Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools
| Date | Stars |
|---|---|
| 2026-08-05 | 933 |
| 2026-08-06 | 933 |
| 2026-08-13 | 952 |
| 2026-08-18 | 960 |
| 2026-08-19 | 964 |
| 2026-08-20 | 969 |
| 2026-08-22 | 975 |
| 2026-08-23 | 1097 |
| 2026-08-24 | 1167 |
| 2026-08-25 | 1242 |
| 2026-08-26 | 1257 |
| 2026-08-27 | 1264 |
| 2026-08-28 | 1267 |
| 2026-08-29 | 1272 |
| 2026-08-30 | 1275 |
| 2026-08-31 | 1278 |
| 2026-09-01 | 1281 |
| 2026-09-03 | 1284 |
| 2026-09-04 | 1285 |
| 2026-09-05 | 1286 |
| 2026-09-06 | 1289 |
| 2026-09-07 | 1292 |
| 2026-09-08 | 1293 |
| 2026-09-09 | 1294 |
| 2026-09-10 | 1299 |
| 2026-09-11 | 1304 |
| 2026-09-12 | 1307 |
| 2026-09-13 | 1310 |
| 2026-09-14 | 1315 |
| 2026-09-16 | 1317 |
| 2026-09-17 | 1316 |
| 2026-09-18 | 1319 |
| 2026-09-19 | 1321 |
| 2026-09-20 | 1323 |
| 2026-09-21 | 1325 |
| 2026-09-23 | 1324 |
| 2026-09-24 | 1326 |
| 2026-09-25 | 1327 |
| 2026-09-26 | 1330 |
| 2026-09-27 | 1331 |
| 2026-09-28 | 1333 |
| 2026-09-29 | 1334 |
| 2026-09-30 | 1335 |
| 2026-10-02 | 1338 |
| 2026-10-03 | 1385 |
| 2026-10-04 | 1479 |
| 2026-10-05 | 1569 |
| 2026-10-06 | 1603 |
| 2026-10-07 | 1605 |
| 2026-10-08 | 1611 |
| 2026-10-09 | 1613 |
| 2026-10-10 | 1615 |
| 2026-10-11 | 1619 |
| 2026-10-12 | 1623 |
| 2026-10-13 | 1629 |
| 2026-10-14 | 1635 |
| 2026-10-15 | 1639 |
| 2026-10-16 | 1641 |
| 2026-10-17 | 1645 |
| 2026-10-18 | 1650 |
| 2026-10-19 | 1651 |
| 2026-10-20 | 1658 |
| 2026-10-21 | 1660 |
| 2026-10-22 | 1662 |
| 2026-10-23 | 1664 |
| 2026-10-24 | 1667 |
| 2026-10-25 | 1669 |
| 2026-10-26 | 1674 |
| 2026-10-27 | 1676 |
| 2026-10-29 | 1677 |
| 2026-10-30 | 1680 |
| 2026-10-31 | 1683 |
| 2026-11-01 | 1687 |
| 2026-11-02 | 1694 |
| 2026-11-03 | 1696 |
| 2026-11-04 | 1700 |
Today
+4 stars today
This week
+24 stars this week
This month
+131 stars this month
Momentum
30.0
growth rate 1.43%/day
# Claude Code thinking skills > 28 portable Agent Skills for structured reasoning in Claude Code, GitHub Copilot, Codex, Cursor, and other compatible tools Claude Code Thinking Skills is a public catalog of Agent Skills. Use it for decisions, diagnosis, systems, risk, strategy, and innovation. Each skill gives an agent a clear procedure. Use a skill when its mechanism fits the task.  ## Contents Jump to [why use this catalog](#why-use-this-catalog), [quick start](#quick-start), [use a skill](#use-a-skill), [skill catalog](#skill-catalog), [evidence](#evidence), [repository layout](#repository-layout), [checks and contribution](#checks-and-contribution), [questions](#questions), or [license](#license). ## Why use this catalog Use these skills when a problem needs a clear reasoning frame. The catalog covers diagnosis, decisions, creation, risk, execution, product, and strategy. Read the [catalog audit](analysis/AUDIT.md) before making performance claims. ## Quick start ### Skills CLI ```bash npx skills add tjboudreaux/cc-thinking-skills ``` Install all skills without prompts: ```bash npx skills add tjboudreaux/cc-thinking-skills --all ``` ### Claude Code plugin ```text /plugin marketplace add tjboudreaux/cc-thinking-skills /plugin install thinking-skills@thinking-skills-marketplace ``` ### Copy from a clone ```bash git clone https://github.com/tjboudreaux/cc-thinking-skills.git mkdir -p /path/to/project/.agents/skills