# tjboudreaux/cc-thinking-skills

28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools

Repository: https://github.com/tjboudreaux/cc-thinking-skills
Canonical: https://ross.abutalabs.com/products/cc-thinking-skills
Language: JavaScript
License: MIT
License Family: permissive
Topics: ai-tools, anthropic, claude, claude-code, critical-thinking, decision-making, first-principles, mental-models, problem-solving, systems-thinking, agent-skills
Last push: 2026-08-07T18:53:22+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 64, longevity 15
- inputs: {"age_days": 217, "days_push": 26, "days_rel": 29, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1260, forks 157 (observed 2026-08-28T04:04:09.433004+00:00)

## What it is
A catalog of 28 portable Agent Skills that give AI coding agents structured reasoning procedures based on mental models like first principles, five whys, pre-mortems, and theory of constraints. It installs into Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools via a CLI, plugin marketplace, or file copy.

## Use cases
- add structured reasoning skills to claude code
- make my ai coding agent think with mental models
- debug a bug using scientific method with an llm agent
- stress-test a launch plan with a pre-mortem skill
- find bottlenecks with theory of constraints in an ai assistant
- install agent skills for cursor or copilot
- choose the right thinking framework for a problem with an ai router

## When to choose
- you use Claude Code, Cursor, Copilot, Codex, or another Agent Skills-compatible tool and want repeatable reasoning procedures
- you want a router that picks the right mental model for diagnosis, decisions, risk, or strategy tasks
- you prefer eval-informed, MIT-licensed skills you can copy into any project

## When to avoid
- you need executable software rather than prompt-based skill definitions for AI agents
- your agent tool does not support the Agent Skills format
- you want guaranteed performance improvements without reviewing the catalog audit

## Facets
- artifact type: plugin
- maturity: active
- function: prompt-engineering, agent-framework, developer-tools, cli
- domain: artificial-intelligence, developer-tools
- platform: cli, cross-platform
- tags: agent-skills, claude-code, mental-models, critical-thinking, reasoning-frameworks, cursor, github-copilot, codex, ai-agents, nodejs

## Member repositories
- tjboudreaux/cc-thinking-skills (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:09.433004+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:04:25.473292+00:00, confidence not recorded.
  - readme: https://github.com/tjboudreaux/cc-thinking-skills (fetched 2026-08-28T04:04:09.433004+00:00, sha 4babd3c01d1f)
- Data as of 2026-08-30T08:39:29.467469+00:00.