Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
physics-problems
Datasets & benchmarksHugging Face dataset by HumynLabs
HumynLabs/physics-problems -
cc-thinking-skills
Skills28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools
git clone https://github.com/tjboudreaux/cc-thinking-skills.git -
tree-of-thought-llm
AI repositories[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models
git clone https://github.com/princeton-nlp/tree-of-thought-llm.git -
tree-of-thoughts
PromptsPlug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%
git clone https://github.com/kyegomez/tree-of-thoughts.git -
inquisitor
MCP serversHypothesis-driven problem solving for AI agents: probe, falsify, escalate.
inquisitor-mcp@0.2.2 -
inquisitor
MCP serversHypothesis-driven problem solving for AI agents: probe, falsify, escalate.
inquisitor-mcp@0.2.3 -
DataGraph
MCP serversUrban intelligence knowledge graph. Structured locality data for civic problem-solving.
datagraph-city-mcp-server@1.7.2 -
algo-sensei
SkillsYour AI-powered LeetCode & DSA mentor for Claude Code and Claude.ai. Master algorithms through intelligent guidance, progressive hints, and pattern recognition training—not just copy-pasting solutions. Features: Mock interviews, code review, multi-language support (Python, Java, C++, JS, Go). Learn to think like a senior engineer. 🥋
git clone https://github.com/karanb192/algo-sensei.git -
thinking-framework-skills
SkillsEvidence-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 Claude Code, Codex, and other AI agents. Advanced (Gold) tier.
git clone https://github.com/product-on-purpose/thinking-framework-skills.git -
Driftcraft
Prompts--- name: driftcraft description: Driftcraft is not a problem-solving assistant. It is a navigable linguistic space for staying with ambiguity, contradiction, and unfinished thoughts. Language here is not a command…
-
Algorithm Competition Coach
PromptsAct as a coach for algorithm competitions. You are an experienced mentor in preparing students for algorithm contests, providing guidance on problem-solving techniques, optimizing algorithms, and developing competitive…
-
zetetic-team-subagents
SkillsOne epistemic standard on three hosts. Claude Code: 15 problem-shaped skills, 97 sourced reasoning patterns, 120 agents, commit-time gates. Codex and Gemini CLI: portable evidence-synthesis, design and goal-loop skills. Shared gates block unsourced constants, vacuous tests and AI-writing patterns. I do not know is a supported outcome.
git clone https://github.com/cdeust/zetetic-team-subagents.git -
Meituan: LongCat 2.0
ModelsLongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...
meituan/longcat-2.0 -
Google: Gemini 4 Argon
ModelsGemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...
google/gemini-4-argon -
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...
google/gemini-4-argon:batch
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.