查询中

搜索技能

为您的 Agent 寻找最完美的能力。

结果数
53,183
符合搜索条件的技能
当前页
1681
共 2660 页
关键词
ai
按名称、标签或描述搜索
machine-learning
4

dspy-categorical

DSPy compositional prompt optimization with categorical signatures, module chaining, and automated prompt tuning. Use when building declarative LLM programs with typed signatures, composing multi-step reasoning modules (ChainOfThought, ReAct, ProgramOfThought), optimizing prompts with MIPROv2/BootstrapFewShot, or creating modular AI pipelines that separate program logic from prompt engineering.

manutej
manutej
data-ai
open
machine-learning
4

funsloth-hfjobs

Training manager for Hugging Face Jobs - launch fine-tuning on HF cloud GPUs with optional WandB monitoring

chrisvoncsefalvay
chrisvoncsefalvay
data-ai
open
llm-ai
4

prompt-dsl

Domain-specific language for categorical prompt composition with functor combinators and natural transformation operators. Use when building composable prompt templates, implementing typed prompt algebras, creating reusable prompt patterns with categorical structure, or designing prompt DSLs that preserve composition properties.

manutej
manutej
data-ai
open
llm-ai
4

langchain

Build production-ready LLM applications with chains, agents, memory, tools, and RAG pipelines using the LangChain framework

vamseeachanta
vamseeachanta
data-ai
open
llm-ai
4

prompt-injection-defense

AIシステムへのプロンプトインジェクション攻撃を防ぎ、入力検証とコンテキスト分離の設計指針を提供するスキル。 Anchors: • OWASP LLM Top 10 / 適用: LLMセキュリティ脅威モデリング / 目的: インジェクション攻撃の分類と防御パターン理解 • Simon Willison's Prompt Injection Research / 適用: 実攻撃パターン分析 / 目的: 実世界の攻撃事例から防御戦略を導出 • Defense in Depth principle / 適用: 多層防御設計 / 目的: 単一障害点の排除 Trigger: Use when designing prompt injection defenses, implementing AI security measures, sanitizing user inputs for LLM systems, separating trusted and untrusted contexts, conducting security reviews for LLM applications, mitigating indirect prompt injection risks.

daishiman
daishiman
data-ai
open
productivity-tools
4

skill-creator

スキルを作成・更新・プロンプト改善するためのメタスキル。 3つのモード(create/update/improve-prompt)を提供し、 Script Firstで100%再現可能な実行を実現する。 Anchors: • Continuous Delivery (Jez Humble) / 適用: 自動化パイプライン / 目的: 決定論的実行 • The Lean Startup (Eric Ries) / 適用: Build-Measure-Learn / 目的: 反復改善 • Domain-Driven Design (Eric Evans) / 適用: ユビキタス言語 / 目的: 一貫した語彙 Trigger: 新規スキルの作成、既存スキルの更新、プロンプト改善を行う場合に使用。 スキル作成, スキル更新, プロンプト改善, skill creation, skill update, improve prompt

daishiman
daishiman
tools
open
llm-ai
4

ai-elements

AI Elements component library for AI-native applications. Use when building chatbots, AI workflows, or integrating with Vercel AI SDK's useChat hook.

laguagu
laguagu
data-ai
open
productivity-tools
4

agent-definition

Guide for creating and configuring AI agents in the DEVS platform. Use this when asked to create new agents, modify agent behavior, or work with agent YAML/JSON files.

codename-co
codename-co
tools
open
llm-ai
4

hallucination-prevention

AIのハルシネーション(幻覚・誤情報生成)を防止するスキル。プロンプトレベル、パラメータレベル、検証レベルの3層防御により、信頼性の高いAI出力を実現。 Anchors: • Thinking, Fast and Slow (Daniel Kahneman) / 適用: System 1/2思考分離 / 目的: 直感的推測の抑制と論理的検証の強制 • Design by Contract (Bertrand Meyer) / 適用: 入出力契約設計 / 目的: 事前条件・事後条件・不変条件による出力保証 • The Pragmatic Programmer / 適用: 実践的改善と品質維持 / 目的: 段階的検証とフィードバックループ構築 Trigger: Use when preventing AI hallucinations, ensuring factual accuracy, requiring verifiable outputs, or implementing truth constraints. hallucination prevention, fact-checking, verification, accuracy, factual output, citation required, ground truth, temperature tuning

daishiman
daishiman
data-ai
open
gaming
4

langgraph-orchestration

LangGraph stateful multi-agent graphs with categorical coordination patterns and cyclic workflows. Use when building stateful AI agent systems, implementing multi-agent orchestration with conditional routing, creating cyclic workflows with persistence, or designing graph-based AI pipelines with checkpointing and human-in-the-loop patterns.

