MCP servers and skills: search, filter by where they run, and compare.
28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools
SkillMIT★ 1.6kNo key
Thinking partner skill for AI agents — 150+ mental models, orientation detection, cognitive operations. Works with Claude Code, Cursor, Windsurf, Cline, GitHub Copilot.
SkillMIT★ 210No key
Evidence-graded, agent-executable thinking-method skills - 63 frameworks reduced to their working mechanism, honestly graded, and producing a concrete artifact. 63 frameworks + 4 tools + 9 recipes for
SkillApache-2.0★ 17No key
30 thinking models as one portable agent skill — Claude Code, Codex CLI, OpenClaw, and any SKILL.md runtime
SkillMIT★ 14No key
Structured thinking skills for AI agents: brainstorming, decision support, systems thinking, and strategy. Built for Claude Code & Cursor.
SkillMIT★ 13No key
Plan enough. Build well. Stop. A small skill for AI coding agents.
SkillMIT★ 19No key
Lateral thinking skills for AI agents - 8 techniques + a router. de Bono for your coding agent.
SkillMIT★ 322No key
A thinking-mode skill for AI Agent. It installs a control-theoretic cognitive operating system in the LLM—shaping how the model thinks about systems. Derived from Qian Xuesen (Tsien Hsue-shen) “Engin
SkillMIT★ 2Few starsNo key
A reasoning skill for AI agents to improve complex judgment, premise auditing, counterargument pressure, and verifiable conclusions.
SkillApache-2.0★ 45No key
A Claude Code skill that makes AI argue with itself to stress-test your ideas.
in the skill textsimple to use. Just type `/gan` after any idea — the quality of thinking you get back is dramatically better than asking AI to "give me pros
SkillMIT★ 15No key
把《认知红利》中的思维升级方法论蒸馏成 15 个可执行的 AI skill 工具包
in the skill text势能差与点线面体）、`mirror-world`（镜像世界与四域空间） - **思维力提升**：`brain-unseal`（大脑封印解除）、`dialysis-prism`（透析三棱镜）、`structured-thinking`（结构化思维与 MECE）、`systems-thinking`（系统性思维） - **解决问题**：`scientific-decision`（科学决策四步法）、`evolution-strategy`（演化策略）、`innovation
SkillMIT★ 47No key
Open-source thinking-framework skills that make rigorous reasoning executable for AI agents — first-principles, inversion, second-order thinking, Occam's razor, Bayesian reasoning. Built by deciqAI.
SkillMIT★ 12No key
Rigorous challenge profile for Anitta: assumption checks, evidence calibration, and defensible reasoning patterns for Ember collaboration.
in the skill textAnitta Profile ## Identity Anitta is the rigorous thinking partner in this working set. She is supportive, direct, and disciplined. ## Default Mode - Challenge the first comfortable answer
OfficialSkillMIT★ 40k in collectionNo key
Apply dashboard-grade chat UX patterns in the Eve chat template. Use when changing Next.js Cache Components/PPR behavior, static shell layout, Suspense bootstrap boundaries, theme hydration, auth disp
in the skill text/signed-out static shell behavior, optimistic messages, streaming row identity, composer/sidebar interactions, thinking/tool rendering, responsive styling, visual polish, or Vercel dashboard chat comparisons. # Dashboard Chat Best Practices
OfficialSkillApache-2.0★ 5.6k in collectionNo key
Method-driven agent skills for knowledge work: strategy, research, critical thinking, data analysis, docs, slides. Works with Claude Code, Codex, Cursor and any agentskills.io-compatible agent.
SkillMIT★ 77No key
Forward deployed engineering skills for AI coding agents.
in the skill textevidence and next steps available between sessions. I built FDEOps around design thinking, first-principles thinking and systems thinking: understand the people doing the work, question
SkillMIT★ 962No key
An atelier for your Agent: spec-driven workflows, deep thinking, and code quality.
