starred, featured, custom, and default agents) to your Next.js app
iblai-vibe-agent-setting
Add the agent Settings tab (name, description, visibility, copy, delete) to your Next.js app
iblai-vibe-agent-skills
Add the agent Skills tab (reusable Agent Skills catalog with per-agent assignment, private skills, file resources, and the chat `/` skill picker) to your Next.js app
iblai-vibe-agent-support
Add the agent Support tab (human support ticket inbox with availability toggle, filters, ticket detail, status updates, and replies) to your Next.js app
iblai-vibe-agent-task
Add the agent Tasks tab (schedule automated periodic agent tasks with run logs) to your Next.js app
iblai-vibe-agent-tool
Add the agent Tools tab (enable/disable agent tools) to your Next.js app
iblai-agent-support
Add the agent Support tab (human support ticket inbox with availability toggle, filters, ticket detail, status updates, and replies) to your Next.js app
iblai-agent-voice
Add the agent Voice tab (pick the agent's voice and configure voice calls) to your Next.js app
iblai-vibe-account
Add account and organization settings page to your Next.js app
iblai-vibe-auth
Add ibl.ai SSO authentication to a vanilla Next.js app
iblai-vibe-cli-maintenance
Internals of the `iblai` CLI (iblai-app-cli) — how its commands, Jinja2 template system, standalone-binary build, and release/publish flows are structured. Use when maintaining, debugging, rebuilding, or reproducing the iblai CLI itself, or when you need to know how `iblai add` / `iblai startapp` / `iblai builds` work under the hood — it preserves the CLI's construction so the behavior can be reproduced or ported.
iblai-vibe-course-access
Add course-content pages (edX user UI) to your Next.js app
iblai-vibe-credential
RBAC setup that lets an API token list and unmask integration credentials on the ibl.ai platform. Use when the user mentions integration credentials, unmasking sensitive credentials, or credential access for a token; see /iblai-vibe-rbac for the broader RBAC model.
iblai-vibe-iconography
Generate every required app-icon size for Tauri desktop, iOS, Windows MSIX, and macOS builds from a single source image. Use when the user mentions app icons, icon generation, iconography, favicons, replacing the logo, or needs the full icon set for a desktop/mobile build. The ready-made default ibl.ai icon set ships in iblai-vibe-ops-build/assets/icons/.
iblai-vibe-local-llm
Use when adding on-device LLM inference (Ollama backend) to a vibe Next.js + Tauri app. Documents the contract a vibe app must implement so the SDK can route chat through a local model via `localLLMProps` — the Tauri command names, event names, and the React hook shape. Mention before wiring "offline AI", "local model", "on-device LLM", or "Ollama" support into a desktop build.
iblai-vibe-monetization-analytics
Build custom Platform analytics surfaces — revenue dashboards, subscriber lists, paywalls overview, and a self-service subscription cancel helper on top of ibl.ai's item monetization. The in-tab MonetizationTab does NOT render revenue or subscriber data today, so these hooks are the building blocks for custom dashboards, leaderboards, and admin tools. Use when the user mentions analytics, revenue, subscribers, sales volume, sales count, commission, dashboard, paywalls list, cancel subscription, or "monetization metrics". See /iblai-vibe-monetization for the family index, /iblai-vibe-monetization-onboard for Stripe Connect status + commission, /iblai-vibe-monetization-configure for paywall setup, /iblai-vibe-monetization-subscription for the user-side counterpart, /iblai-vibe-auth for token wiring, and /iblai-vibe-rbac for the IsPlatformAdmin gate.
iblai-vibe-monetization-checkout
Build the buyer-facing PaywallModal, access-check gate, Stripe checkout flow, and public/guest buy surface for ibl.ai's item-level monetization. Use when the user mentions paywall, checkout, gate content, access check, 402, hard paywall, locked content, PaywallModal, redirect to Stripe, success_url / cancel_url, guest checkout, anonymous buy, public pricing, or selling a single item to logged-out visitors. See /iblai-vibe-monetization for the family index, /iblai-vibe-monetization-configure for the prerequisite paywall + price setup, /iblai-vibe-monetization-onboard for the Connect-ready Platform requirement, /iblai-vibe-monetization-subscription for the post-purchase My Purchases tab, and /iblai-vibe-auth for token wiring.