manutej
manutej
development
open
security
4

permission-patterns

Rules for evaluating, classifying, and deduplicating AI tool permissions

JacobPEvans
JacobPEvans
testing-security
open
productivity-tools
4

ai-sdk-v6-ui

Build React chat interfaces with Vercel AI SDK v5/v6. Agent integration, tool approval, auto-submit. Use when: implementing AI SDK v5/v6 chat UIs or troubleshooting "useChat failed to parse stream", "useChat no response", or "stale body values" errors.

blockmatic
blockmatic
tools
open
machine-learning
4

funsloth-local

Training manager for local GPU training - validate CUDA, manage GPU selection, monitor progress, handle checkpoints

chrisvoncsefalvay
chrisvoncsefalvay
data-ai
open
database-tools
4

backup-recovery

データベースバックアップ戦略、RPO/RTO設計、復旧ランブック作成、検証運用を体系化するスキル。 多層防御と復旧演習を通じて、復旧準備の抜け漏れを防ぐ。 Anchors: • Database Reliability Engineering / 適用: 信頼性設計 / 目的: 失敗前提の運用整理 • Backup & Recovery (W. Curtis Preston) / 適用: バックアップ戦略 / 目的: 復旧可能性の担保 • Site Reliability Engineering / 適用: RTO/RPO設計 / 目的: 目標と検証の整合 Trigger: Use when designing backup strategies, defining RPO/RTO, drafting recovery runbooks, planning DR drills, or verifying backup readiness. backup strategy, rpo rto, recovery runbook, disaster recovery, backup validation

daishiman
daishiman
databases
open
sql-databases
4

database-migration

Safe database schema changes for Fluxby's custom migration system. Handles OPFS, Tauri, and Node.js SQLite backends with verification and repair capabilities.

houke
houke
databases
open
cms-platforms
4

supabase-local-development

This skill should be used when the user asks to "start supabase locally", "set up local supabase", "run supabase dev", "initialize supabase project", "configure local database", "start local postgres", "use supabase CLI", "generate database types", or needs guidance on local Supabase development, Docker setup, environment configuration, or database migrations.

constellos
constellos
development
open
sql-databases
4

agentuity-cli-cloud-db-get

Show details about a specific database. Requires authentication. Use for Agentuity cloud platform operations

agentuity
agentuity
databases
open
sql-databases
4

database-monitoring

データベース監視の設計・実装・検証を体系化するスキル。 SQLite/Tursoの統計情報、スロークエリ、接続数、ストレージを含めた監視運用を整理する。 Anchors: • Designing Data-Intensive Applications / 適用: 性能とスケーリング設計 / 目的: 監視メトリクスの根拠整理 • Database Reliability Engineering / 適用: SREの監視設計 / 目的: 監視項目の体系化 • Observability / 適用: 監視と診断 / 目的: 可観測性の向上 Trigger: Use when designing database monitoring metrics, alert thresholds, SLI/SLOs, or operational dashboards for SQLite/Turso. database monitoring, sqlite metrics, turso monitoring, slow query, alerting, sli slo

daishiman
daishiman
databases
open
sql-databases
4

indexing-strategies

SQLiteにおけるインデックス設計戦略の専門知識。 B-Treeインデックス、部分インデックス、式インデックス、カバリングインデックスの特性と選択基準を提供。 Turso + Drizzle ORM環境での実装を前提とする。 Anchors: • Designing Data-Intensive Applications (Martin Kleppmann) / 適用: データモデリング・インデックス設計原則 / 目的: 体系的なインデックス戦略の確立 • SQLite Documentation / 適用: B-Tree実装・クエリプランナー挙動 / 目的: SQLite特有の最適化技法の適用 • Drizzle ORM / 適用: index()構文・マイグレーション / 目的: 型安全なスキーマ定義 Trigger: Use when designing database indexes, analyzing query performance, optimizing read operations, evaluating index candidates, or implementing Drizzle ORM index migrations. Keywords: index, indexing, B-Tree, query performance, SQLite, Drizzle, cardinality, selectivity, covering index, partial index, expression index.

daishiman
daishiman
databases
open
上一页
第 1681 页 / 共 2660 页
下一页