All authors
Claude Skills by tools-only
github.com/tools-only19,166 skills18 installs6,168 views
- 107 Data Integrity Guardian B48e5bcdUse this agent when you need to review database migrations, data models, or any code that manipulates persistent data. This includes checking migration safety, validating data constraints, ensuring transaction boundaries are correct, and verifying that referential integrity and privacy requirements are maintained. <example>Context: The user has just written a database migration that adds a new column and updates existing records. user: \"I've created a migration to add a status column to the ...Votes: 0GitHub stars: 9
- 107 Instructions Example Fc7c9897Demonstrates using instructions (system prompts) to control LLM behaviorVotes: 0GitHub stars: 9
- 1070 Bank Statement For Contoso F01ec495**Overview:** This will mimic a standard bank statement for the primary operating account of the company. **Fraudulent Element:** The statement will show large deposits from "Project X" clients (who don't exist), which correlate with the inflated sales on the Income Statement. However, there will be a notable absence of subsequent cash collections, indicating that while sales were recorded, the money was never actually received. **Key Elements:** - **Account Information:** Account number, ban...Votes: 0GitHub stars: 9
- 1071 Cash Flow Statement For Contoso 69f59edaIn this fictional scenario, Contoso claims a record-setting year in terms of profit. However, when examining actual cash flows, the weakness in collections is obvious. A swelling Accounts Receivable balance — driven by fabricated sales such as the $30M "Project X" contract — absorbs much of the cash that would otherwise be generated by operations. This imbalance between net income and operating cash highlights a key **red flag for revenue recognition fraud**, and serves as an example for audi...Votes: 0GitHub stars: 9
- 1072 Purchase Orders Sales Invoices Ed8c44ed789 Contoso Drive, Silicon Valley, CA 94043 Phone: (555) 123-4567 | Email: [info@contoso.com](https://www.google.com/url?sa=E&q=mailto%3Ainfo@contoso.com) Website: [www.contoso.com](https://www.google.com/url?sa=E&q=http%3A%2F%2Fwww.contoso.com)s Invoices **Overview:** These are the source documents for transactions. **Fraudulent Element (Sales Invoices):** I will create several fictitious sales invoices addressed to "Aurora Systems LLC" and "Zenith Solutions Group" for large amounts related ...Votes: 0GitHub stars: 9
- 1073 Network Security Incident Response Fe1dd1e0This document provides comprehensive procedures for identifying, containing, and resolving network security incidents to protect organizational assets and data.Votes: 0GitHub stars: 9
- 1074 System Backup Recovery Procedures E5745225This document outlines comprehensive procedures for backing up critical systems and data, as well as recovery processes to ensure business continuity and data protection.Votes: 0GitHub stars: 9
- 1075 Hardware Software Support Procedures 24d9d96fThis document provides comprehensive procedures for supporting hardware and software issues, including troubleshooting, maintenance, procurement, and lifecycle management across the organization.Votes: 0GitHub stars: 9
- 108 Deployment Verification Agent C14718e4Use this agent when a PR touches production data, migrations, or any behavior that could silently discard or duplicate records. Produces a concrete pre/post-deploy checklist with SQL verification queries, rollback procedures, and monitoring plans. Essential for risky data changes where you need a Go/No-Go decision. <example>Context: The user has a PR that modifies how emails are classified. user: \"This PR changes the classification logic, can you create a deployment checklist?\" assistant: \...Votes: 0GitHub stars: 9
- 108 Professional D27c4aa1``` Professional Salesforce integration architecture diagram:Votes: 0GitHub stars: 9
- 109 Market 1933d2f1Market-by-market expansion guides for US, UK, DACH, France, and Canada. ---Votes: 0GitHub stars: 9
- 109 System Prompt Design 466505afYou are [Name], [brief identity statement].Votes: 0GitHub stars: 9
- 110 Data Retention 924168b9This policy outlines the requirements and controls/procedures LiteLLM Cloud has implemented to manage the retention and deletion of customer data.Votes: 0GitHub stars: 9
- 110 Document 3befa79bThis document provides a comprehensive breakdown of ISO 13485:2016 requirements for medical device Quality Management Systems (QMS).Votes: 0GitHub stars: 9
- 1100 Advanced 87d29bd8Define task dependencies in `project.json`:Votes: 0GitHub stars: 9
- 111 Files Endpoints 2d280d7eFiles are used to upload documents that can be used with features like Assistants, Fine-tuning, and Batch API. Use this to call the provider's `/files` endpoints directly, in the OpenAI format.Votes: 0GitHub stars: 9