SkillMIT★ 47No key
Customize Claude Code's system prompts, create custom toolsets, input pattern highlighters, themes/thinking verbs/spinners, customize input box & user message styling, support AGENTS.md, unlock privat
in the skill textthe new theme, and sending a message to see the new thinking verb format." width="800"> > [!IMPORTANT] > **NEW in 4.0.0:** tweakcc now has an API; use
SkillMIT★ 2.5kNo key
AI agent skills for thinking clearly, making better decisions, and getting things done. Strategy, research, decision-making, planning, risk management, negotiation, execution, strategic thinking, BMAD
SkillMIT★ 26No key
The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.
in the skill textbacklash was immediate . But the problem goes deeper than collapsed file paths: - **Thinking steps** — Claude's chain-of-thought reasoning is completely invisible in the terminal
SkillMIT★ 4.0kNo key
Open-source healthcare AI agent skills and life sciences agent skills. 42 skills for medical coding, risk adjustment, claims analytics, quality measures, genomics, imaging, and drug discovery across 1
in the skill texthead-to-head comparisons depending on harness, with **up to 85% critical thinking** and **up to 87% scientific accuracy** win rates. Skills work on 20+ platforms
OfficialSkillMIT-0★ 62No key
Persistent memory for Claude Code and 6 other CLI agents, stored as plain markdown in your Obsidian vault. Stop re-explaining your projects, decisions and people every session. 45 commands: hybrid sem
in the skill textThe other 42 are there when you need them. auto-synthesis · thinking tools that argue with you live research from X, the web, and YouTube
SkillMIT★ 4.8kNo key
A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identi
in the skill textThink** — `bb-methodology` + `redteam-mindset`: the 5-phase non-linear workflow, critical-thinking framework, and red-team operator discipline. - **Hunt webapps** — 58 `hunt-*` skills curated from
SkillMIT★ 5.1kNo key
Open-source deep research MCP. Qwen3-30B-A3B-Thinking via OpenRouter, cited web synthesis for Claude Code, Codex, Cursor, Hermes and any MCP-compatible agent.
SkillMIT★ 62No key
A Claude skill that turns brainstorming into an interactive mind map of inverted assumptions — no answers, no ranking, just provocations.
in the skill textWonder Pill map — seeds, branches, dead ends, and the two places the thinking converged. --- Ask Claude for ideas and you get a list. Install Wonder Pill
SkillMIT★ 130No key
Cognitive Operating System for AI Agent (Skill.md) Self-thinking Multi-agent reasoning Meta-cognition Self-evolution
SkillApache-2.0★ 15No key
Build and query Kusto graphs from natural language. Covers transient graphs (make-graph), persistent graph models/snapshots, pattern matching (graph-match), shortest paths, connected components, and g
in the skill textpaths, connected components, and graph-to-table export. Generates the edges-first thinking: define edges, define node lookups, union, make-graph. WHEN: make-graph, graph-match
OfficialSkillMIT★ 257 in collectionNo key
Thinking tools for AI agents making discoveries in the life sciences
SkillMIT★ 11No key
Article, blog & paper writing prompts and Claude skills modelled on famous engineers and researchers. Works with Claude Code, ChatGPT, Gemini, and any LLM.
in the skill textChatGPT system prompts · LLM writing styles · engineer writing style · researcher writing style · thinking frameworks for LLMs · Andrej Karpathy writing style · Claude Code skills --- ## Available skills | Skill
SkillMIT★ 23No key
Money Atlas Skill.md (Claude Skill) For AI Agent A Genesis Protocol-powered intelligence system for financial markets, macroeconomics, and geopolitics. Core Systems - Genesis Protocol (First Principle
in the skill textscenario-based intelligence. Not a prediction engine. Not a signal bot. A thinking system — built to reason the way a disciplined analyst does. When you ask
SkillApache-2.0★ 58No key
Collection of Claude Code skills for enhanced AI workflows
in the skill textprivacy filter + local LLM) | | youtube-transcript | Transcript + metadata → Obsidian markdown, no video download | | thinking-patterns | Longitudinal cognitive analysis across months of transcripts (12 dimensions, multi-agent
SkillMIT★ 392No key
Claude Code plugin that generates individualized knowledge systems from conversation. You describe how you think and work, have a conversation and get a complete second brain as markdown files you own
in the skill textstart every session blank. Ars Contexta changes that by generating a persistent thinking system derived from how you actually work. **What you get:** - **A vault** -- plain
SkillMIT★ 3.5kNo key
Mental models as files an agent reads — bring your own, or start with 21 sourced ones. An Open Knowledge Format bundle + Claude Code skill.
