'dev tool' 검색 결과

Cryptographic security for agentic systems — zero-trust agent networking, signed message envelopes (JWS/JWE), capability-based security (ocaps), Merkle tree audit trails, WASM sandboxing, and formal verification. Covers CLI dev tool security, mTLS between agents, permission boundaries (least privilege for AI agents), and supply chain security for skills/plugins. Activate on: "agent security", "zero trust agents", "secure agent communication", "capability-based security", "ocap", "signed messages between agents", "agent audit trail", "sandbox agent execution", "agent permissions", "mTLS agents", "cryptographic verification", "agent supply chain", "OWASP agentic", "prove agent did X", "tamper-proof agent logs". NOT for: application-level SAST scanning (use security-auditor), network firewall rules (use infrastructure), SOC2/HIPAA compliance (organizational), or prompt injection defense (use prompt-engineer).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design low-friction UX, interaction patterns, and comeback loops for AI coding assistant apps, agent consoles, background coding agents, and Port Daddy swarm/operator surfaces. Use when creating flows like prompt-to-diff, context attach, plan/apply/review, checkpoint rollback, background-agent dashboards, visual proof, or multi-agent invocation. NOT for generic landing pages, static dashboards, or implementation-only changes without product flow.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Recommend, create, preview, and attach Coval trace-based metrics from OpenTelemetry spans. Use when a user has Coval traces and wants custom trace metrics, trace-aware LLM judge metrics with include_traces, latency, token usage, provider failures, tool behavior, vertical-specific workflow signals, or production monitoring based on trace attributes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Improve Coval trace quality after basic ingestion works. Use when traces are sparse, missing useful STT/LLM/TTS/tool spans, missing attributes needed for Coval built-in metrics, or when a customer wants maximum debugging and observability value from agent traces.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill should be used when the user asks to "このファイルを変えたら何が壊れる？", "what depends on this function", "影響範囲を調べて", "show me what imports this module", or wants to understand the blast radius before modifying a shared utility, exported type, or public API. Traces import/require references up to two levels deep and lists affected test files.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill should be used when the user asks to "このエラーを直して", "help me debug this", "fix this stack trace", "なぜこのエラーが出るの", "CI が落ちた", or pastes an error message or stack trace and wants help diagnosing it. Classifies the error type, identifies related files, and proposes up to three root-cause hypotheses with concrete fix plans.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guide the user through starting a new web application project — elicit requirements (MoSCoW scoping), create architecture and requirements documents, break work into tasks, and register them as a GitHub Project kanban board. Use when the user says "新しいWebアプリを作りたい", "Webアプリの立ち上げを手伝って", "start a new web app project", "プロジェクトの要件を整理したい", or "GitHub Projectにタスクを登録したい".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Explain selected code or a specified file/function in plain language, including what it does, why it exists, and potential pitfalls

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill should be used when the user asks to "PR を出す前に確認して", "check if this branch is ready to merge", "run pre-PR checks", "PRを作る前にチェックして", or wants to verify a branch before opening a pull request. Executes verification commands, validates Conventional Commits format, and confirms documentation is updated, then reports whether gh pr create is safe to run.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill should be used when the user asks to "これらのIssueを全部実装して", "implement these issues autonomously", "Issue一覧を自動で片付けて", "これらのタスクを順番に実装してPRにして", or provides a list of GitHub Issue numbers/URLs for autonomous batch implementation. Fetches all specified Issues, resolves dependency order, then iterates through each — creating a worktree, implementing, and opening a PR — without user intervention.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

ユーザーからの修正・指摘を受けた際の学習記録と自己改善ループ。ユーザーから「違う」「そうじゃない」「前にも言ったけど」といった修正を受けた時、同じミスを繰り返していると気づいた時、セッション開始時の教訓確認で使う。修正やフィードバックを受けたら必ずこのスキルを参照する。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill should be used when the user asks to "ドキュメントを更新して", "sync the docs", "update CLAUDE.md after this change", "実装に合わせてドキュメントを直して", or notices that docs have drifted from the codebase. Diffs git history to identify what changed, proposes targeted updates to CLAUDE.md, docs/architecture.md, docs/requirements.md, and README.md, then applies only approved changes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