- 111 User 69c071ea- The user has been reading about OpenAPI specifications and exploring tools like Swagger and Postman. - Alex's technology stack includes Django and FastAPI for Python services, Kubernetes for orchestration, Redis for caching, and Apache Kafka for event streaming. - Alex has an interest in system design and scalability patterns and is learning about event-driven architecture and message queues. - For food in San Francisco, check out the Ferry Building Marketplace for gourmet options and local Votes: 0GitHub stars: 9
- 112 Caching 0a1c9f90:::note For OpenAI/Anthropic Prompt Caching, go [here](../completion/prompt_caching.md) ::: Cache LLM Responses. LiteLLM's caching system stores and reuses LLM responses to save costs and reduce latency. When you make the same request twice, the cached response is returned instead of calling the LLM API again. - In Memory Cache - Disk Cache - Redis Cache - Qdrant Semantic Cache - Redis Semantic Cache - S3 Bucket Cache - GCS Bucket CacheVotes: 0GitHub stars: 9
- 112 Caching Aa4e1124:::note For OpenAI/Anthropic Prompt Caching, go [here](../completion/prompt_caching.md) ::: Cache LLM Responses. LiteLLM's caching system stores and reuses LLM responses to save costs and reduce latency. When you make the same request twice, the cached response is returned instead of calling the LLM API again. - In Memory Cache - Disk Cache - Redis Cache - Qdrant Semantic Cache - Redis Semantic Cache - S3 Bucket Cache - GCS Bucket CacheVotes: 0GitHub stars: 9
- 112 Yaml 2b8ae481```yaml apiVersion: litmuschaos.io/v1alpha1 kind: ChaosEngine metadata: name: nginx-chaos namespace: default spec: # Application information appinfo: appns: 'default' applabel: 'app=nginx' appkind: 'deployment'Votes: 0GitHub stars: 9
- 1125 Techniques 1b8b80c5Step-by-step guides for each technique.Votes: 0GitHub stars: 9
- 1127 Master Mental Models F5a5624d> **แก่นความคิดจาก Masters** — ไม่ใช่แค่ copy style แต่เข้าใจ WHY ---Votes: 0GitHub stars: 9
- 1128 Business Model Canvas Dedaa429Created by Alexander Osterwalder and Yves Pigneur, published in "Business Model Generation" (2010).Votes: 0GitHub stars: 9
- 1129 Idea Pipeline 05adb805From raw ideas to actionable plans. Frameworks for refining, validating, and executing creative ideas. ---Votes: 0GitHub stars: 9
- 113 Model Access Groups F5c5a40cGroup multiple models under a single name, then grant keys or teams access to the entire group. Add or remove models from a group without updating individual keys. Use cases: - Separate production and development models - Restrict expensive models to specific teams - Organize models by provider or capability - Control access to model families with wildcards (e.g., `openai/*`) ```mermaid graph LR subgraph AG1["Access Group: 'prod-models'"] M1["gpt-4o"] M2["claude-opus"] end subgraph AG2["Acces...Votes: 0GitHub stars: 9
- 113 Visionary 7b2340d31. **Visionary Leadership** - Define compelling future state - Communicate vision consistently - Inspire action toward vision - Measure progress systematicallyVotes: 0GitHub stars: 9
- 1130 Gestalt D9df8f3fGestalt principles explain how humans perceive visual elements as organized patterns rather than separate parts. Developed by German psychologists in the 1920s (Wertheimer, Koffka, Kohler).Votes: 0GitHub stars: 9
- 1131 Customer 8333b7a1**Use when:** Understanding target customers, product development, marketing ```markdown - **Age:** [Range] - **Gender:** [If relevant] - **Location:** [Geography] - **Income:** [Range] - **Education:** [Level] - **Occupation:** [Job/Role] [2-3 sentences about their life/work situation] - [Primary goal] - [Secondary goal] - [Tertiary goal] - [Frustration 1] - [Frustration 2] - [Frustration 3] - **Information sources:** [Where they learn] - **Decision fVotes: 0GitHub stars: 9
- 1132 Risk Stakeholder 342381a4**Use when:** Prioritizing risks, resource allocation for risk mitigation ``` │ Unlikely │ Possible │ Likely │ Almost Certain │ ───────────┼──────────┼──────────┼────────┼────────────────┤ Catastrophic│ Medium │ High │Critical│ Critical │ ───────────┼──────────┼──────────┼────────┼────────────────┤ Major │ Low │ Medium │ High │ Critical │ ───────────┼──────────┼──────────┼────────┼────────────────┤ Moderate │ Low │ Low │ MediumVotes: 0GitHub stars: 9
- 1133 Common Pitfalls 9be6a90d1. [Overview](#overview) 2. [Critical Gotchas (Must Know!)](#critical-gotchas-must-know) - [1. M Code Column References with Special Characters](#1-m-code-column-references-with-special-characters) - [2. Case Sensitivity](#2-case-sensitivity) - [3. Lazy Filter (Hardcoded Values)](#3-lazy-filter-hardcoded-values) - [4. Wrong Order: Filter Before Fill Down](#4-wrong-order-filter-before-fill-down) - [5. Banker's Rounding](#5-bankers-rounding-not-normal-rounding) - [6. Date Locale Votes: 0GitHub stars: 9
