Retrieve author-written Agent Skills for an LPM package, including usage patterns, anti-patterns, gotchas, and best practices for code generation. Skills are version-specific and resolve from local package.json.
ISC
699,244 tools. Updated 2026-10-24 17:58
"Using local LLMs for code writing, reviewing, and rule generation" matching MCP tools:
- Browse knowledge-layer entities by type (observation, rule, knowledge) to avoid duplicates before writing or to review a type.MIT
- Generate or modify code files with smart diffs. Provide file path and detailed prompt to create or edit files using context for accurate code generation.MIT
- Create markdown documentation for one code file using Writulos. Provide the source code, optional filename, and context; each call uses one monthly generation.MIT
- Execute supplied local Playwright code or a local test file. This is a code-execution and artifact-writing boundary: qmax-mcp first requires an MCP human-approval elicitation bound to the exact test digest.MITDestructive
- Modify a custom function's code, description, or category, with new code validated by compilation first. Calling rule sets use the updated code from their next generation.Apache 2.0Destructive
Matching MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that gives AI agents direct access to VMware vSphere infrastructure, enabling VM lifecycle management, snapshots, datastore operations, networking, and more via 55 typed tools built on govc.12 npmMIT
- AlicenseAqualityAmaintenanceEnables AI to search and retrieve regulations from Dongguk University's integrated rule management system.10MIT
Matching MCP Connectors
Fetch URLs and return clean Markdown for RAG — nav, ads and boilerplate stripped.
Crawls any website and generates a standards-compliant /llms.txt file and JSON-LD schema bundle.
- Retrieve system environment details including OS, Python version, installed libraries, and execution mode before generating code. Helps tailor code to the current setup and avoid errors.MIT
- Run large language models from Replicate for text generation, Q&A, code writing, summarization, translation, and more. Tune output with customizable model, temperature, system prompt, and generation limits.MIT
- Get guidance on writing effective prompts for Grok Imagine video generation. Learn prompt structure, examples, and tips to improve results.MIT
- Retrieve Kinesis stream and MSK cluster details to check capacity mode, shard count, encryption, and state before writing producer/consumer code or reviewing streaming architecture.MIT
- Retrieve test scenarios for specified components. Use for writing tests or reviewing implementations against the spec. More efficient than full spec retrieval when only tests are needed.MIT
- Retrieve Andrej Karpathy's coding guidelines to avoid over-engineering and unnecessary changes before writing or reviewing code.MIT
- Generate a unified chronological timeline merging oncology documents and conversation entries for reviewing medical history, sharing with doctors, or writing patient journals.MIT
- Index a local repository for semantic code search. Scans files, splits them into functions/classes, and generates embeddings for retrieval.-
- Provide typical callees, familiar imports, and replacement guidance for a file based on repository patterns to inform code writing.MIT
- List all API Gateway routes (REST, HTTP, WebSocket) with methods, paths, and invoking Lambda functions before writing handlers or reviewing integration coverage.MIT
- Run AI model inference on GPU. Supports image generation, video, LLMs, audio transcription, and utilities. Use shortcuts or model IDs. Pay $0.05 USDC per request.MIT
- Retrieve the global default language code used for artifact generation.MIT
- Scan Kotlin/JVM code for security issues using a 216-rule analyzer. Returns rule id, message, location, and severity to fix issues while writing.MIT
- Get best practices and examples for writing effective image generation prompts. Craft detailed prompts to produce better results.MIT
- Find ranked snippets from AudioDN's bundled documentation to ground integration code in canonical answers before writing it.MIT