Recently added

The first open source email gateway for AI agents — SPF/DKIM verified inbound, HMAC-signed delivery, webhook + WebSocket fan-out, CLI +…

AI-native, open-source backend-as-a-service with a built-in Model Context Protocol server.

Diagnostic-only test suite auditor.

Test automate API endpoint testing including request generation, validation, and comprehensive test coverage for REST and GraphQL APIs.

Backtest crypto and traditional trading strategies against historical data.

Configure this skill configures service meshes like istio and linkerd for microservices.

Local-only OSS contribution command center.

Execute use when you need to work with Ansible automation.

Drive an already-reserved Kobiton device from a natural-language intent.

Generate production-grade engineering design diagrams (architecture, sequence, delta, drift) as self-contained dark-themed HTML files with accessible…

Generate production-ready stored procedures for PostgreSQL, MySQL, and SQL Server with proper error handling, transaction management, and security best practices.

Generate comprehensive test reports with metrics, coverage, and visualizations.

Process use when you need to work with database operations.

Test provision and manage isolated test environments with configuration and data.

Test coordinate parallel test execution across multiple environments and frameworks.

Orchestrate a penetration test by routing user intent to one or more of the 25 narrow skills in this pack.

Create automatically creates new AI assistant code plugins with proper structure, validation, and marketplace integration when user mentions creating a…

Validate automatically validates AI assistant code plugin structure, schemas, and compliance when user mentions validate plugin, check plugin, or plugin…

Run local Appium test scripts against Kobiton devices.

Execute load testing, stress testing, and performance benchmarking.

Execute analyzes existing plugins to extract their capabilities, then adapts and applies those skills to the current task.

Validate load balancer behavior, failover, and traffic distribution.

Detect visual changes in UI components using screenshot comparison.

Track and manage regression test suites across releases.

Validate API contracts using consumer-driven contract testing (Pact, Spring Cloud Contract).

Validate CORS policies for security issues and misconfigurations.

Validate CSRF protection implementations for security gaps.

Use vibe watch to run a managed Harness waiter that returns to the same conversation later.

The local-first Agent OS — your AI partner lives on your own machine.

The implementation-lane standard for delivering a PR across the Avibe repositories (avibe, avibe-backend, avibe-docs, avault, and vault-sandbox) —…

Safely inspect and modify local Avibe configuration, routing, runtime settings, watches, scheduled tasks, Avibe Cloud remote access, and operational state.

Use Orca's Linear CLI through orca linear ... commands to read linked ticket context with orca linear issue --current --full --json,…

Use the public orca CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments,…

Control a mobile (iOS) emulator / simulator stream from inside Orca using the orca CLI.

Control an Android emulator / device from inside Orca using the orca CLI.

Set up, review, debug, or validate Orca per-workspace environment recipes — on-demand, disposable runtimes (cloud sandboxes, VMs, or local)…

Use Orca orchestration for structured multi-agent coordination: threaded messages, blocking ask/reply flows, task dispatch,…

Instar-specific development skill used by the instar-developing agent (Echo, or any agent assigned instar-dev responsibilities).

Iteratively review an instar-development spec with multi-angle internal reviewers (security, scalability, adversarial, integration,…

Verifying Part 1 of the spec — does the server actually auto-demote to send-only when the lifeline owns the poll slot?

Generate flat, minimal educational SVG visuals as HTML

The user asks to generate a Word document (report, letter, contract).

Exploratory QA of web apps: find bugs, evidence, reports

Drug discovery: ChEMBL search, drug-likeness, interactions.

Read-only EVM client: wallets, tokens, gas across 8 chains.

Build, test, and deploy Python MCP servers.

Trigger this skill when the user asks about: - Exercises, workouts, gym routines, muscle groups, workout splits - Food macros, calories,…

Ground answers and documents in cited, verifiable sources.

Plan and run multi-agent video production pipelines

Manual OAuth for remote MCP servers on headless gateways.

OBLITERATUS: abliterate LLM refusals (diff-in-means).

Follow the money via public records and sanctions data.

p5.js sketches: gen art, shaders, interactive, 3D.

Generate a report, invoice, or multi-page document as PDF.

Pixel art w/ era palettes (NES, Game Boy, PICO-8).

Query Polymarket: markets, prices, orderbooks, history.

The user asks to build a slide deck, report presentation, or pitch deck.

TRL: SFT, DPO, GRPO, RLOO reward modeling for LLM RLHF

"Remove my (or my family member's) data from data brokers / people-search sites." - "Opt me out", "delete me from Spokeo/Whitepages/etc.",…

Creating .xlsx reports: multiple sheets, number formats, styling, merged cells, freeze panes, autofilter, conditional formatting, charts,…