Skill Claude CodeCodex
Run the decomposed review pipeline for a single hypothesis and persist each review stage as a structured artifact.
Scientific agent skills for Claude Code and Codex that turn research goals into auditable hypothesis generation, review, ranking, evolution, and synthesis.
Skill Claude CodeCodex
Run the decomposed review pipeline for a single hypothesis and persist each review stage as a structured artifact.
Skill Claude CodeCodex
Summarize the completed reviews for a hypothesis.
Skill Claude CodeCodex
Simulate the hypothesis mechanism and identify failure scenarios.
Skill Claude CodeCodex
Extract recurring critique patterns from the completed review of a hypothesis.
Skill Claude CodeCodex
Select the next island strategy and parent hypothesis set for one evolution round.
Skill Claude CodeCodex
Run the canonical literature search bridge for one evidence query and persist traceable evidence artifacts.
Skill Claude CodeCodex
Apply deterministic Elo updates for one completed tournament batch, persist touched hypotheses, and write the ranking update receipt.
Skill Claude CodeCodex
Generate a ResearchPlan from input.md or equivalent raw research input.
Skill Claude CodeCodex
Generate the final research overview from the top-ranked hypotheses.
Skill Claude CodeCodex
Interpret the user's high-level research intent into RUNPOLICY.yaml and state/POLICYDECISION.json.
Skill Claude CodeCodex
Goal.
Skill Claude CodeCodex
Goal.
Skill Claude CodeCodex needs its repo
Goal.
Skill Claude CodeCodex
Goal.
Skill Claude CodeCodex
Goal.
Skill Claude CodeCodex
Goal.
Skill Claude CodeCodex
Goal.
Skill Claude CodeCodex
Goal.
Skill Claude CodeCodex
Produce the current state/STRATEGYPLAN.json bundle for configuration, generation, review, evolution, or overview routing.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: