Skip to content
Back to search

thinking-skills-marketplace

MarketplaceWorks with Claude CodeGitHub

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

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/tjboudreaux--cc-thinking-skills/badge.svg)](/listings/tjboudreaux--cc-thinking-skills)

HTML

<a href="/listings/tjboudreaux--cc-thinking-skills"><img src="/api/listings/tjboudreaux--cc-thinking-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Skills CLI

npx skills add tjboudreaux/cc-thinking-skills

Install all skills without prompts:

npx skills add tjboudreaux/cc-thinking-skills --all

Claude Code plugin

/plugin marketplace add tjboudreaux/cc-thinking-skills
/plugin install thinking-skills@thinking-skills-marketplace

Copy from a clone

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/`.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 28 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "thinking-skills-marketplace",
  3. "owner": {
  4. "name": "TJ Boudreaux",
  5. "email": "tj@tjboudreaux.com"
  6. },
  7. "metadata": {
  8. "description": "Mental models and thinking skills for Claude Code, with eval-informed guidance for better reasoning",
  9. "version": "1.0.0"
  10. },
  11. "plugins": [
  12. {
  13. "name": "thinking-skills",
  14. "source": "./",
  15. "description": "28 eval-informed thinking skills for Claude Code, including first-principles, probabilistic reasoning, systems thinking, TRIZ, OODA, pre-mortem analysis, and more",
  16. "version": "1.0.0",
  17. "category": "productivity",
  18. "tags": [
  19. "thinking",
  20. "mental-models",
  21. "decision-making",
  22. "systems-thinking",
  23. "problem-solving",
  24. "cognitive-frameworks"
  25. ]
  26. }
  27. ]
  28. }
README.md · README · 179 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Claude Code thinking skills
  2. > 28 portable Agent Skills for structured reasoning in Claude Code, GitHub Copilot, Codex, Cursor, and other compatible tools
  3. 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.
  4. ![Claude Code thinking skills banner](assets/readme-banner.png)
  5. ## Contents
  6. 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).
  7. ## Why use this catalog
  8. Use these skills when a problem needs a clear reasoning frame. The catalog covers diagnosis, decisions, creation, risk, execution, product, and strategy.
  9. Read the [catalog audit](analysis/AUDIT.md) before making performance claims.
  10. ## Quick start
  11. ### Skills CLI
  12. ```bash
  13. npx skills add tjboudreaux/cc-thinking-skills
  14. ```
  15. Install all skills without prompts:
  16. ```bash
  17. npx skills add tjboudreaux/cc-thinking-skills --all
  18. ```
  19. ### Claude Code plugin
  20. ```text
  21. /plugin marketplace add tjboudreaux/cc-thinking-skills
  22. /plugin install thinking-skills@thinking-skills-marketplace
  23. ```
  24. ### Copy from a clone
  25. ```bash
  26. git clone https://github.com/tjboudreaux/cc-thinking-skills.git
  27. mkdir -p /path/to/project/.agents/skills
  28. cp -R cc-thinking-skills/skills/* /path/to/project/.agents/skills/
  29. ```
  30. Claude Code can also load the same directories from `~/.claude/skills/` or `.claude/skills/`.
  31. ## Use a skill
  32. Start with the router when the right frame is unclear:
  33. ```text
  34. Use thinking-model-router to choose the right framework for this problem.
  35. ```
  36. Invoke a leaf skill when the match is clear:
  37. ```text
  38. Use thinking-scientific-method to localize this bug.
  39. Use thinking-reversibility to classify this architecture decision.
  40. Use thinking-pre-mortem to stress-test this launch plan.
  41. Use thinking-theory-of-constraints to find the binding bottleneck.
  42. ```
  43. 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.
  44. ## Skill catalog
  45. The 28 active skill IDs match the directories under [`skills/`](skills/)
  46. ### Route and compose
  47. - [`thinking-model-router`](skills/thinking-model-router/); choose `NONE`, one frame, or a few complementary frames
  48. - [`thinking-model-combination`](skills/thinking-model-combination/); sequence distinct models when one model leaves a blind spot
  49. ### Diagnose and understand
  50. - [`thinking-scientific-method`](skills/thinking-scientific-method/); rank causes and test the cheapest discriminator
  51. - [`thinking-five-whys-plus`](skills/thinking-five-whys-plus/); find systemic causes after localization
  52. - [`thinking-kepner-tregoe`](skills/thinking-kepner-tregoe/); compare IS/IS-NOT defects and must/want options
  53. - [`thinking-systems`](skills/thinking-systems/); map flows, feedback, delays, and high-impact points
  54. - [`thinking-map-territory`](skills/thinking-map-territory/); resolve conflicts between docs and live behavior