iblai-vibe-monetization-configure
Build the admin MonetizationTab inside the Account page — the Platform seller wizard that turns an agent/course/program/pathway/custom item into a paid product, with paywall settings (grandfathering, free tier, trial days) and per-item pricing tiers. Use when the user mentions monetization tab, paywall configuration, item pricing, pricing tiers, wizard, custom items, grandfathering, item search, or "configure a paywall". See /iblai-vibe-monetization for the family index, /iblai-vibe-monetization-onboard for the Stripe Connect prerequisite, /iblai-vibe-monetization-checkout for what buyers see, /iblai-vibe-monetization-subscription for the user purchases pane, /iblai-vibe-monetization-analytics for revenue, /iblai-vibe-account for the host page, /iblai-vibe-rbac for the can_sell_items gate, /iblai-vibe-auth for token wiring.
iblai-vibe-monetization-onboard
Build the Stripe Connect Express onboarding surface for Platform sellers — the status card with Configured / Incomplete / Not Configured badge, the Configure Stripe / Complete Setup / Stripe Dashboard action button, the onboard-refresh round-trip when an onboarding link expires, and the is_ready_for_payments gate every later paywall depends on. Use when the user mentions Stripe Connect, Connect Express, onboarding, status card, is_ready_for_payments, dashboard link, disconnect Stripe, or "the Platform can't accept payments yet". See /iblai-vibe-monetization for the family overview, /iblai-vibe-monetization-configure for what comes next once Connect is ready, /iblai-vibe-monetization-checkout for the buyer flow, /iblai-vibe-account for the page that hosts the MonetizationTab, /iblai-vibe-auth for token wiring, /iblai-vibe-rbac for IsPlatformAdmin.
iblai-vibe-monetization-subscription
Build the user-facing PurchasesTab inside the Profile page — list, detail, and cancel for the current user's subscriptions on a Platform. Use when the user mentions purchases, my subscriptions, subscription list, cancel subscription, stripe portal, grandfathered, legacy subscription, subscription detail, or cancel-at-period-end. See /iblai-vibe-monetization for the family index + auth + RBAC, /iblai-vibe-monetization-checkout for how the user got here (paywall, checkout, callback), /iblai-vibe-monetization-analytics for the admin subscriber view, /iblai-vibe-profile for the Profile shell that hosts this tab, and /iblai-vibe-auth for the token wiring.
iblai-vibe-monetization
Reference and family index for ibl.ai's item-level monetization system — Stripe Connect Express, paywalls, per-item pricing tiers, checkout, subscriptions, and revenue analytics. Distinct from /iblai-vibe-credit (Platform-wide credit balances). Use when the user mentions monetization, paywalls, item sales, Stripe Connect, pricing, subscriptions, or asks where a monetization workflow lives. See /iblai-vibe-monetization-onboard for Connect onboarding, /iblai-vibe-monetization-configure for the admin MonetizationTab + wizard, /iblai-vibe-monetization-checkout for the PaywallModal + access-check + Stripe checkout (incl. guest/public buy), /iblai-vibe-monetization-subscription for the user PurchasesTab + cancel flow, /iblai-vibe-monetization-analytics for revenue and subscribers, /iblai-vibe-credit for Platform-wide credits, /iblai-vibe-auth for token wiring.
iblai-vibe-navbar
Add a responsive navbar with logo, page links, notification bell, and profile dropdown
iblai-vibe-notification
Add notification bell and center page to your Next.js app
iblai-vibe-onboard
Design and build a high-converting questionnaire-style onboarding flow for your app, modelled on proven conversion patterns from top subscription apps.
