# Claude Code Thinking Skills By **tjboudreaux** ยท Skills 39 mental-model skills for Claude Code, first principles, Bayesian, OODA, pre-mortem, and more, all invoke-by-name with no setup. - Source: https://github.com/tjboudreaux/cc-thinking-skills - Repository: https://github.com/tjboudreaux/cc-thinking-skills - Tags: claude-code, mental-models, critical-thinking, open-source, reasoning, agent, mit - Pricing: free - Upvotes: 0 ## Features - 39 named thinking-framework skills invoke by name in Claude Code chat - thinking-model-router meta-skill automatically routes problems to the right framework - Plugin marketplace install with zero configuration required - Manual copy to ~/.claude/skills/ for global or per-project use - Elevate-or-Kill evaluation scorecard published openly for all 39 skills - Frameworks grounded in Munger, Kahneman, Goldratt, TRIZ, OODA, and Meadows - Quality scripts for validating, scoring, and improving skill files - MIT licensed, no restrictions on use, modification, or distribution --- ## Why it matters Most AI prompt packs claim to make models smarter but never test the claim. Claude Code Thinking Skills took the opposite approach: it ran all 39 frameworks through a length-controlled, replication-gated "Elevate-or-Kill" evaluation pipeline, then published the results, including the inconvenient finding that no skill currently holds a proven, replicated accuracy gain. That transparency is rare, and it matters when you're deciding whether to add a dependency. ## The big picture The collection covers six domains: decision-making and analysis (first principles, pre-mortem, Kepner-Tregoe), cognitive and behavioral (Bayesian, debiasing, steel-manning), systems and strategy (OODA, theory of constraints, Cynefin), problem-solving and innovation (TRIZ, five-whys-plus, scientific method), estimation and risk (Fermi estimation, red team, Lindy effect), and product (jobs-to-be-done, effectuation). Three meta-skills, including `thinking-model-router`, help you pick and combine frameworks. ## How it works Each skill is a `SKILL.md` file in Claude Code's skill system, which loads only when invoked, so unused frameworks cost nothing. You call any skill by name in the Claude Code chat, or you start with `thinking-model-router` and let it route the problem to the right framework. The plugin marketplace install (`/plugin marketplace add tjboudreaux/cc-thinking-skills`) is the recommended path; manual copy to `~/.claude/skills/` also works. ## By the numbers The closest candidate to a proven skill is `thinking-scientific-method` (hypothesis-differential debugging), which scored +5.3 percentage points (p=0.061, n=150) in its primary run and +8.0pp (p=0.001) in a separate replication. Per the README, because a significant replication cannot rescue a primary run that fails the p<0.05 gate, its verdict remains DIRECTIONAL-NOT-REPLICATED. A pre-registered, larger-N study is flagged as future work. ## Yes, but Treat these as well-grounded structured-reasoning scaffolds, not as proven accuracy boosters. The frameworks themselves are real and established; the empirical case for a model-accuracy lift is not yet there, and the project says so plainly. For teams that want structure in how Claude reasons through architecture decisions or incident postmortems, that scaffolding is still valuable even without a replicated accuracy gain. ## The bottom line If you want Claude Code to reason with named, established frameworks instead of ad-hoc heuristics, this is the most rigorously documented collection available. Start with `thinking-model-router`, pick the framework that fits your problem, and read the Elevate-or-Kill Scorecard before drawing conclusions about accuracy gains. ## FAQ ### What is Claude Code Thinking Skills? Claude Code Thinking Skills is a library of 39 mental-model and critical-thinking frameworks packaged as Claude Code skills. Each skill wraps a named reasoning framework, from first-principles thinking to the theory of constraints, into a file Claude loads and applies when you invoke it by name. The collection is MIT licensed, grounded in frameworks from Munger, Kahneman, Goldratt, Altshuller/TRIZ, and Boyd, and organized across six domains covering decisions, cognition, systems, problem-solving, estimation, and product thinking. ### How do I install and use it? The recommended install is via the Claude Code plugin marketplace: run `/plugin marketplace add tjboudreaux/cc-thinking-skills` followed by `/plugin install thinking-skills@thinking-skills-marketplace`. Alternatively, clone the repo and copy the skills folder to `~/.claude/skills/` for global use, or to `.claude/skills/` inside a specific project. Once installed, invoke any skill by name in Claude Code chat, for example `Use the theory-of-constraints to find our bottleneck`. If you are unsure which framework fits, start with `thinking-model-router` and let it route you. ### Is it free or open source? Yes, the project is released under the MIT license, which means you can use, modify, and distribute it freely. There is no paid tier or commercial restriction. The full source, including the evaluation pipeline and scorecard, is publicly available on GitHub. ### What is it best for? It works best when you want Claude Code to reason with an explicit, named framework rather than ad-hoc heuristics. Per the README, it suits engineers debugging complex systems, architects evaluating design tradeoffs, teams running incident postmortems, and founders stress-testing plans. The `thinking-model-router` meta-skill is the recommended entry point if you are unsure which of the 39 frameworks fits your situation. ### How does it compare to alternatives like wanikua/thinking-skills? The main difference is scope and evaluation rigor. This collection ships 39 frameworks versus the 20 custom commands in wanikua/thinking-skills, and it is the only one to run a replication-gated Elevate-or-Kill evaluation and publish the results. wanikua/thinking-skills uses the older `.claude/commands/` convention and simpler installation (copy the folder), while this project targets the Claude Code plugin marketplace and the newer SKILL.md skill system. Both are MIT licensed. ### What are the limitations? The most important limitation is documented by the project itself: per the published Elevate-or-Kill Scorecard, zero skills currently hold a robust, replicated ELEVATE verdict, meaning none are proven to improve Claude's accuracy. The closest candidate, `thinking-scientific-method`, showed a directional signal (+5.3pp, p=0.061 in the primary run) but fails the p<0.05 significance gate. Treat the skills as well-grounded structured-reasoning scaffolds rather than guaranteed accuracy boosters. A pre-registered, larger-N study is recommended as future work. --- [View on Analog](https://analoghq.ai/tjboudreaux/skills/claude-code-thinking-skills)