  55. - [`thinking-cynefin`](skills/thinking-cynefin/); classify the cause-and-effect domain
  56. - [`thinking-socratic`](skills/thinking-socratic/); expose hidden requirements with direct questions
  57. ### Decide and evaluate
  58. - [`thinking-reversibility`](skills/thinking-reversibility/); separate easy-to-undo choices from costly commitments
  59. - [`thinking-opportunity-cost`](skills/thinking-opportunity-cost/); compare a choice with the top forgone use of resources
  60. - [`thinking-probabilistic`](skills/thinking-probabilistic/); forecast with base rates, ranges, and belief updates
  61. - [`thinking-second-order`](skills/thinking-second-order/); trace delayed effects, incentives, and feedback
  62. - [`thinking-steel-manning`](skills/thinking-steel-manning/); build the strongest opposing case before deciding
  63. - [`thinking-bounded-rationality`](skills/thinking-bounded-rationality/); set a good-enough threshold and stop the search
  64. - [`thinking-circle-of-competence`](skills/thinking-circle-of-competence/); check the evidence boundary before answering
  65. - [`thinking-lindy-effect`](skills/thinking-lindy-effect/); weigh durability while checking for domain change
  66. ### Create and improve
  67. - [`thinking-first-principles`](skills/thinking-first-principles/); separate physics from convention and rebuild from basics
  68. - [`thinking-triz`](skills/thinking-triz/); resolve apparently incompatible design requirements
  69. - [`thinking-via-negativa`](skills/thinking-via-negativa/); remove harmful or nonessential elements first
  70. - [`thinking-thought-experiment`](skills/thinking-thought-experiment/); test controlled what-if scenarios when real tests cost too much
  71. - [`thinking-jobs-to-be-done`](skills/thinking-jobs-to-be-done/); understand the progress users hire a product to make
  72. - [`thinking-effectuation`](skills/thinking-effectuation/); act from available means under uncertainty
  73. ### Manage risk and execution
  74. - [`thinking-pre-mortem`](skills/thinking-pre-mortem/); turn failure paths into fixes and stop checks
  75. - [`thinking-red-team`](skills/thinking-red-team/); review authorized attack paths with reproducible findings
  76. - [`thinking-margin-of-safety`](skills/thinking-margin-of-safety/); size buffers against error and breach cost
  77. - [`thinking-theory-of-constraints`](skills/thinking-theory-of-constraints/); find and manage the binding throughput constraint
  78. - [`thinking-ooda`](skills/thinking-ooda/); act while a time-pressured situation changes
  79. ## Evidence
  80. The catalog audit reports:
  81. - 28 active skills, all manual-only
  82. - no automatic-retain verdict
  83. - `portfolio-v1` with zero model calls and an unmeasured result
  84. - a provisional `thinking-scientific-method` row at +4.0 percentage points
  85. The +4.0-point row is below the +5-point utility margin and has evidence gaps. Treat it as directional evidence, not an accuracy claim. See the [decision-ready audit](analysis/AUDIT.md) and [`analysis/evidence.json`](analysis/evidence.json)
  86. ## Repository layout
  87. ```text
  88. skills/ Agent Skill source
  89. scripts/ skill validation
  90. evals/ structural, routing, and outcome evals
  91. analysis/ evidence registry and audit
  92. .claude-plugin/ Claude Code metadata
  93. ```
  94. Study artifacts live under [`evals/studies/`](evals/studies/). External datasets follow their license limits.
  95. ## Checks and contribution
  96. Validate skill structure:
  97. ```bash
  98. node scripts/validate-skills.js
  99. ```
  100. Run the local structural gate:
  101. ```bash
  102. EVAL_RUN=local node evals/run-structural.js
  103. ```
  104. Run routing evaluation with the authenticated `droid` CLI:
  105. ```bash
  106. EVAL_RUN=local node evals/run-routing.js
  107. ```
  108. Read the [evaluation harness guide](evals/README.md) and [CONTRIBUTING.md](CONTRIBUTING.md) before changing the catalog.
  109. To add a skill, create `skills/thinking-{name}/SKILL.md` with Agent Skills YAML front matter, a precise trigger, a non-trigger boundary, a procedure, and checks. Run validation and the relevant evaluation before submitting.
  110. ## Questions
  111. ### Which skill should I start with?
  112. Use `thinking-model-router` when the fit is unclear. Use a leaf skill when the task already names its mechanism.
  113. ### Can I use a skill without the router?
  114. Yes. Invoke any skill directly when its trigger matches.
  115. ### Do these skills guarantee better model accuracy?
  116. No. The evidence supports structured procedures, not a guaranteed accuracy gain.
  117. ## License
  118. MIT License. See [LICENSE](LICENSE) for the full text.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.