3.1万 件 ・ 関連度順
概要と使いどころ
Interacts with live Hunk diff review sessions via CLI. Inspects review focus, navigates files, hunks, and exact lines, reloads session contents, adds inline review comments, and paints attention marks on character ranges. Use when the user has a Hunk session running or wants to review diffs interactively.
日本語の概要は準備中です。原文の説明を表示しています。
archive ステップ完了後に Next Steps を評価し優先度付きのチェンジ登録提案を生成するサブエージェント
Guide for defining RL environments — the Env protocol, EnvGroupBuilder, RLDataset, and custom environment creation. Use when the user asks about RL environments, reward functions, or how to define custom tasks for RL training.
日本語の概要は準備中です。原文の説明を表示しています。
Guide for hyperparameter selection — learning rate formulas, LoRA rank, batch size, group size, schedules, and model-specific tuning. Use when the user asks about learning rate, batch size, hyperparameter tuning, or how to configure training parameters.
日本語の概要は準備中です。原文の説明を表示しています。
Reference for Tinker SDK types — Datum, ModelInput, TensorData, SamplingParams, response types, error types, and helper functions. Use when the user needs to build training data, construct model inputs, understand response objects, or handle errors.
日本語の概要は準備中です。原文の説明を表示しています。
Guide for testing conventions and CI pipelines — unit tests, integration smoke tests, pytest markers, and GitHub Actions workflows. Use when the user asks about testing, CI, running tests, or adding tests for a recipe.
日本語の概要は準備中です。原文の説明を表示しています。
Guide for dataset construction — SupervisedDatasetBuilder, RLDatasetBuilder, ChatDatasetBuilder, and custom dataset creation from JSONL, HuggingFace, or conversation data. Use when the user asks about datasets, data loading, data preparation, or custom data formats.
日本語の概要は準備中です。原文の説明を表示しています。
Guide for choosing models in Tinker — available model families, model types (base, instruction, reasoning, hybrid, vision), architecture (dense vs MoE), and how to match renderers to models. Use when the user asks which model to use, what models are available, or how to pick a model for their task.
日本語の概要は準備中です。原文の説明を表示しています。
Performs comprehensive FiveM resource security, performance, and compatibility audits. Detects backdoors, RATs, SQL injection, event exploitation, NUI vulnerabilities, dupes, crash/DoS vectors, npm and build-chain supply chain attacks, and malware patterns across ESX, QBCore, QBox, ox_lib, and ND_Core frameworks, on both GTA V Legacy and Enhanced builds. Use whenever a FiveM/cfx resource is being reviewed — even if not explicitly asked — including: audit FiveM script, review FiveM security, optimize FiveM resource, check FiveM performance, FiveM code review, review Lua script security, audit ESX resource, audit QBCore resource, audit QBox resource, check for exploits, FiveM vulnerability scan, GTA V Enhanced migration check, resmon optimization, or asking whether a leaked, cracked, nulled or unknown-origin script is safe to run.
日本語の概要は準備中です。原文の説明を表示しています。
Use when: investigating a legacy, inherited, third-party-built, or otherwise newly-unfamiliar codebase before scoping a migration or major refactor. Formalizes a repeatable five-step investigation pass — entry-point census, business-rule classification, side-effect/idempotency cataloging, implicit-contract discovery, semantic-duplication detection — plus a canonical per-project Open Questions document. Requires checkable signals: ticket keywords or prior documentation gaps. Not a mandatory gate; reserved for entry-point-heavy work in code areas with no prior investigation record.
日本語の概要は準備中です。原文の説明を表示しています。
Shared foundation for all human-voice writing skills. Load before any profession-specific skill. Contains: burstiness principle, perplexity principle, soul injection techniques, community-discovered AI patterns with sources, additional core patterns, banned AI vocabulary, and scoring rubric.
日本語の概要は準備中です。原文の説明を表示しています。
Use when: Good morning Team, start-of-day briefing, or morning status request. Architect orchestrates; Builder, Tester, and Router return their sections as subagents.
日本語の概要は準備中です。原文の説明を表示しています。
Use when: a general codebase assessment, pre-migration/pre-rewrite review, feasibility question about converting/migrating/rewriting a codebase (how hard, effort), or explicit security-focused request needs a structured, repeatable security audit pass covering hardcoded secrets, injection-prone constructs, auth/debug backdoors, insecure config defaults, and weak credential storage. Complements (does not replace) the built-in /security-review command. Not a mandatory gate on every ticket.
日本語の概要は準備中です。原文の説明を表示しています。
Activate for any ticket that changes React components, user-facing flows, or UI state. Ensures all five observable UI states are verified before state:ready-for-qa.
日本語の概要は準備中です。原文の説明を表示しています。
Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
日本語の概要は準備中です。原文の説明を表示しています。
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
日本語の概要は準備中です。原文の説明を表示しています。
Use when: analysing a project's architecture, structure, and infrastructure health from the System perspective.
日本語の概要は準備中です。原文の説明を表示しています。
Master orchestrator for the 5-step productivity system. Runs the full audit-architect-analyst-refinery-compounder loop or individual steps. Use when: (1) "run the full loop", "start the system", "architect system", (2) "run step N", "run audit", "run architect", (3) "what step am I on?", "system status", "where am I in the loop?", (4) "continue", "resume", "next step". Manages state, sequencing, and skill chaining across all 5 steps.
日本語の概要は準備中です。原文の説明を表示しています。
Master orchestrator for the 5-step productivity loop. Runs audit, architect, analyst, refinery, and compounder in sequence or individually. Use when you want to run the full loop, start the system, check system status, resume from where you left off, or run a specific step. Manages state, sequencing, and skill chaining. Supports full loop, single step, resume, and status-only modes.
日本語の概要は準備中です。原文の説明を表示しています。
Build, run, and debug iOS apps on Simulator with XcodeBuildMCP. Use when launching an app, inspecting simulator UI or logs, or diagnosing runtime behavior.
日本語の概要は準備中です。原文の説明を表示しています。
Design App Intents, app entities, and App Shortcuts for iOS system surfaces. Use when exposing app actions or content to Shortcuts, Siri, Spotlight, widgets, or controls.
日本語の概要は準備中です。原文の説明を表示しています。
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
日本語の概要は準備中です。原文の説明を表示しています。
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
日本語の概要は準備中です。原文の説明を表示しています。
Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.
日本語の概要は準備中です。原文の説明を表示しています。