개발 스킬

Run configured evaluation benchmarks on the detected GPU hardware and update matching reference-table cells with the results. New hardware or workload combinations get new rows, while personal Local-* tables are skipped. The refresh is committed locally.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Refreshing benchmark reference results after running the suite
• Adding results for a new GPU or workload combination
• Rerunning selected benchmarks or failed rows

Set up application registration and authentication with Microsoft Entra ID. Guides API permissions, credentials, and OAuth 2.0 flows, with MSAL authentication library examples for user sign-in and service-to-service access.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Registering an application in Microsoft Entra ID
• Adding user sign-in to a console application
• Configuring API permissions for an application

Commit and push local changes, then create a pull request or update an existing one based on the branch state. The skill prepares commit messages and new pull request details from the changes being submitted.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a pull request from local changes
• Adding changes to an existing pull request
• Choosing staged changes or all changes for a commit

Review local branches, pull requests, commits, or files and address issues. The skill selects a single-agent or multi-agent workflow based on the environment, with automatic fixes for lower-risk issues and confirmation for high-risk changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing changes on a local branch
• Starting a pull request review from its number or URL
• Checking a specific commit or file

Review a branch's commits, combine adjacent changes that belong together, and improve commit messages. A rebuilt history is prepared separately and replaces the original branch only after the user reviews and confirms the proposed changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Combining unpushed commits on the current branch
• Cleaning up a named branch without checking it out
• Improving unclear commit messages

Commit local changes to the current Git branch with a message based on the project's conventions. When staged and unstaged changes coexist, choose which to include. The skill does not push changes or create pull requests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving local work as a commit
• Committing only changes already staged
• Staging and committing all local changes

Use this skill to understand and customize a Hugo theme or site. It directs you to guidance for page creation, content, configuration, components, modules, scripts, architecture, and styling, so you can follow the project’s documented approach.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a page or homepage section
• Managing Markdown content and frontmatter
• Configuring menus, languages, or SEO

Run and debug a local web app using a managed browser, while collecting server and browser events in one shared timeline. Reproduce an issue, inspect relevant logs and network activity, make a fix, and repeat the same interaction to compare evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reproducing a browser bug in a local web app
• Inspecting server and browser events together
• Letting a user test a running local app

Convert Next.js bundle analyzer data into NDJSON, a line-based format that works with tools like jq and grep. Inspect route sizes, large source files, output files, and module dependencies to find areas worth reviewing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare compressed bundle sizes across routes
• Find the largest source files in a project
• Inspect client-side JavaScript sources

Create thin adapters for Codex, Claude Code, Gemini CLI, Cursor, and other listed runtimes from one canonical AGENTS.md core. This helps generated repositories map shared instructions to each tool’s local conventions without duplicating the core.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate adapters for several AI runtimes
• Keep shared agent instructions in one core file
• Document each runtime’s command alias

Plan how a single canonical agent behavior contract can run across tools such as Codex, Claude Code, Gemini CLI, and Cursor. Get a runtime matrix covering entry points, commands, adapters, memory access, limitations, and verification steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning an agent for several runtimes
• Comparing entry points and global commands
• Documenting memory access and capability limits

Checks whether an Agentlas agent repository has the files and validation steps needed for public distribution, including GitHub release, Codex plugin submission, Claude adapters, and one-line installation. It also checks that public packages exclude secrets and private materials.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare an Agentlas repo for public GitHub release
• Check files for Codex plugin submission or Claude distribution
• Review one-line installation and public safety checks

Builds a single Agentlas agent, a coordinated team, or a package for an existing agent. It clarifies the work through an interview, researches relevant tools and examples, then creates instructions and supporting package files in English.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating one agent for a clearly scoped role
• Designing a team that divides work across roles
• Packaging or repairing an existing agent

Prepare a project folder for Agentlas so future agent work can use project memory and sitemap data. It guides safe activation, adds missing state files without replacing existing content, and routes durable memory updates through a review process.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a project folder for Agentlas
• Auditing automatic project activation
• Adding project memory and sitemap files

Build, repair, or package Agentlas agents and teams with Hephaestus. The skill delegates the request to the shared hep-build instructions, which define the workflow for producing or fixing an agent or team package.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating an Agentlas agent or team
• Repairing an existing agent package
• Packaging an agent or team with Hephaestus

Design an agent team around the user’s job and target runtime. Define when separate roles are useful, how work passes between them, and who owns memory, policy, and evaluation; receive a role list and team topology.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a new multi-agent team
• Defining roles and handoff direction
• Assigning memory, policy, and evaluation owners

Prepare an agent package for public distribution by checking required Codex and Claude Code files, install commands, verification scripts, and release safety boundaries. Useful when publishing a plugin or open-source package.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a Codex plugin for registration
• Checking Claude Code installation files
• Reviewing a package before a GitHub release

Adds and audits lifecycle records for Agentlas skills, including a candidate registry, trial evidence, and Curator decisions. It checks promotion gates, approval status, evidence gaps, and rollback readiness before a skill can become first-class.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up lifecycle records for packaged skills
• Audit evidence before promoting a skill
• Check approval gates and rollback readiness

Creates lightweight runtime adapters for a canonical agent core, so one set of instructions can be mapped into Codex, Claude Code, Antigravity, Cursor, and generic AGENTS.md conventions. Each adapter follows its runtime's local conventions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adapting one agent core for several AI runtimes
• Creating runtime-specific command and skill files
• Keeping adapter instructions linked to a canonical AGENTS.md

Use this guide to create or repair `.agentlas/routing-card.json`. It explains what each field should contain, which fields affect agent matching, and how misplaced sentences or descriptions can prevent a card from being found.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a routing card for an agent package
• Checking which fields affect hub matching
• Fixing fields that prevent a card from matching

Plan how a shared agent core can run across tools such as Codex, Claude Code, Antigravity, and Cursor. Define each runtime’s entry point, commands, adapters, memory access, limitations, and verification method in a comparison matrix.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a shared agent setup across runtimes
• Documenting each runtime’s entry point and commands
• Comparing memory access and runtime limitations

Convert or repair an existing agent or team package for Agentlas. It preserves useful behavior, adds routing, memory, evaluation, and runtime contracts, then verifies package structure and public safety before a handoff or release.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Converting an existing agent package to Agentlas
• Repairing a team package for local installation
• Preparing a package for plugin use or open-source release

Compare installed Copilot session event schemas with the Session Log canvas baseline, classify changes, and guide code, fixture, documentation, and baseline updates. It helps keep new session data visible while preserving readability for sessions recorded by earlier versions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check schema changes after updating Copilot
• Investigate unknown events or missing canvas data
• Update rendering and synthetic fixtures for changed events

Resolve which cspell configuration a project command actually loads, then curate project terms and ignored paths. The workflow updates the active config or dictionary, reruns the same spell check, and reports the changes and remaining issues.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding project terms to a spell-check dictionary
• Aligning ignored paths with project ignore files
• Finding likely typos among unknown words