codex-reasoning-rigor
Force deliberate, evidence-backed, non-generic reasoning for complex engineering work. Use when the user asks for deeper thinking, less generic output, higher specificity, better workflow discipline, monitoring plans, or stronger quality-oriented delivery instead of shallow best-practice answers.
npx skills add majiayu000/claude-skill-registry --skill codex-reasoning-rigor --agent codex
Same command for any agent — swap --agent for claude-code, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Codex Reasoning Rigor ## Overview Use this skill to turn vague or generic model behavior into explicit decision-making, repo-grounded evidence gathering, and output contracts that are concrete enough to verify. Activate it when the task is important enough that "sounds right" is not good enough. ## Activation Activate on explicit `$codex-reasoning-rigor` or `$rigor`. Activate when the user says or implies: - "don't be generic" - "think harder" or "go deeper" - "make it specific" - "I need better workflow / monitoring / output quality" - "give me tradeoffs, not vague advice" - "show evidence" - "use the repo, not generic training data" Also activate for: - architecture or refactor decisions with hidden risk - reviews that need actionable findings instead of summaries - operational plans that need monitoring signals and stop/ship criteria - repeated tasks where model output has drifted or become bland ## Core Protocol Run this protocol before answering or implementing: ### 1. Task Contract Lock these fields explicitly: - `goal`: what outcome must change - `constraints`: what cannot change - `non_goals`: what should stay out of scope - `evidence_required`: what proof would make the
- Overview
- Activation
- Core Protocol
- 1. Task Contract
- 2. Decision Surface
- 3. Repo Grounding
- 4. Monitoring Lens
- 5. Output Contract
- Anti-Generic Rules
- Working Pattern
- Resources
What does the codex-reasoning-rigor skill do?
Force deliberate, evidence-backed, non-generic reasoning for complex engineering work. Use when the user asks for deeper thinking, less generic output, higher specificity, better workflow discipline, monitoring plans, or stronger quality-oriented delivery instead of shallow best-practice answers.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill codex-reasoning-rigor --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.