Results for “runtime”

Power Platform ソリューションの全体アーキテクチャを設計する。Copilot Studio / Power Automate / Code Apps / Copilot Managed Runtime / Power Pages / AI Builder の使い分け判断、コンポーネント選定、統合パターンを決定する。社内向け画面は利用者のライセンス（Power Apps Premium か、Copilot Credits の従量課金か）と利用頻度をヒアリングし、Code Apps と Copilot Managed Runtime を使い分ける。構成が確定したら、実装着手前に admin スキルで環境チェック（既定環境ではないか・マネージド環境・Code Apps / MCP の有効化・セキュリティ ロール）と DLP 事前チェック（使用コネクタがブロックされていないか・Business / Non-business が混在しないか）を実行して結果をユーザーに提示する。Agent 365 の AI チームメイトを採用する場合はライト実装（PoC）と本格実装（private リポジトリ + CI/CD + Agent Evals）を AskUserQuestion で選ばせ、Git ホスティング（GitHub / Azure DevOps Repos / その他）も確定してから実装へ進む。外部の文章を読むエージェントではプロンプト インジェクション対策を設計段階で工数に含める。

The English summary is being prepared. Showing the original description.

AIエージェントのWebアプリを「AWS CDK（デプロイはCDKD）＋ S3 ＋ CloudFront ＋ AgentCore Runtime」で組むときの全体構成。画面は S3 から静的に配信し、サーバー側の処理が要るときだけ Lambda Web Adapter（または Lambda Web Functions）を足す判断基準。スタックの分け方、BucketDeployment での配置とキャッシュ指定、SPA の振り分け、runtime-config.json で環境値を渡す型、Lambda を足すときの Function URL と CloudFront OAC の権限、フロントから AgentCore を直接呼ぶ配線、ローカル開発、デプロイ前後の検証。新しくエージェントのWebアプリを作るとき、Amplify Hosting 以外の配信基盤を選ぶとき、画面の配信に Lambda が要るか迷ったとき、CloudFront 経由の Function URL が 403 になるときに読む。

The English summary is being prepared. Showing the original description.

Performs runtime mobile security exploration of iOS applications using Objection, a Frida-powered toolkit that enables security testers to interact with app internals without jailbreaking. Use when assessing iOS app security posture, bypassing client-side protections, dumping keychain items, inspecting filesystem storage, and evaluating runtime behavior. Activates for requests involving iOS security testing, Objection runtime analysis, Frida-based iOS assessment, or mobile runtime exploration.

The English summary is being prepared. Showing the original description.

Performs runtime mobile security exploration of iOS applications using Objection, a Frida-powered toolkit that enables security testers to interact with app internals without jailbreaking. Use when assessing iOS app security posture, bypassing client-side protections, dumping keychain items, inspecting filesystem storage, and evaluating runtime behavior. Activates for requests involving iOS security testing, Objection runtime analysis, Frida-based iOS assessment, or mobile runtime exploration.

The English summary is being prepared. Showing the original description.

Plan and verify security controls for AI agents that read untrusted content and use tools. Review permissions, file boundaries, network destinations, and credentials, then test that rejected actions leave no unintended changes.

• Reviewing security boundaries in an agent runtime
• Checking isolation between tenants and workspaces
• Testing credential cleanup and tool output limits

Add interactive features to published Artifact pages using supported runtime capabilities, features granted by the viewer environment. Build saved checklists, shared data views, connector integrations, Claude-powered interactions, and file uploads or downloads with permission-aware behavior.

• Build polls and checklists that save changes
• Create task boards with shared data
• Display connected data on an Artifact page

Build HyperFrames animations from small motion recipes, scene templates, and transitions. The skill guides runtime selection, including GSAP, Lottie, and Three.js, and provides an audit script to examine timing and choreography while following HyperFrames requirements for reproducible rendering.

• Combine motion recipes into a scene
• Build a multi-phase brand reveal from a template
• Design transitions between scenes

Implement or review incompatible changes for Remotion 5 while preserving version 4 compatibility. Use a single compile-time flag to switch runtime behavior and public TypeScript types together, with migration guidance and checks for affected packages.

• Implementing v5 defaults while preserving v4 behavior
• Reviewing changes to public TypeScript types
• Documenting breaking changes and migration steps

Build quantum circuits with Qiskit, test them locally, and prepare them for IBM quantum hardware. The skill covers hardware-specific circuit conversion, sampling, expectation values, and analysis of measurement results, uncertainty, and resource usage.

• Building and simulating quantum circuits locally
• Adapting circuits to IBM quantum hardware
• Comparing sampled results and expectation values

Inspect an agent’s current model, processing limits, workspace, tools, and message routing details. Diagnose unavailable capabilities, adjust permitted runtime settings, or keep temporary session notes, with advance notice before changes that affect the model or limits.

