llm-ai
4
pr-transcript
Export the current Pi session transcript to an HTML file for inclusion in a pull request. Use when the user is ready to submit a PR and wants to include an AI session transcript.
llimllib
data-ai
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
llm-ai
4
agent-patterns
Modular orchestration of agent patterns from Anthropic's engineering guide. Intelligently selects and implements prompt chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer, and autonomous agents. Includes pattern combinations and language-specific implementations.
markpitt
data-ai
llm-ai
4
spec-generator
Generates implementation specifications from conversation context optionally enriched with GitHub issue data
fractary
data-ai
llm-ai
4
prompt-executor
Execute prompts from ./prompts/ directory with various AI models. Use when user asks to run a prompt, execute a task, delegate work to an AI model, run prompts in worktrees/tmux, or run prompts with verification loops.
cruzanstx
data-ai
llm-ai
4
session-management
Claude Codeセッションの状態管理、コンテキスト保持、会話履歴の効率的な運用を支援するスキル。 長時間セッションでのコンテキスト消費最適化、セッション再開時の状態復元、 マルチタスク切り替え時の状態保存・復元を提供する。 Anchors: • The Pragmatic Programmer (Hunt & Thomas) / 適用: 状態管理の原則 / 目的: 効率的なセッション運用 • Domain-Driven Design (Evans) / 適用: コンテキスト境界 / 目的: 適切な状態分離 • Clean Architecture (Martin) / 適用: 依存関係管理 / 目的: セッション間の独立性確保 Trigger: Use when managing Claude Code sessions, preserving context across interactions, or optimizing token usage in long conversations. session management, context preservation, token optimization, session state, conversation history
daishiman
data-ai
llm-ai
4
fine-tuning-data-generator
Generates comprehensive synthetic fine-tuning datasets in ChatML format (JSONL) for use with Unsloth, Axolotl, and similar training frameworks. Gathers requirements, creates datasets with diverse examples, validates quality, and provides framework integration guidance.
markpitt
data-ai
llm-ai
4
quality-enriched-prompting
[0,1]-enriched category implementation for gradient-based prompt quality optimization. Use when implementing quality-aware prompt systems, building enriched categorical structures for prompt evaluation, creating continuous optimization over prompt spaces, or applying Bradley's enriched category theory to language model quality scoring.
manutej
data-ai
llm-ai
4
flexus-bot-dev
Develop and test Flexus bots. Use when working with bot files (*_bot.py, *_prompts.py, *_install.py), flexus_client_kit, or kanban/scheduler systems.
smallcloudai
data-ai
llm-ai
4
vector-search-alternatives
SQLiteプロジェクト向けのベクトル検索代替戦略スキル。 SQLite VSS、外部ベクトルDB、RAGパイプラインの実装を提供します。 Anchors: - The Pragmatic Programmer（Andrew Hunt）/ 適用: 実践的ソリューション選定 / 目的: 適材適所の技術選択 - Designing Data-Intensive Applications（Martin Kleppmann）/ 適用: データシステム設計 / 目的: スケーラブルなアーキテクチャ - Building LLM Apps（各種論文）/ 適用: RAGパターン / 目的: 効果的な情報検索 Trigger: Use when implementing vector search, building RAG systems, setting up SQLite VSS, or integrating external vector databases like Pinecone or Weaviate.
daishiman
data-ai
llm-ai
4
prompt-engineering
Comprehensive prompting techniques including chain-of-thought, few-shot, zero-shot, system prompts, persona design, and evaluation patterns
vamseeachanta
data-ai
llm-ai
4
prompt-engineering
Use this skill when writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.
rohunvora
data-ai
llm-ai
4
skill-name
Explain what this skill does and when Claude should use it. Include trigger keywords and use cases.