cp -R cc-thinking-skills/skills/* /path/to/project/.agents/skills/ ``` Claude Code can also load the same directories from `~/.claude/skills/` or `.claude/skills/`. ## Use a skill Start with the router when the right frame is unclear: ```text Use thinking-model-router to choose the right framework for this problem. ``` Invoke a leaf skill when the match is clear: ```text Use thinking-scientific-method to localize this bug. Use thinking-reversibility to classify this architecture decision. Use thinking-pre-mortem to stress-test this launch plan. Use thinking-theory-of-constraints to find the binding bottleneck. ``` The Claude Code plugin uses `thinking-skills:thinking-model-router` as the exact router ID. The router can return `NONE`, one skill, or up to three complementary skills. ## Skill catalog The 28 active skill IDs match the directories under [`skills/`](skills/) ### Route and compose - [`thinking-model-router`](skills/thinking-model-router/); choose `NONE`, one frame, or a few complementary frames - [`thinking-model-combination`](skills/thinking-model-combination/); sequence distinct models when one model leaves a blind spot ### Diagnose and understand - [`thinking-scientific-method`](skills/thinking-scientific-method/); rank causes and test the cheapest discriminator - [`thinking-five-whys-plus`](skills/thinking-five-whys-plus/); find systemic causes after localization - [`thinking-kepner-tregoe`](skills/thinking-kepner-tregoe/); compare IS/IS-NOT defects and must/want options - [`thinking-systems`](skills/thinking-systems/); map flows, feedback, delays, and high-impact points - [`thinking-map-territory`](skills/thinking-map-territory/); resolve conflicts between docs and live behavior - [`thinking-cynefin`](skills/thinking-cynefin/); classify the cause-and-effect domain - [`thinking-socratic`](skills/thinking-socratic/); expose hidden requirements with direct questions ### Decide and evaluate - [`thinking-reversibility`](skills/thinking-reversibility/); separate easy-to-undo choices from costly commitments - [`thinking-opportunity-cost`](skills/thinking-opportunity-cost/); compare a choice with the top forgone use of resources - [`thinking-probabilistic`](skills/thinking-probabilistic/); forecast with base rates, ranges, and belief updates - [`thinking-second-order`](skills/thinking-second-order/); trace delayed effects, incentives, and feedback - [`thinking-steel-manning`](skills/thinking-steel-manning/); build
Excerpt of 7,644 characters
Read on GitHub
95
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:fc972c08aba11435, llm:Repository topics and description: 'ai-tools, anthropic, claude, claude-code, critical-thinking, decision-making, first-principles, mental-models, problem-solving, systems-thinking' and description: '18 mental models and critical thinking frameworks for Claude Code - First Principles, Bayesian, Systems Thinking, OODA, Pre-Mortem, and more'
matched fp:fc972c08aba11435, llm:Repository topics and description: 'ai-tools, anthropic, claude, claude-code, critical-thinking, decision-making, first-principles, mental-models, problem-solving, systems-thinking' and description: '18 mental models and critical thinking frameworks for Claude Code - First Principles, Bayesian, Systems Thinking, OODA, Pre-Mortem, and more'