iblai-tools-tab
Add the agent Tools tab (enable/disable agent tools) to your Next.js app
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-11 00:16
Agents & models
26,072 results
iblai-vibe-house-journeys
The three first-run journeys of an ibl.ai official app, the OS's way — a user whose only organization is the community one gets the app on it, on read-only…
agentic-workflow-advisor
Analyzes IBM watsonx Orchestrate agentic workflow artefacts (JSON or Python @flow) and returns prioritised architecture recommendations grouped by impact. Use…
maintain-loop
Run one cycle of a feedback loop defined with make-loop — collect items, propose an outcome for each, get the user's approvals and corrections, turn…
rails-engine-reviewer
Use when reviewing a Rails engine, mountable engine, engine.rb, host-app integration, install generators, dummy app coverage, namespace boundaries, or engine…
adopt-this-repo
Help a user or agent adopt this repository structure into another project by deciding what to copy, what to adapt, what to skip, and producing a simple…
use-this-repo
Help a user understand this repository, decide which AI structure pieces they need, and adapt the template to their own project.
opencode-agent-generator
Creates OpenCode agents in project folders for opencode serve operations. Use when you need to autonomously create specialized OpenCode agents that will be…
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
eval
Build, run, or update minimal evaluation benchmarks for AI prompts, LLM calls, multi-model comparisons, and core functions. Use when creating new eval scripts,…
chestny-znak-mcp
Connect the Chestny ZNAK API (GIS MT) and SUZ to an AI assistant: marking codes, emission orders and authenticity verification directly from the chat. Installs an MCP server…
consilium-principis
A personal board of directors made of AI personas of real thinkers. The user selects figures (public-domain out of the box: Sun Tzu, Marcus Aurelius, Epictetus,…
diadoc-mcp
Connect the Diadoc API (Kontur) to an AI assistant and work with electronic document management from chat. Installs the diadoc-mcp MCP server with 114 methods: incoming and…
hh-mcp
Connect the hh.ru (HeadHunter) API to an AI assistant and work with vacancies, responses, and resumes directly from the chat. Installs the hh-mcp MCP server with 133 methods…
moysklad-mcp-install
Install the MCP server MoySklad (moysklad-mcp) for a non-technical user in zero-terminal mode: the person says "install MoySklad MCP" — the agent takes…
sbis-mcp
Connect the SBIS (Saby) API to an AI assistant and work with documents, signatures and employees from chat. Installs the sbis-mcp MCP server with 45 JSON-RPC commands:…
yandex-market-mcp
Connect Yandex Market to an AI assistant and work with the partner cabinet directly from chat. Installs the MCP server `yandex-market-mcp-ru`: 165 methods of the official API,…
empirical-prompt-tuning
A method for improving an agent-facing text instruction (a skill, a slash command, a task prompt, a CLAUDE.md section, a code-generation prompt) by having a…
blueprint-generate
End the Q&A phase and generate the plan. Use after the blueprint skill has gathered enough context.
gateway-client-imgly
Build IMG.LY-hosted apps that call the IMG.LY AI Gateway using the end user's IMG.LY/Clerk session — no API key on the client, no token-mint backend. Activate…
agent-kernel-evolve
Universal Self-Evolve & Self-Learning guide for AI agents. Enables any agent (Claude, Antigravity, Cursor, Codex, Gemini, OpenCode) to automatically capture…
agentic-workflow
Pluripotent stem-cell framework and universal agentic toolchain for autonomous workflows. Use when designing, building, orchestrating, validating, or…
claude-in-chrome
Use when automating web browsing, page interactions, or DevTools via Chrome browser