- 1134 40 Principles D16f9835Complete reference with examples for each principle.Votes: 0GitHub stars: 9
- 1139 01 Architecture 37b4a68eOpenViking is a context database designed for AI Agents, unifying all context types (Memory, Resource, Skill) into a directory structure with semantic retrieval and progressive content loading.Votes: 0GitHub stars: 9
- 1139 01 Architecture 7cefa3b3OpenViking is a context database designed for AI Agents, unifying all context types (Memory, Resource, Skill) into a directory structure with semantic retrieval and progressive content loading.Votes: 0GitHub stars: 9
- 1139 01 Architecture Ab1576abOpenViking is a context database designed for AI Agents, unifying all context types (Memory, Resource, Skill) into a directory structure with semantic retrieval and progressive content loading.Votes: 0GitHub stars: 9
- 1139 01 Architecture Cf6896caOpenViking is a context database designed for AI Agents, unifying all context types (Memory, Resource, Skill) into a directory structure with semantic retrieval and progressive content loading.Votes: 0GitHub stars: 9
- 1139 01 Architecture D23ff7eeOpenViking is a context database designed for AI Agents, unifying all context types (Memory, Resource, Skill) into a directory structure with semantic retrieval and progressive content loading.Votes: 0GitHub stars: 9
- 114 Security Encryption Faq 9d958893**Yes**, LiteLLM encrypts data in transit using TLS/SSL.Votes: 0GitHub stars: 9
- 114 Software 5eb6450eSoftware licensing with device activation management.Votes: 0GitHub stars: 9
- 115 Building Acc64050---Votes: 0GitHub stars: 9
- 115 Ui Credentials 5836695eYou can add LLM provider credentials on the UI. Once you add credentials you can reuse them when adding new modelsVotes: 0GitHub stars: 9
- 115 Ui Credentials Efbaa719You can add LLM provider credentials on the UI. Once you add credentials you can reuse them when adding new modelsVotes: 0GitHub stars: 9
- 1154 Basic Sensors 478ae8d4For the basic sensor pattern with cursors, see the main SKILL.md Quick Reference section.Votes: 0GitHub stars: 9
- 116 Hashicorp Vault 543d6fee:::info ✨ **This is an Enterprise Feature** [Enterprise Pricing](https://www.litellm.ai/#pricing) [Contact us here to get a free trial](https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat) ::: | Feature | Support | Description | |---------|----------|-------------| | Reading Secrets | ✅ | Read secrets e.g `OPENAI_API_KEY` | | Writing Secrets | ✅ | Store secrets e.g `Virtual Keys` | | Authentication Methods to Hashicorp Vault | ✅ | AppRole, TLS Certificate, Token | Read secrets from...Votes: 0GitHub stars: 9
- 116 Hashicorp Vault 70047036:::info ✨ **This is an Enterprise Feature** [Enterprise Pricing](https://www.litellm.ai/#pricing) [Contact us here to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions) ::: | Feature | Support | Description | |---------|----------|-------------| | Reading Secrets | ✅ | Read secrets e.g `OPENAI_API_KEY` | | Writing Secrets | ✅ | Store secrets e.g `Virtual Keys` | | Authentication Methods to Hashicorp Vault | ✅ | AppRole, TLS Certificate, Token | Read secrets from [Has...Votes: 0GitHub stars: 9
- 116 Production 5ddec098Production patterns for integrating Large Language Models into applications. ---Votes: 0GitHub stars: 9
- 117 Leveldb 1796ccc9leveldb Log format ================== The log file contents are a sequence of 32KB blocks. The only exception is that the tail of the file may contain a partial block. Each block consists of a sequence of records: block := record* trailer? record := checksum: uint32 // crc32c of type and data[] ; little-endian length: uint16 // little-endian type: uint8 // One of FULL, FIRST, MIDDLE, LAST data: uint8[length] A record never starts within the last six bytes of a block (since...Votes: 0GitHub stars: 9
- 117 Spend Queue Warnings 4281305fThe "Spend update queue is full" warning occurs in high-volume LiteLLM proxy deployments when the internal spend tracking queue reaches capacity. This is a protective mechanism to prevent memory issues during traffic spikes.Votes: 0GitHub stars: 9
- 118 Content 726fd5c8The **content-creator** skill is ready for deployment and includes:Votes: 0GitHub stars: 9
- 1183 Agentbench 2e453108AgentBench benchmark for evaluating LLMs as autonomous agents across diverse environments including OS, databases, and web.Votes: 0GitHub stars: 9
- 1183 Agentbench E0f23d17AgentBench benchmark for evaluating LLMs as autonomous agents across diverse environments including OS, databases, and web.Votes: 0GitHub stars: 9