iblai-vibe-ops-build
Build and run your ibl.ai app on desktop and mobile (iOS, Android, macOS, Surface)
iblai-vibe-agent-voice
Add the agent Voice tab (pick the agent's voice and configure voice calls) to your Next.js app
iblai-vibe-billing
Add the tenant Billing settings surface (Plan & Credits with Stripe upgrade, add-credits, and auto-recharge; the workspace-wide Spend Limit; and the Agent Limits table managing every agent's spend cap in one place) to your Next.js app
iblai-vibe-history
Add the user profile History surface (review and export your own conversations with AI agents — Conversations tab with filters and a two-column transcript preview, and an Exports tab listing generated reports) to your Next.js app
iblai-vibe-memory
Add the tenant Memory settings surface (manage every user's global memories and every agent's memories from one place — Global and Agent tabs with per-user memory toggles and the full per-agent memory manager) to your Next.js app
iblai-vibe-monetization-app-paywall
Put a Stripe "pay to enter" gate on a whole vibe-starter app using the tenant's OWN Stripe key via the DM Stripe proxy paywall endpoints — no Stripe Connect, no commission, no webhooks. Admin setup (probe the tenant's stored Stripe credential — never collect a key in chat — then create app-tagged product + prices), two server routes + lib/paywall.ts, the client PaywallGate, and the /paywall pricing + return pages. Use when the user mentions charging for the whole app, pay to enter, app paywall, subscribe to use the app, gate the app behind payment, or selling access with their own Stripe account. See /iblai-vibe-monetization for the item-level Stripe Connect family index, /iblai-vibe-monetization-checkout for selling individual items in-platform, /iblai-vibe-ops-deploy for shipping the server env, /iblai-vibe-auth for token wiring.
iblai-vibe-analytics
Add analytics dashboard page to your Next.js app
iblai-vibe-component
Add an iblai component or feature to your app
iblai-vibe-credit
Add the ibl.ai credit balance widget.
iblai-vibe-invite
Add user invitation dialogs to your Next.js app
iblai-api-agent-access
Manage role-based access to an ibl.ai agent via the platform API — list role policies, search users/groups, and grant/revoke editor, chat, or analytics_viewer roles for users, groups, and emails. Use when controlling who can edit, chat with, or view analytics for an agent.
iblai-api-agent-chat
Set up live chat with a deployed ibl.ai agent by wiring the hosted iblai-api-agent-chat MCP server into the project (.mcp.json / claude mcp add) using the .env Api-Token and a chosen agent's unique id. Use to enable runtime conversations with an agent. The actual chatting then happens through the MCP server's tools.
iblai-api-agent-create
Create a new ibl.ai agent from a template via the platform API — set name, display name, description, system prompt, and LLM provider; returns the new agent's unique id. Use when creating an agent from scratch, then configure it with the other /iblai-api-agent-* skills.
iblai-api-agent-dataset
Manage an ibl.ai agent's training datasets (RAG) via the platform API — list training docs, add resources (file, URL, YouTube, Blackboard, website crawl, GitHub), train/untrain, set visibility and retrain schedule, and delete. Use when feeding an agent knowledge.
iblai-api-agent-disclaimer
Manage an ibl.ai agent's disclaimers via the platform API — the Advisory text (saved through the agent settings endpoint) and the User Agreement (create/update/activate). Use when adding legal or advisory notices users must see or accept.
iblai-api-agent-embed
Configure an ibl.ai agent's embed/widget settings via the platform API — anonymous access, custom CSS/JS, mode, voice/attachment toggles, starter prompts, SSO, share links, and redirect tokens. Use when embedding an agent on an external website.
iblai-api-agent-eval
Measure and improve agent quality via the platform API — evaluation datasets, dataset items (JSON, CSV upload, or from chat traces), experiment runs, LLM-as-Judge and human-annotation scoring, score configs, and CSV export. Use to test an agent against a dataset and grade the results.
iblai-api-agent-history
Read an ibl.ai agent's conversation history and summaries via the platform API — list conversations with sentiment/topic/user/date filters, get general summaries and per-conversation memory, and export chat history as an async report. Use when reviewing or exporting how users have chatted with an agent.
iblai-api-agent-mcp
MCP connectors for ibl.ai agents, end to end — register MCP servers (featured multi-tenant sharing, enable/disable, OAuth service linkage), manage credential connections with the auth_type × scope matrix (org / agent / per-user), wire servers onto an agent, run the OAuth connected-service lifecycle, handle per-user in-chat OAuth (the oauth_required / oauth_connection_resolved chat events), and debug MCP auth failures (401s, missing OAuth prompts, agents ignoring servers). Use when wiring an agent to external MCP servers and tools, or designing/troubleshooting MCP auth.