thomasholknielsen
data-ai
llm-ai
4
few-shot-learning-patterns
Few-Shot Learning（少数例示学習）のパターンとベストプラクティスを提供するスキル。効果的な例示の設計、構造化、配置により、AIの出力品質を大幅に向上させます。 • The Pragmatic Programmer / 適用: 例示パターン設計の品質基準 / 目的: 実践的改善と一貫性維持 • Few-Shot戦略 / 適用: 段階的複雑度設計と最適shot数決定 / 目的: AIの学習効率最大化 Trigger: Use when you need to design effective example patterns for AI learning, standardize output formats, or improve task performance beyond zero-shot capabilities. Keywords: few-shot, examples, prompting, output consistency, pattern learning.
daishiman
data-ai
llm-ai
4
log-searcher
Searches logs by content keywords, patterns, and filters with context extraction
fractary
data-ai
llm-ai
4
error-recovery
Provides structured error handling protocol for all agent operations. Ensures users receive clear error reports, troubleshooting guidance, and actionable next steps. Use when any tool operation fails, encounters an error, or produces unexpected results.
costiash
data-ai
llm-ai
4
check-skill-conflicts
This skill should be used when checking for naming conflicts between local skills (~/.claude/skills) and plugin-provided skills (~/.claude/plugins). Use to identify duplicate or similarly named skills that may cause inconsistent agent behavior.
plinde
data-ai
llm-ai
4
cli-detector
Detect installed AI coding CLIs and local model providers; outputs a cached JSON inventory for routing (/detect-clis).
cruzanstx
data-ai
llm-ai
4
vercel-ai-sdk-v6-engineering-playbook
Use when implementing AI features in TypeScript/Next.js with Vercel AI SDK v6 (generateText/streamText, tools, structured output, streaming route handlers). Enforces v6 APIs and best practices; prevents hallucinated options.
steveoon
data-ai
llm-ai
4
agentuity-cli-cloud-vector-search
Search for vectors using semantic similarity. Requires authentication. Use for Agentuity cloud platform operations
agentuity
data-ai
llm-ai
4
postgres-semantic-search
PostgreSQL-based semantic and hybrid search with pgvector and ParadeDB. Use when implementing vector search, semantic search, hybrid search, or full-text search in PostgreSQL. Covers pgvector setup, indexing (HNSW, IVFFlat), hybrid search (FTS + BM25 + RRF), ParadeDB as Elasticsearch alternative, and re-ranking with Cohere/cross-encoders. Supports vector(1536) and halfvec(3072) types for OpenAI embeddings. Triggers: pgvector, vector search, semantic search, hybrid search, embedding search, PostgreSQL RAG, BM25, RRF, HNSW index, similarity search, ParadeDB, pg_search, reranking, Cohere rerank
laguagu
data-ai
llm-ai
4
detecting-ai-code
Use when auditing code for AI authorship, reviewing acquisitions/contractors, verifying academic integrity, or during code review - provides systematic tiered framework for detecting fully AI-generated AND AI-assisted code patterns with confidence scoring
galihcitta
data-ai
llm-ai
4
prompt-engineering-for-agents
エージェント向けプロンプトエンジニアリングを専門とするスキル。System Prompt設計、Few-Shot Examples、Role Prompting技術により、高品質なエージェント動作を実現します。 Anchors: • The Pragmatic Programmer (Andrew Hunt, David Thomas) / 適用: 手順設計と実践的改善 / 目的: 体系的なプロンプト設計 • Role Prompting patterns / 適用: ペルソナ設計と役割定義 / 目的: エージェント動作の最適化 • Few-Shot Learning / 適用: 効果的な例示選択 / 目的: 文脈構成の改善 • Prompt Engineering Guide (DAIR.AI) / 適用: プロンプト最適化技術 / 目的: 高品質な応答生成 Trigger: Use when designing system prompts for agents, optimizing agent behavior, implementing role prompting, creating few-shot examples, or improving agent prompt quality. Keywords: system prompt, agent prompting, role prompting, few-shot learning, prompt optimization, agent behavior
daishiman
data-ai