evo-anything
01MCP server Claude CodeCodexCursor +2
MCP server "evo-anything" as configured in DataLab-atom/EvoAny. Runs /home/user/Evo-anything/dist/server.js with node.
MCP server Claude CodeCodexCursor +2
MCP server "evo-anything" as configured in DataLab-atom/EvoAny. Runs /home/user/Evo-anything/dist/server.js with node.
Agent
You analyze the target repository to identify which functions to optimize.
Agent
You drive the evolution loop. You do not generate code or run benchmarks — you coordinate.
Agent
You review code changes before they are benchmarked. Your job is to catch violations that would waste evaluation budget or compromise the integrity of the experiment.
Agent
You analyze the results of each generation and write structured memory to guide future evolution.
Agent
You are the ResearchAgent — a specialized agent focused on understanding why evolutionary code changes work, not just that they work. Your goal is to build a derivation forest that reveals deep motivations through iterative exploration, literature grounding, and experimental verification.
Agent
You handle the full lifecycle of a single code variant: generate, validate, evaluate.
Skill Claude CodeCodex
Answer research questions using a local vector DB and online literature search, with auto-ingest for new papers. Use when you need to find relevant academic work or verify if an idea is novel.
Skill Claude CodeCodex
Boost a target — increase its evolution priority.
Skill Claude CodeCodex
Start evolutionary optimization on a git repository.
Skill Claude CodeCodex
Freeze a target — stop evolving it.
Skill Claude CodeCodex
Find, clone, and set up a codebase for a given task, then hand off to /evolve.
Skill Claude CodeCodex
Assemble D-layer chapter files (intro, method, experiment, related) into a complete LaTeX paper with bibliography and consistency checks. Use when combining all sections into a final manuscript.
Skill Claude CodeCodex
Generate evolution report.
Skill Claude CodeCodex
Iteratively build a derivation forest from evolution results to discover deep motivations and grade contributions for paper writing. Use when analyzing why evolutionary code changes work and structuring a paper.
Skill Claude CodeCodex
Search online academic literature (arXiv, Papers With Code, Google Scholar) and return structured results with BibTeX citations.
Skill Claude CodeCodex
Check current evolution progress.
Skill Claude CodeCodex
Generate the Experiments section with benchmark results, ablation studies, statistical analysis, and comparison with baselines.
Skill Claude CodeCodex
Generate the Introduction section of an academic paper from the C-layer derivation forest's convergence points and contributions. Outputs LaTeX format.
Skill Claude CodeCodex
Generate the Method section of an academic paper describing the proposed approach, baselines, and experimental setup. Outputs LaTeX format.
Skill Claude CodeCodex
Generate the Related Work section by surveying existing approaches and positioning the paper's contributions relative to the literature.