Tools tagged with "Official"

Use this skill to test an agent's quality after building or fixing it. Runs eval test sets against a published agent via Direct Line API (default, auto), Copilo

Use this skill to fix an agent after eval failures. Classifies root causes (instruction gaps, boundary violations, routing failures, knowledge gaps, scoring iss

Use this skill to start a new MCS agent project. Creates the folder structure in Build-Guides/, copies template files, and detects the intake path (SDR document

Use this skill to autonomously build, evaluate, and fix an MCS agent until it reaches SHIP verdict. Composite of /mcs-build → /mcs-eval → /mcs-fix → re-eval, ma

Use this skill to run the MCS build pipeline verify-fix harness against the canonical kitchen-sink agent. The harness reads back every component from MCS via AP

Use this skill to generate an export from agentspec.json without running a build. Produces a single self-contained HTML file with three tabs: Brief (design stat

Use this skill to research and design an agent before building it. Reads project documents, identifies agents, researches MCS components, scores architecture, w

Use this skill to detect changes across all external dependencies (knowledge cache, upstream repos, Elevate, eval-guide plugin, MCP servers, om-cli binary, MS L

Automate browser interactions, test web pages and work with Playwright tests.

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

Automate browser interactions, test web pages and work with Playwright tests.

A deliberately broken fixture used by example/README.md to show what each rule's error output looks like.

Drive the user's desktop in the background — clicking, typing, scrolling, dragging — without stealing the cursor, keyboard focus, or switching virtual desktops

Inspect Playwright trace files from the command line — list actions, view requests, console, errors, snapshots and screenshots.

Reference fixture for dartskillslint. Demonstrates a SKILL.md that passes every default rule: hyphen-lowercase name matching the parent directory, a properly si

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

[Skill] Add a new component to Azure Linux. Use when importing packages from Fedora, creating comp.toml files, choosing inline vs dedicated definitions, or sett

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

[Skill] aks, aks health, cluster health, node pool, activity logs - Inspect Koji AKS cluster health, node pool status, autoscaling, activity logs, deployment fa

HeartMuLa: Suno-like song generation from lyrics + tags.

[Skill] Build and test Azure Linux components using azldev. Use when building packages, debugging build failures, inspecting mock chroots, preparing sources, or

Iterative Python via live Jupyter kernel (hamelnb).

[Skill] deployment context, aks, azure, koji - Resolve Koji AKS deployment context -- resource group, cluster name, subscription, Log Analytics workspace, and m

Install and select animated petdex mascots for Hermes.

[Skill] Diagnose and fix overlay issues in Azure Linux components. Use when overlays fail to apply, produce unexpected results, or need debugging. Triggers: ove

SAM: zero-shot image segmentation via points, boxes, masks.

[Skill] Examine Koji builds, fetch task info and logs from the Koji Web UI, identify failures, and provide root cause analysis. Use when triaging Koji build fai

vLLM: high-throughput LLM serving, OpenAI API, quantization.

[Skill] kql, queries, log analytics, container logs - KQL query templates for Koji container logs, pod errors, restarts, Kubernetes events, build job activity,

Yuanbao (元宝) groups: @mention users, query info/members.

[Skill] Batch-triage build failures from a JSON results file — diagnose with parallel sub-agents, bucketize by root cause, and produce a consolidated summary. U

[Skill] metrics, azure-monitor, aks - Query Azure Monitor metrics for Koji AKS node CPU, memory, disk usage, and pod readiness.

[Skill] Test and inspect packages in Azure Linux mock chroots. Use when testing built RPMs, inspecting dependencies, debugging runtime issues, or verifying pack

[Skill] Remove components from Azure Linux. Use when deleting packages, cleaning up unused dependencies, or pruning the distro. Triggers: remove component, dele

[Skill] Review an Azure Linux component definition for hygiene and best practices. Use when reviewing comp.toml files, checking overlay quality, validating file

[Skill] Refresh component lock files with azldev comp update. Use when finalizing a component change for PR, bumping an upstream commit pin, or investigating lo