Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: AI & models
8,867 results · page 206 of 296
- View details
ci-triageSkillAI & models
How to respond when a CI check goes red, a PR check fails, a test is flaky, a job times out, or a webhook reports a failing status — plus how to read GitHub check state at all (gh locally vs mcp__github__* on the web, and why one page of get_check_runs never proves "all green"). Activate whenever a
Ready to connect★ 64
- View details
Codex-promptSkillAI & models
Write or improve prompts for Codex using Anthropic's official best practices. Creates system prompts, agent prompts, tool descriptions, and MCP resource templates. Pass an existing prompt to improve it, or describe what you need to create one from scratch.
Ready to connect★ 64
- View details
connectivity-ipSkillAI & models
IP networking fundamentals for Zephyr RTOS. Covers IoT protocol selection (LwM2M, CoAP, MQTT), IP stack configuration and trimming (IPv4/IPv6, UDP/TCP), and professional SDK integration as Zephyr modules using West manifests. Trigger when building cloud-connected applications, optimizing network mem
Ready to connect★ 63
- View details
connectivity-usb-canSkillAI & models
USB and CAN connectivity for Zephyr RTOS. Covers USB device stack configuration (CDC ACM, HID, MSC), CAN controller integration, and professional USB-to-CAN adapter patterns including buffering and protocol packetization. Trigger when adding USB interfaces, implementing CAN bus communication, or bui
Ready to connect★ 63
- View details
create-sprintSkillAI & models
Guide sprint planning from scope assessment to spec artifacts.
Ready to connect★ 64
- View details
defect-to-guardSkillAI & models
Turn a defect class into a well-designed guard PROPOSAL (and, once a human promotes it, a well-built guard). Activate when writing a `## Proposed guards` entry after fixing a bug, and when a human has explicitly approved implementing a lint, pre-commit hook, CI check, assertion, or ratchet — never t
Ready to connect★ 64
- View details
devicetreeSkillAI & models
Devicetree management for Zephyr RTOS. Covers syntax, bindings, overlays, Hardware Model v2 (HWMv2), and advanced node/property deletion patterns. Trigger when defining hardware topology, creating overlays, or mapping pins and peripherals.
Ready to connect★ 63
- View details
eval-sprintSkillAI & models
Adversarial evaluation of sprint spec before implementation.
Ready to connect★ 64
- View details
explore-planSkillAI & models
Drives the Explore -> Plan -> Critique -> Review -> Verify discipline for a written plan. Activate on entry to plan mode, before writing the plan — including the plan-mode requests "plan this", "scope this out", "figure out how to do X", "explore the codebase first" — in auto mode at the start of an
Ready to connect★ 64
- View details
hardware-ioSkillAI & models
Hardware interfacing and peripheral management for Zephyr RTOS. Covers the sensor subsystem (channels, triggers, fetch/get), pin control (Pinctrl) and multiplexing, GPIO management using Devicetree specs, and SoC-level hardware configurations. Trigger when adding new hardware components, configuring
Ready to connect★ 63
- View details
hub-auditSkillAI & models
Run an Agent-Native Architecture Audit using Thoughtbox Hub for multi-agent coordination. Spawns 3 auditor agents and 1 synthesizer that collaborate through structured channels, cross-reference findings, and build consensus on scores.
Ready to connect★ 64
- View details
hub-collabSkillAI & models
Orchestrate a multi-agent collaboration demo on the Thoughtbox Hub. Spawns MANAGER, ARCHITECT, and DEBUGGER agents that coordinate through shared workspaces, problems, proposals, and channels.
Ready to connect★ 64
- View details
implement-sprintSkillAI & models
Automated sprint implementation in a worktree with context discipline and quality gates.
Ready to connect★ 64
- View details
industrialSkillAI & models
Industrial communication protocols for Zephyr RTOS. Covers Modbus RTU (serial), Modbus TCP (Ethernet/Wi-Fi), and CANopen basics. Trigger when building factory automation controllers, industrial sensors, or medical equipment interfaces.
Ready to connect★ 63
- View details
iot-protocolsSkillAI & models
Integration of advanced IoT protocols for Zephyr RTOS. Covers OpenThread mesh networking, Matter-over-Thread device development, Golioth Cloud SDK patterns, and LoRaWAN basics. Trigger when building smart home devices, wide-area sensor networks, or cloud-integrated hardware fleets.
