Loading...
Loading...
Found 1,557 Skills
Orchestrate large-scale TYPO3 code changes across multiple files in parallel. Migrations, bulk TCA modernization, Fluid template refactoring, hook-to-event conversions, namespace renames, and extension-wide upgrades. Decomposes work into independent units, executes them, and verifies with tests. Use when working with batch, migrate, bulk, mass refactor, convert all, upgrade all, rename across, find and replace, parallel, codemod, TYPO3 migration.
Orchestrate the full ToolUniverse self-improvement cycle: discover APIs, create tools, test with researcher personas, fix issues, optimize skills, and push via git. References and dispatches to all other devtu skills. Use when asked to: run the self-improvement loop, do a debug/test round, expand tool coverage, improve tool quality, or evolve ToolUniverse.
Integrate Didit Database Validation API to verify personal data against government databases. Use when the user wants to validate identity against government records, verify national ID numbers, check CPF/CURP/DNI/cedula numbers, perform identity database lookups, validate identity documents against official sources, or implement database verification for Latin American or Spanish identity documents using Didit. Supports 18 countries with 1x1 and 2x2 matching methods.
Detect and analyze heap spray attacks in memory dumps using Volatility3 plugins to identify NOP sled patterns, shellcode landing zones, and suspicious large allocations in process virtual address space.
Manage Cilium network policies: profile selection, access labels, Hubble debugging, platform namespace CNPs, and emergency escape hatch procedures. Use when: (1) Deploying a new application and setting network profile, (2) Debugging blocked traffic with Hubble, (3) Adding shared resource access, (4) Creating platform namespace CNPs, (5) Using the escape hatch for emergencies, (6) Verifying network policy enforcement. Triggers: "network policy", "hubble", "dropped traffic", "cilium", "blocked traffic", "network profile", "access label", "escape hatch", "cnp", "ccnp"
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
Detect compromised O365 and Google Workspace email accounts by analyzing inbox rule creation, suspicious sign-in locations, mail forwarding rules, and unusual API access patterns via Microsoft Graph and audit logs.
Systematic design quality evaluation. Hierarchy, type, color, space, craft, system. Use when evaluating whether a design is ready to ship, running quality audits, or setting quality standards.
Best practices for Docker-based ROS2 development including multi-stage Dockerfiles, docker-compose for multi-container robotic systems, DDS discovery across containers, GPU passthrough for perception, and dev-vs-deploy container patterns. Use this skill when containerizing ROS2 workspaces, setting up docker-compose for robot software stacks, debugging DDS communication between containers, configuring NVIDIA Container Toolkit for GPU workloads, forwarding X11/Wayland for rviz2 and GUI tools, or managing USB device passthrough for cameras and serial devices. Trigger whenever the user mentions Docker with ROS2, docker-compose for robots, Dockerfile for colcon workspaces, container networking for DDS, GPU containers for perception, devcontainer for ROS2, multi-stage builds for ROS2, or deploying ROS2 in containers. Also trigger for CI/CD with Docker-based ROS2 builds, CycloneDDS or FastDDS configuration in containers, shared memory in Docker, or X11 forwarding for rviz2. Covers Humble, Iron, Jazzy, and Rolling distributions across Ubuntu 22.04 and 24.04 base images.
Calculate construction costs using DDC CWICR resource-based methodology. Break down costs into labor, materials, equipment with transparent pricing.
A skill that uses GLM-V native grounding capabilities for coordinate conversion, bounding-box visualization, and more. GLM-V native grounding can locate any target specified by the prompt in an image and output relative coordinates normalized to 0-1000 based on image size. Coordinate formats include 2D bounding box (default), 2D points, and 3D bounding box. GLM-V also supports spatiotemporal localization and tracking of multiple prompt-specified targets in videos, outputting 2D bounding boxes per second.
Designs and orchestrates a realistic interview simulation platform with voice AI, whiteboard evaluation, gaze-tracking proctoring, and mobile spaced repetition. Use for building mock interview infrastructure, configuring sessions, and adaptive difficulty. Activate on "interview simulator", "mock interview", "practice session", "voice mock". NOT for individual round-type coaching, resume writing, or prep timeline coordination.