• Diagnose why a capability is unavailable
• Check capacity before a large task
• Adjust allowed model presets or iteration limits

Review open commitments in acc and record success or failure with supporting notes. Distinguish self-assessment from owner validation or observed real-world results, and keep commitments open when they are still waiting on an outcome.

• Reviewing open commitments in acc
• Closing commitments with verified outcomes
• Distinguishing self-assessment from external validation

Guides contributors through adding a new programming language to Airflow, covering SDK structure, runtime coordination, communication rules, executable packaging, tests, and the documentation and configuration changes needed for a pull request.

• Adding support for a new programming language
• Choosing how Airflow launches a language runtime
• Implementing communication and executable bundles

Reconstruct frontend behavior from served JavaScript, build manifests, and source maps, which link built code to source. Trace loaded modules, recover route and API references, and identify the smallest asset sequence that explains observed behavior.

• Reconstructing the structure of served JavaScript
• Recovering route and API references from built assets
• Tracing chunk loading and obscured loader code

Analyze running iOS apps in a CTF sandbox, a controlled challenge environment. Trace methods, inspect secure storage, and examine request signing and certificate checks to identify the state needed to reproduce an accepted request.

• Trace Objective-C or Swift methods
• Inspect Keychain and local app storage
• Examine certificate checks and request signing

Learn how to check Claude Code tool calls against a policy and create digitally signed execution records. This walkthrough covers setup, offline verification, tamper demonstrations, and CI/CD integration before adopting the protect-mcp runtime plugin.

• Evaluate signed audit records before adopting runtime hooks
• Demonstrate offline verification and tamper detection
• Verify agent execution records in CI/CD

Deploy and operate Falco to monitor running containers in Kubernetes or Docker. Choose a driver, validate detection rules, confirm alerts for suspicious activity, and forward those alerts to a central security monitoring system.

• Installing Falco on a Kubernetes cluster
• Choosing a driver for the Linux environment
• Checking alerts for suspicious container activity

Assess iOS and Android app security using OWASP MASTG, a mobile security testing guide. Examine app files, runtime behavior, stored data, authentication, and API traffic, then document vulnerabilities, their impact, and suggested fixes.

• Assess mobile app security before release
• Check sensitive data storage and network traffic
• Test authentication and resistance to runtime manipulation

Test iOS apps while they run using Objection and Frida, tools for inspecting and changing runtime behavior. Examine stored credentials, files, memory, and authentication calls, and evaluate client-side protections during authorized security assessments.

• Check stored iOS app data for sensitive information
• Inspect HTTPS traffic during authorized testing
• Observe authentication behavior without source code

Fix defects in Composio SDK through focused reproduction, root-cause analysis, regression tests that check for recurrence, and targeted verification. Use it for reported bugs, failing tests, CI regressions, runtime errors, or incorrect SDK behavior.

• Reproducing and fixing reported SDK bugs
• Investigating failing tests
• Fixing regressions in automated CI checks

Plan and, after explicit approval, run controlled checks of software behavior. Compare baseline and failure cases, repeat sensitive measurements, and report observed results with execution context, comparison conditions, and the status of temporary evidence files.

• Investigating a suspected runtime regression
• Checking retries, interruptions, and concurrent operations
• Comparing latency or cost under matched conditions

Investigate difficult bugs by adding temporary logs to the actual execution path and reproducing the reported behavior. Analyze JSONL logs, which store one structured event per line, then fix the cause, verify regression tests, and remove debugging artifacts.

• Investigating bugs that occur only during manual use
• Tracing event order in streaming or concurrent operations
• Checking whether passing tests cover the reported bug

Build a Table v9 plugin when built-in settings and typed metadata are insufficient. Guides custom state, options, and methods, with initialization hooks and runtime checks to ensure declared APIs actually exist and reset correctly.

• Add reusable custom table behavior
• Design plugin state and reset behavior
• Keep declared APIs consistent with runtime behavior

Investigate cmux interface and runtime problems using debug logs, profiling, and the Debug menu. It guides changes to terminal rendering and tab lists, with checks for typing latency, SwiftUI state handling, and differences between macOS versions.

• Investigating focus and tab switching problems
• Checking typing latency after rendering changes
• Tuning layout and colors through Debug windows

Prepare a local NemoClaw development environment, repair setup problems, or check readiness. It also handles explicitly requested command-line access, runtime onboarding, and launching the coding agent pinned by the project.

• Setting up a local NemoClaw development environment
• Checking readiness before starting development
• Repairing local dependency, build, or hook problems