UNPKG

aiwg

Version:

Deployment tool and support utility for AI context. Copies agents, skills, commands, rules, and behaviors into the paths each AI platform reads (Claude Code, Codex, Copilot, Cursor, Warp, OpenClaw, and 6 more) so one source of truth works across 10 platfo

58 lines (57 loc) 1.29 kB
{ "id": "verbalized-sampling", "type": "addon", "name": "Verbalized Sampling", "version": "1.0.0", "description": "Training-free prompting technique that improves output diversity by 1.6-2.1x through verbalized probability distributions, addressing RLHF mode collapse", "core": false, "autoInstall": false, "author": "AIWG Contributors", "license": "MIT", "repository": "https://github.com/jmagly/aiwg", "keywords": [ "diversity", "verbalized-sampling", "mode-collapse", "creative", "ideation", "brainstorming", "synthetic-data", "prompting" ], "researchFoundation": { "arXiv:2510.01171v3": "Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity (2025)" }, "entry": { "agents": "agents/", "prompts": "prompts/", "skills": "skills/", "rules": "rules/" }, "agents": [ "content-diversifier" ], "prompts": [ "vs-standard", "vs-cot", "vs-multi" ], "skills": [ "diversity-tuning" ], "rules": [ "diversity-awareness" ], "dependencies": { "required": [], "optional": ["voice-framework"] }, "configuration": { "defaults": { "k": 5, "diversityThreshold": 0.1, "outputFormat": "json", "autoApply": false } } }