NeVibeCode · repository · 28 items
cc-thinking-skills: a set by tjboudreaux
The tjboudreaux/cc-thinking-skills repository on GitHub: 28 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.
About the repository
- GitHub
- tjboudreaux/cc-thinking-skills
- Stars
- ★ 1,758
- Installs across cards
- 19,457
- License
- MIT
- Source updated
- 2026-08-07
- In the catalog since
- 2026-10-25
thinking-first-principles skill thinking-first-principles — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that separates real constraints from inherited convention and rebuilds from primitives.
CX Codex +1
844installs
thinking-pre-mortem skill thinking-pre-mortem assumes a plan or launch has already failed, traces concrete causes backward, and turns them into explicit gates, owners, and verification checkpoints.
CX Codex +1
804installs
thinking-red-team skill thinking-red-team — a skill for authorized security review: it models the attacker, maps the attack surface, and keeps only findings with a reproducible exploit path and a verified fix.
CX Codex +1
800installs
thinking-theory-of-constraints skill thinking-theory-of-constraints is a Claude Code skill that finds a pipeline's binding constraint and plans the theory-of-constraints steps. It addresses pipelines where one stage limits throughput.
CX Codex +1
767installs
thinking-opportunity-cost skill thinking-opportunity-cost forces your AI coding agent to identify the best forgone alternative and calculate the net value delta before committing engineering hours or budget.
CX Codex +1
735installs
thinking-socratic skill thinking-socratic surfaces unstated assumptions and undefined terms before coding begins. Helps the agent ask decisive questions instead of guessing requirements.
CX Codex +1
730installs
thinking-second-order skill thinking-second-order traces consequences beyond an immediate fix, including reactions, timing, probability and feedback. Use it for architecture or strategic decisions with lasting effects.
CX Codex +1
717installs
thinking-model-router skill thinking-model-router — a router skill that maps domain and problem type to one thinking skill, or returns NONE. Useful when you would otherwise guess or stack frameworks.
CX Codex +1
713installs
thinking-steel-manning skill thinking-steel-manning builds the strongest opposing argument before rejecting or adopting a technical plan. Useful for architecture reviews and preventing sycophantic AI agreement.
CX Codex +1
708installs
thinking-systems skill thinking-systems — a skill for problems that resist local fixes: it maps the system, finds feedback loops and delays, then ranks interventions by leverage.
CX Codex +1
708installs
thinking-triz skill thinking-triz — a skill for when two design requirements pull against each other. It names the conflict and looks for a resolution that keeps both benefits.
CX Codex +1
690installs
thinking-probabilistic skill thinking-probabilistic is a Claude Code skill for forecasting timelines, outcomes, and risks with base rates, ranges, and evidence-based updates. Automatic invocation is disabled, so ask the agent to use it explicitly.
CX Codex +1
689installs
thinking-scientific-method skill thinking-scientific-method is a Claude Code skill that ranks falsifiable bug hypotheses and runs the cheapest discriminating check before code changes.
CX Codex +1
681installs
thinking-reversibility skill thinking-reversibility — a skill that makes the agent check how expensive a decision is to undo before it decides how much analysis to spend. Useful when you can't tell whether deep thought is warranted.
CX Codex +1
677installs
thinking-five-whys-plus skill thinking-five-whys-plus builds an evidence-backed causal chain from a localized fault to its systemic root. It helps uncover why an issue happened when symptom-level hotfixes keep failing.
CX Codex +1
671installs
thinking-ooda skill thinking-ooda — a skill for incidents and moving-target debugging: it runs the agent through Observe→Orient→Decide→Act at ~70% confidence, then re-observes.
CX Codex +1
669installs
thinking-via-negativa skill thinking-via-negativa — a skill for Claude Code and five other platforms that makes the agent subtract before it adds. Kicks in when the reflex reaches for a new feature, dependency, or abstraction.
CX Codex +1
665installs
thinking-circle-of-competence skill thinking-circle-of-competence makes the agent answer only from what it read or ran in this session. Useful when a confident wrong answer costs you.
CX Codex +1
664installs
thinking-jobs-to-be-done skill thinking-jobs-to-be-done works out the progress a user hires a product for, then ranks features by it. Useful when you cannot tell what to cut and what to grow.
CX Codex +1
661installs
thinking-cynefin skill thinking-cynefin sorts a problem into a Cynefin domain by cause and effect, then names the response mode: runbook, analysis, probe or stabilize. Useful when a method keeps failing.
CX Codex +1
658installs
thinking-bounded-rationality skill thinking-bounded-rationality — a skill that halts a search at the first option clearing a threshold you set beforehand, instead of comparing forever.
CX Codex +1
655installs
thinking-thought-experiment skill thinking-thought-experiment — a skill for when a real test is too rare, large or irreversible: the agent runs one counterfactual with an isolated variable and bounds what the result implies.
CX Codex +1
654installs
thinking-model-combination skill thinking-model-combination — a skill that sequences 2–3 mental models with named roles when one model leaves a blind spot. Built for multi-domain decisions.
CX Codex +1
654installs
thinking-map-territory skill The thinking-map-territory skill makes the agent check live code or data whenever a doc, test, metric or assumption disagrees with observed behavior.
CX Codex +1
652installs
thinking-kepner-tregoe skill thinking-kepner-tregoe — a skill for narrowing a defect with IS/IS-NOT analysis and for picking between options with MUST screening, weighted WANTs and downside checks.
CX Codex +1
651installs
thinking-margin-of-safety skill thinking-margin-of-safety makes the agent add a buffer to capacity, timeouts and schedule estimates, scaled by leftover uncertainty and the cost of a breach instead of the optimistic edge.
CX Codex +1
649installs
thinking-effectuation skill thinking-effectuation — a skill for Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode that guides the agent to act from available means and affordable loss rather than forecasts.
CX Codex +1
648installs
thinking-lindy-effect skill thinking-lindy-effect — a skill for Claude Code, Cursor and other platforms that teaches the agent to choose technologies and practices by survival time: the longer a solution has lasted, the longer it will last.
CX Codex +1
643installs