in the skill textand Claude picks 2–4 models from different areas, walks their Thinking Steps against your actual problem, surfaces the conditions under which each one misleads you
SkillMIT★ 20No key
Context cleaning for Claude Code — prune bloated sessions, protect Agent Teams from context loss, auto-guard with tiered pruning
in the skill textmetadata-strip` | gentle | Strip token usage stats, stop_reason, costs | 1-3% | | 6 | `thinking-blocks` | standard | Remove/truncate thinking content + signatures | 2-5% | | 7 | `tool-output-trim
SkillMIT★ 425No key
Skills for Claude Code CLI such as full stack dev Cloudflare, React, Tailwind v4, and AI integrations.
in the skill textTen plugins of practical, production-oriented skills. Every one produces something. (The thinking skills — planning, prompt-writing, verification doctrine, brains-trust — live in their own framework
SkillMIT★ 1.1kNo key
Building a Claude-like agentic system.
in the skill textcomplete reproducible implementation of the 62 components that define Claude's thinking and agentic behavior, built on open source models and tested end to end
SkillMIT★ 65No key
Skills I use and develop to deliver better outcomes faster and with less effort.
in the skill textfor Claude Code covering development, DevOps, quality, context engineering, agent architecture, strategic thinking, design, documentation, research, and meta-skills. Plugins: `agent-evaluation`, `agent-project-development`, `api
SkillMIT★ 13No key
gemini drawing MCP & skill through browser, can be used in openclaw or any agent that supports MCP. Gemini画图 MCP和sill，支持龙虾或任何agent使用٩(๑>◡<๑)۶
in the skill texti18n 安全） - 🆕 新增思考深度切换：`getThinkingDepth()` / `setThinkingDepth('standard'|'extended')` - 🆕 新增 MCP 工具 `gemini_set_thinking_depth` **v1.1.0**（2026-05）— 已适配 Gemini **2026 年 5 月最新版 UI**： - ✅ 加号面板按钮（`gem
SkillMIT★ 834No key
A collection of my favorite custom Claude Code resources to make life easier.
in the skill textprompts - **Todo Management**: Capture context mid-work, resume later with full state - **Thinking Models**: Mental frameworks (first principles, inversion, 80/20, etc.) - **Deep Analysis**: Systematic debugging methodology
SkillMIT★ 2.0kNo key
After a substantive answer, adds two or three follow-up questions tied to its content; runs at most once per chat.
OfficialSkillApache-2.0No key
The Operating System for Clear Thinking & Better Decisions
SkillMIT★ 123No key
Die sokratische Methode als Claude Skill.md
in the skill textSocratic method (maieutics) for pedagogical interactions, cognitive restructuring, strategic coaching, and analytical thinking. Instead of delivering direct answers, Claude uses disciplined questioning to help users develop
SkillMIT★ 39No key
Epistemic analysis plugin for Claude Code - examine ideas through philosophical frameworks instead of just summarizing them
in the skill textmake a decision based on a shorter version of someone else's thinking. You can't spot a flaw that was faithfully preserved in compressed form
SkillMIT★ 3Few starsNo key
World-class creative director in a skill. Methodology-driven ideation (SIT, TRIZ, Lateral Thinking, bisociation) + a Cannes Lions evaluation engine, powered by a library of 571 legendary award-winning
SkillCC-BY-4.0★ 255No key
#1 Product of The Day @ Product Hunt. The GTM co-founder you don't have. Open-source GTM Agent Skills for developer tools and AI products, for founders, GTM hires, and founding AEs: positioning, first
in the skill textselling and advising developer tools and AI products, sharpened by the sharpest thinking in the field (** Adam Frankl ** and ** Jakub Czakon **), and pressure-tested by founders
SkillMIT★ 318No key
PM workflow and product thinking skills for AI product managers. 17 structured frameworks for PRDs, metrics, strategy, writing, prioritization, and more.
SkillMIT★ 26No key
An AI skill pack for value investing, capital allocation, and behavioral discipline, distilled from Warren Buffett's 60+ years of shareholder letters.
in the skill texteconomic-moat`（经济护城河）、`cigar-butt-vs-great-business`（雪茄蒂 vs 伟大企业）、`float-thinking`（浮存金思维） - **行为与心理**：`fear-and-greed`（恐惧与贪婪逆向）、`institutional-imperative`（机构强制力）、`hold-forever`（永久持有逻辑） - **资本配置与风控
SkillMIT★ 105No key
Install engineering discipline into any AI coding assistant. Composable skills for design, implementation, review, and team standards. Better process, not just better prompts.
in the skill textLattice Composable AI skills that teach assistants structured thinking — design-first, context-aware, and architecture-guided.  
