MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Ensemble (ensemblework.com): an AI notes app and workspace to plan your day with AI, manage AI context, and work with AI agents like Claude Code, Codex, Cursor and Copilot.
MCPLink only★ 1Few stars
~66% Faster, ~44% Less Tokens, The only AI coding workflow you need, Supports small models
SkillLink onlyFew stars
按卡帕西 LLM Wiki 工作流初始化并维护个人主题知识库的 Agent 技能(适用 Claude Code / Cursor / Codex 等,纯中文):承重事实全程可溯源(Grounding Invariant + 证据.py 机械核查)、Triage 四处置、级联更新与主张版本、脚本化索引对账(0/0/0/0)、待查问题聚合、懒检测增量清单 / Chinese Karpathy LLM-
SkillLink only★ 1Few stars
Multi-model LLM token cost budget ledger and burn rate forecaster enforcing spending limits and early warning alerts
MCPLink only★ 7
Multi-model LLM token cost budget ledger and burn rate forecaster enforcing spending limits and early warning alerts
SkillLink only★ 7
Quiet suggestions that steer agent sessions away from token-wasting habits. Suggests only; never blocks.
SkillLink only★ 1Few stars
Structured rubric evaluator calculating weighted composite Likert scores across quality criteria
SkillLink only★ 7
Turn a repository URL into a fact-verified GitHub Wiki: clone, inventory, run and probe the subject, scaffold QA-clean pages, audit every link and diagram, deliver a pushable commit.
SkillLink onlyFew stars
Structured rubric evaluator calculating weighted composite Likert scores across quality criteria
SkillLink only★ 7
Adaptive multi-tier TPM and RPM rate limiter with smooth leaky bucket queuing and predictive burst wait estimation
MCPLink only★ 7
Adaptive multi-tier TPM and RPM rate limiter with smooth leaky bucket queuing and predictive burst wait estimation
SkillLink only★ 7
麦当劳配餐决策 Skill｜1881 种搭配里算出三档最优解，并告诉你为什么不是另外那些。控卡、忌口、拼单 max-min 公平分配；LLM 不参与算钱，每个数字可追溯。
SkillLink only★ 127
Multi-agent ensemble voting with Borda count, Condorcet analysis, and confidence-weighted majority resolution
SkillLink only★ 7
EvoFlow: 三层进化栈的自进化 LLM Agent 框架 / Self-evolving LLM agent framework (three-layer evolution stack)
MCPLink only★ 2Few stars
Multi-agent ensemble voting with Borda count, Condorcet analysis, and confidence-weighted majority resolution
SkillLink only★ 7
Real-task tests of AI models — source of modeltested.com
MCPLink onlyFew stars
Self-hosted AI-платформа с расширенными возможностями: RAG, агенты, веб-поиск, исследования, коннекторы, любые LLM и гибкие настройки
MCPLink only★ 36
Security auditor for MCP servers. Detects tool poisoning, risky tools and leaked secrets using rule checks and an LLM, with verified evidence for every finding.
MCPLink onlyFew stars
🍟 麦当劳中国官方 MCP 智能助手技能：把 35 个原子工具编排成 4 条业务流 —— 活动推送 · 联名关注 · 最优惠点餐 · 多人群点聚合账单。算价用 calculate-price 真算，下单必二次确认。｜McDonald's China MCP agent skill: campaigns, collab watch, best-value ordering, group bill
SkillLink only★ 395
Token entropy and n-gram perplexity analyzer auditing LLM outputs for degenerate repetition loops and vocabulary collapse
MCPLink only★ 7
Priority-weighted context window token pruner and FIFO eviction engine protecting LLM prompt boundaries
MCPLink only★ 7
Maximal Marginal Relevance (MMR) exemplar selector optimizing semantic relevance and diversity for LLM prompt engineering
MCPLink only★ 7
Adaptive sliding window query debouncing and micro-batch coalescing engine optimizing LLM and tool call throughput
MCPLink only★ 7
Token entropy and n-gram perplexity analyzer auditing LLM outputs for degenerate repetition loops and vocabulary collapse
SkillLink only★ 7
Who stands behind it