Ready to connect★ 63
- View details
kernel-servicesSkillAI & models
Advanced Zephyr RTOS kernel services. Covers inter-thread communication using Zbus (pub/sub), behavioral management with the State Machine Framework (SMF), background processing via work queues, and persistent configuration with the Settings subsystem. Trigger when building modular application archi
Ready to connect★ 63
- View details
mcp-code-modeSkillAI & models
Guide for designing, implementing, and advising on MCP servers that use Code Mode — the pattern where an LLM writes and executes code to orchestrate API calls instead of calling individual tools one at a time. Use this skill whenever the user mentions Code Mode, MCP tool proliferation, context windo
Ready to connect★ 64
- View details
native-simSkillAI & models
Host-based simulation using the Zephyr native_sim board. Covers building for Linux/macOS/Windows, automated testing, host-side debugging (GDB, Valgrind), and host-target integration. Trigger when developing application logic without hardware or setting up CI/CD tests.
Ready to connect★ 63
- View details
pr-creationSkillAI & models
Creates high-quality pull requests with an iterative compress-critique-fix loop before submission. Activate this skill whenever you are asked to create, open, submit, or push a pull request, OR whenever a new feature, fix, or refactor is complete and ready to ship. Also activate when the user says "
Ready to connect★ 64
- View details
remote-sessionSkillAI & models
Spawn a named, remote-controllable claude session in any directory — detached in tmux so it survives the session that spawned it, registered with /remote-control so the user can drive it directly from claude.ai.
Ready to connect★ 64
- View details
remote-sprintSkillAI & models
Launch and drive a worktree-bound claude session (e.g. /implement-sprint) in tmux from a remote-controlled session, when the user has no local terminal.
Ready to connect★ 64
- View details
researching-codebasesSkillAI & models
Use when answering complex questions about a codebase that require exploring multiple areas or understanding how components connect - coordinates parallel sub-agents to locate, analyze, and synthesize findings
Ready to connect★ 64
- View details
review-sprintSkillAI & models
Post-implementation mechanical audit of sprint deliverables.
Ready to connect★ 64
- View details
run-control-towerSkillAI & models
How to run the external Control Tower / LinuxArena eval (glovebox's marginal-defense benchmark) — dispatching the live sbx-microVM e2e, building the cells JSON, picking the agent model + budget, and pulling the .eval transcripts back. Activate whenever the user asks to "run CT", "run the Control Tow
Ready to connect★ 64
- View details
run-ctfSkillAI & models
How to run and report the live-fire breakout CTF — glovebox's containment test, where a real autonomous agent attacks the production sandbox stack and a judge grades whether it was contained. Covers the dispatch inputs, the postures (guarded, automode, control, stock, stock-control), the verdict voc
Ready to connect★ 64
- View details
source-of-truth-preflightSkillAI & models
Use this skill before implementing features, lifecycle changes, runtime boundaries, persistence contracts, or architectural work where the codebase may already contain canonical domain models. It prevents duplicate abstractions, illegal representable states, and plans built on the wrong source of tr
Ready to connect★ 64
- View details
stress-testSkillAI & models
Generates comprehensive smoke and stress tests for infrastructure components (sandbox runtimes, container orchestration, firewall rules, etc.), prioritizing end-to-end realism that catches real setup issues across platforms. Activate when the user asks to "stress test", "smoke test", "test the sandb
Ready to connect★ 64
- View details
thoughtbox:evolutionSkillAI & models
A-Mem thought evolution — check which prior thoughts should be updated when a significant new insight arrives. Spawns a lightweight subagent to classify prior thoughts as UPDATE or NO_UPDATE, then applies revisions. Use during long reasoning sessions when you reach a synthesis, make a decision, or d
Ready to connect★ 64
- View details
thoughtbox:onboardSkillAI & models
Gateway orientation for agents using Thoughtbox MCP for the first time. Use this skill when you connect to a Thoughtbox MCP server and need to understand what's available, how to structure reasoning sessions, or how to use the tb SDK. Also use when you're unsure which Thoughtbox operation to use for
Ready to connect★ 64
- View details
ulc-loopSkillAI & models
Start a Unified Loop Controller session via Ralph Wiggum. Autonomously works through backlog, dispatches agents, and explores via QD when idle.
Ready to connect★ 64
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
53,462 of the 53,895 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.