サブエージェントを活用した並列実行・調査委譲・コンテキスト管理の戦略。複雑な問題への対処、調査・探索タスク、複数の選択肢の比較検討、大規模なリファクタリングなどでこのスキルを参照する。「調べて」「比較して」「並列で」「複数のアプローチを試して」といったリクエストや、メインのコンテキストが肥大化しそうな場面で使う。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill should be used when the user asks to "最小再現環境を作って", "再現環境を構築して", "問題を切り分けたい", "パッケージの不具合か確認したい", "create a minimal reproduction", "isolate the issue", "build a repro environment", "reproduce this bug", "narrow down the cause", "is this a package bug or my code", "このPRの問題を再現して", "this commit broke something", or wants to determine whether a bug is caused by a package, the environment, or application code. Accepts PR URLs, commit hashes, or branch names as input.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill should be used when the user asks to "このIssueを実装して", "implement this issue", "fix this bug", "このタスクをやって", "Issue

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Configure a Node.js project with pnpm, TypeScript, latest versions, and parallel script patterns following modern best practices

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill should be used when the user asks to "既存プロジェクトのタスクを整理して", "技術的負債をIssue化して", "このコードベースを改善するタスクを洗い出して", "GitHub Projectに健全化タスクを登録して", "break down what needs to be fixed in this project", "surface tech debt as issues", or "create a project board for cleanup work". Diagnoses pain points and codebase health of an existing project, then registers improvement tasks as GitHub Issues and a Project Board.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Runs Docker Desktop and its WSL2 layer, checking RAM and disk before container work. Trigger when Docker Desktop or a container won't start, vmmem eats RAM or the Docker disk keeps growing; to set a WSL memory cap in .wslconfig; to list or install WSL distros; to bring a compose stack up or down; to prune images and build cache; to run a command in a container; to log in to a registry; or say dockerrunner (audit, check, up, down, prune, status, refresh). Local LLMs (Docker Model Runner too) are lmstudiorunner's; images comfyrunner's; VMs and sandboxes hypervrunner's; Docker's MCP catalog its MCP Toolkit's; registry tokens keywarden's.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Hands work to a local model served by LM Studio and verifies what comes back. Trigger to offload, delegate or batch work to a local, offline or on-device model; to queue unattended runs that keep only what passes; to ask which installed model fits a job or whether to switch; to size a task before delegating; when a local model returns nothing, repeats itself or drifts on a long list; when LM Studio shares the GPU with an image tool, or to free its hold; or say lmstudiorunner (audit, size, queue, run, status). Reads models from the live LM Studio API. Cloud model picks and prompt text are promptwright's; a schedule's guardrails agentwright's.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Directs pixel art that must read at several zoom scales at once — per-scale palette and silhouette rules, terrain-versus-unit contrast, a one-scene look test, and briefs for an artist or image generator. Trigger when a game renders one world through zoom bands or levels of detail, a pixelated 3D or 2.5D band with billboards included; when a sprite, unit or icon vanishes against terrain zoomed out; for a cross-band look test or pixel-art style guide; or say pixelsmith (test, brief, audit, 3d). Works from a described scene. Drawing is an art tool's job; rendering and LOD code the game's engineering; a brand palette brandscribe's; game audio soundsmith's.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Runs the test-first build loop (spec, plan, thin slices, failing test first, verify, commit) for a Godot 4 game in GDScript or C# first; in a TypeScript, Python or other repo when test-first, slices or a reproduce-first fix is asked for. Trigger to build or add a game feature, mechanic, stat, system or milestone, even when told to test later; to turn a spec or grill record into slices; to fix a game bug from a reproduction, one hypothesis at a time; on "write the test first", "what's the next slice", "is this slice done" or "is this milestone ready to exit"; or say slicesmith (spec, plan, slice, fix, exit). Run proof and gate rulings are godotsmith's; diff review a review tool's; repo maps researchscribe's; art pixelsmith's; audio soundsmith's; interviews grillwright's; fan-out dispatchwright's.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.