CLAUDE CODE MARKETPLACES
SkillsMarketplacesMCPDigestLearnAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Web & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web CrawlingAutomation & Workflows
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Learn
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic
  1. Skills
  2. /
  3. orchestra-research
  4. /
  5. ai-research-skills
  6. /
  7. Guidance

Guidance

Editor's Note

If you've ever fought with an LLM to produce valid JSON only to get malformed output, this is the fix. Guidance is Microsoft Research's framework that uses grammars and regex to constrain generation at the token level, so you get guaranteed valid JSON, XML, or any structured format you define. It backs up one token before generating to avoid awkward spacing issues, supports multi-step workflows with Python control flow, and works with Claude, GPT-4, or local models. The regex constraint approach is clever: it filters invalid tokens during generation rather than hoping the model gets it right. Most useful when you're building agents or data pipelines where parsing failures break everything downstream.

Install

npx skills add https://github.com/orchestra-research/ai-research-skills --skill guidance
Votes
0
Installs249
Categories
AI & Agent BuildingData Science & ML
First SeenJun 3, 2026
View on GitHub

Comments

Login to comment

Related AI & Agent Building Skills

View all →
agentica-prompts

parcadei/continuous-claude-v3

0
398
3.8k
agentica prompts
llm-application-dev-langchain-agent

sickn33/antigravity-awesome-skills

0
306
39.4k
llm application dev langchain agent
agentic-eval

github/awesome-copilot

0
9.4k
34.3k
Iterative evaluation and refinement patterns for improving AI agent outputs through self-critique loops.
ai-prompt-engineering-safety-review

github/awesome-copilot

0
9.4k
34.3k
Comprehensive safety analysis and improvement framework for AI prompts with detailed assessment methodologies.
emblem-ai-prompt-examples

emblemcompany/agent-skills

0
8.7k
10
emblem ai prompt examples
finalize-agent-prompt

github/awesome-copilot

0
8.6k
34.3k
Polish and refine agent prompt files against proven best practices.