iblai-api-agent-memory
Manage an ibl.ai agent's memories via the platform API — list and filter agent (mentor) memories (by category, user, email, date), curate global (cross-agent) memories, add/edit/delete memories, manage memory categories, and toggle capture/recall settings. Use when inspecting or curating what an agent remembers.
iblai-api-agent-privacy
Configure an ibl.ai agent's Privacy Router via the platform API — enable PII detection, choose redact/mask/block action, select entity types (PERSON, EMAIL_ADDRESS, US_SSN, …), set the privacy response, and toggle output filtering (saved through the agent settings endpoint). Use when controlling how the agent handles personal data.
iblai-api-agent-prompt
Manage an ibl.ai agent's prompts via the platform API — built-in system/proactive/study/guided prompts and greeting settings (saved through the agent settings endpoint), plus full CRUD on suggested prompts. Use when editing what an agent says and suggests.
iblai-api-agent-safety
Configure an ibl.ai agent's moderation and safety systems via the platform API — enable flags, system prompts and responses (saved through the agent settings endpoint) — and review or delete flagged-prompt moderation logs. Use when setting guardrails or auditing flagged content.
iblai-api-agent-sandbox
Connect/disconnect an ibl.ai agent's sandbox (Claw) instance, manage Claw instances, push config, run health/connectivity checks, and set the agent's model — via the platform API. Use when wiring an agent to a sandboxed workspace.
iblai-api-agent-session
Talk to a deployed ibl.ai agent directly over REST/SSE (or WebSocket) and manage its chat sessions — POST a prompt to the agent chat endpoint, attach arbitrary metadata (surfaced later as client_context), and list/read sessions and per-task history exports. The direct-transport counterpart to iblai-api-agent-chat's MCP wiring; use when you want raw streamed chat + session records rather than an MCP server.
iblai-api-agent-setting
Read and write an ibl.ai agent's core settings via the platform API — name, description, category, profile image, visibility, and feature flags (anonymous, featured, LTI, attachments, voice, memory, multi-query RAG, forkable). Also fork/duplicate and delete an agent. Use when configuring an agent's basic identity and capabilities.
iblai-api-agent-skill
Manage an ibl.ai agent's skills via the platform API — browse the org skill catalog, assign/unassign skills to an agent, and create/edit/delete catalog skills. Requires a connected sandbox. Use when giving an agent reusable skill instructions.
iblai-api-agent-support
Manage an ibl.ai agent's human-support tickets via the platform API — list and filter the tickets users raised with an agent (by agent, requester, status, session), read a ticket's conversation thread, reply as the support team, change ticket status, and close or delete tickets. Use when triaging or responding to support requests escalated from agent chats.
iblai-api-inference
Run inference against an ibl.ai deployment through its OpenAI-compatible API — same request/response shape as OpenAI's /v1/chat/completions, routed to any configured provider/model (e.g. openai/gpt-5). List models, then POST OpenAI-format messages for a single completion or a streamed SSE response, with Api-Token auth. Use to generate completions or tool calls directly, without the agent-chat MCP server or agent wiring.
iblai-api-search
Discover agents and learning content in an ibl.ai organization via the platform API — faceted, paginated search over agents and the catalog (courses, programs, pathways, skills), personalized (RAG) recommendations, global/personalized agent search, and seller-facing sellable-items search; plus admin management of the recommendation prompts. Use to find, browse, or get recommended agents/content (mostly read-only; recommendation-prompt endpoints write).
iblai-vibe-deslop
Audit and harden existing codebases (especially AI-generated / vibe-coded ones) for production readiness. Use when the user asks to review, audit, clean up, harden, deslop, refactor, or fix quality issues across an existing codebase. Works in two phases — first a thorough multi-pass audit written to a structured file, then systematic fixes applied in safety-tiered order. Language-agnostic. Does NOT change business logic — only hardens, cleans, and robustifies.
Showing top 100 of 125 skills by quality score. Browse the full catalog at /browse.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.