Autonomous optimization loop — iterates on prompts, skills, templates, or code overnight. Two evaluation modes: deterministic (eval.py with proxy heuristics) for mechanical checks, or AI judge (LLM rubric scoring) for creative/subjective quality. Uses 4-way agent separation for unbiased evaluation.
Plugin autoresearch from marketplace benai-skills in naveedharri/benai-skills. Commands read from the repo's manifest — 1 month ago.
autoresearchAutonomous goal-directed iteration loop that continuously improves prompts, templates, configs, or code. Two evaluation modes — deterministic (eval.py with proxy heuristics) or AI judge (LLM rubric scoring). Uses four-way separation in both modes. Inspired by Karpathy's autoresearch.
autoresearch-eval-agentEval Agent for AutoResearch. Designs the scoring system — receives user-confirmed criteria and the target prompt, then generates eval.py + test_cases.json (deterministic mode) or rubric.md + test_cases.json (AI judge mode). The main agent never sees the eval artifacts in detail.
autoresearch-judgeJudge Agent for AutoResearch. Scores outputs against a locked rubric for quality assessment. Operates with fresh context every iteration — knows NOTHING about iteration count, prompt changes, or optimization goals. Only follows the rubric.
autoresearch-test-runnerTest Runner Agent for AutoResearch. Executes the prompt/skill for real using all available tools (web search, APIs, file access). Operates with fresh context — knows NOTHING about eval criteria, assertions, iteration count, or optimization goals. This isolation ensures the main agent cannot influenc
Every BenAI skill in one install. All 130 skills across marketing, sales, SEO, ads, design, YouTube, creative, operations, second-brain OS, Baalda OS, Marketing OS, and general productivity. Add this one plugin to get the complete library.
130 skills · 15 agents · 4 MCP servers
Paid ads toolkit (14 skills + 6 audit subagents). Covers Google, Meta, LinkedIn, TikTok, YouTube, and Microsoft Ads. Includes audits, budget allocation (70/20/10), creative + brand context, landing pages, strategic planning, and competitive intel.
14 skills · 6 agents · 2 MCP servers
The BenAI sales OS as skills: lead generation, qualification and research, CRM mining, LinkedIn engagers, email personalization, call prep, one-pagers, pipeline reviews, post-disco proposals, rep grading, win/loss analysis, and sales assets.
14 skills · 4 agents
General-purpose AI productivity toolkit: browser automation, audio transcription, deep research, decision frameworks, fact-checking, file organization, prompt engineering, MCP server building, and more. 17 community skills in one install.
17 skills
Rank higher and grow organic traffic with programmatic SEO, technical audits, and Search Console optimization. Create email sequences that convert, build compelling case studies, and generate professional infographics. Repurpose YouTube content into LinkedIn posts, newsletters, GIFs, and visual diagrams.
13 skills · 3 MCP servers
The Ben AI YouTube pipeline after the edit: Studio wizard to Unlisted, UTM links, Bitly import, chapters and tags, description, then repurposing into LinkedIn, newsletter, Circle post or course, and clips.
14 skills · 2 agents
Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly, seeing its previous work, until completion.
3 commands · hooks
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
Token usage tracking, model cost attribution per agent, budget alerts, and optimization recommendations
24 skills · 1 command · 1 agent · hooks
Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.
44 skills · 1 MCP server
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
CockroachDB plugin for Claude Code — explore schemas, write optimized SQL, debug queries, and manage distributed database clusters directly from your AI coding agent.
34 skills · 3 agents · 3 MCP servers · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.