GitHub
my-reviewer
Create specialized agents for Claude Code. Use for agent, sub-agent, subagent, autonomous, task agent, custom agent, agent definition, agent config
Skills IA Contenu et médias
Découvrez les skills Contenu et médias, comparez leurs dépôts et consultez leurs instructions.
Catégories: Contenu et médias
Contenu et médias Effacer les filtres
Explorer
GitHub
oracle-agent-spec-expert
Design framework-agnostic AI agents using Oracle's Open Agent Specification for portable, interoperable agentic systems with JSON/YAML definitions
GitHub
oracle-adk-expert
Build production agentic applications on OCI using Oracle Agent Development Kit with multi-agent orchestration, function tools, and enterprise patterns
GitHub
oracle-ai-architect
Extended reference material for Oracle AI architecture with deep technical implementations
GitHub
meta-prompt-generator
Claude Skill用SKILL.md生成AIエージェント。アーキタイプ駆動設計により、 勝利条件から逆算した高品質プロンプトを生成する。 **Trigger:** 以下のいずれかで起動 - 「〇〇用のスキル/プロンプトを作成」 - 「このプロンプ...
GitHub
greeting
Generate a warm, friendly greeting message for a person. Use when the user asks for a greeting or wants to be welcomed.
GitHub
ai-sdk-5
Vercel AI SDK 5 patterns. Trigger: When building AI chat features - breaking changes from v4.
GitHub
session-retrospective
Analyze a Claude Code session and suggest configuration improvements. Use when reviewing a completed session to identify opportunities for permissions, memory/rules, skills, agents, or hooks improvements. Trigg...
GitHub
load-conversation
Load the full content of a previous Claude Code conversation into current context. Use when user asks to "load conversation " or "show me conversation " or references loading/viewing a past conversation by its...
GitHub
mixseek-prompt-builder
MixSeekのプロンプトビルダー設定ファイル（prompt_builder.toml）を生成します。「プロンプトを設定」「プロンプトビルダーを作成」「ラウンド別プロンプト」といった依頼で使用してください。
GitHub
conversation-search
Search indexed conversation history to find past conversations, locate when topics were discussed, or identify which project conversations occurred in. Use when user asks questions like "when did we discuss X?"...
GitHub
mixseek-model-list
MixSeek-Coreで利用可能なLLMモデルの一覧を表示します。「使えるモデル」「モデル一覧」「どのモデルがある」「モデルを取得」「APIからモデル」といった依頼で使用してください。API経由でプロバイダー別のモデル情報を動的...
GitHub
m1-aisthsis
FEP Octave M1: 知覚モジュール (I-E-F)。状況・文脈を即時認識し、意味を推論する。 Use when: 新規メッセージ受信時、文脈が不明確な時、「これは何？」質問時、セッション開始時。 Use when NOT: 既に状況把握済みで行動決...
GitHub
japanese-to-prompt-converter
日本語の曖昧な要件をClaude 4.5向け最適プロンプトに変換する自動化エージェント。 アーキタイプ駆動設計（Precision + Speed）で、8秒以内に実行可能なプロンプトを生成。
GitHub
calculator
Perform basic arithmetic operations (addition, subtraction, multiplication, division). Use when the user asks to calculate or solve math problems.
GitHub
unit-converter
Convert between different units of measurement for temperature, distance, weight, and volume. Use when the user asks to convert units or measurements.
GitHub
ralph-loop
Use for autonomous WORKER mode execution - selects highest priority FAILING item with ralph_loop.enabled=true, reads PRD context, implements with iteration tracking, records attempts, commits on success or reve...
GitHub
infra-executor-agent
Executes infrastructure tasks including builds, deployments, configs, and cluster operations, following acceptance criteria and committing changes
GitHub
plan-forge-cli
Run plan-forge CLI directly to generate development plans. Use when user asks to run plan-forge, generate a plan via CLI, or needs to use plan-forge commands directly (not via MCP). Covers new plans, resume, fe...
GitHub
agent-ops-recovery
Handle failures and errors during workflow. Use when build breaks, tests fail unexpectedly, or agent gets stuck. Semi-automatic recovery with user confirmation for destructive actions.
GitHub
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
GitHub
agent-ops-baseline
Create .agent/baseline.md and later compare against it. Use when capturing baseline build/lint/test results or investigating newly introduced findings.
GitHub
agnosticv-validator
Validate AgnosticV catalog configurations against best practices and deployment requirements
GitHub
verify
Manifest verification runner. Spawns parallel verifiers for Global Invariants and Acceptance Criteria. Called by /do, not directly by users.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.