/research-test
Creates tests for research code and generates publication-quality visualizations. Requires implemented code in `src/` of an active research output directory.
$ npx -y skills add Axect/magi-researchers --skill research-test --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/research-test
Context preview
The summary Claude sees to decide when to auto-load this skill.
Creates tests for research code and generates publication-quality visualizations. Requires implemented code in `src/` of an active research output directory.
Three AI models, one synthesis — Claude, Gemini & Codex cross-verify each other for rigorous multi-perspective research
Other skills on magi-researchers.
- /research-brainstorm
Generates and cross-validates research ideas using Gemini and Codex in parallel, then synthesizes results with Claude.
Open skill - /research-execute
Executes the research code in `src/` to generate result artifacts in `results/`. This is Phase 3.5 of the research pipeline, sitting between Implementation (Phase 3) and Testing & Visualization (Phase 4).
Open skill - /research-explain
Generates high-quality explanations of concepts using Gemini and Codex in parallel (Phase 1: MAGI strategy exploration), then synthesizes a single-voice explanation with Claude (Phase 2: convergent generation).
Open skill - /research-implement
Implements research code based on an existing research plan. Requires a `research_plan.md` to be present in the active research output directory.
Open skill - /research-report
Generates a structured markdown research report from all previous phase outputs. Actively integrates existing plots, generates missing visualizations, and cross-verifies claim-evidence integrity. Requires at least some prior phase results to exist.
Open skill - /research-search
Searches academic literature via OpenAlex (240M+ works) and optionally web sources. Standalone skill for quick literature discovery without the full brainstorm pipeline.
Open skill