菜单
This skill should be used when the user asks to search for external algorithms, find related implementations, discover alternative approaches, or look up papers and code for computational math optimization methods.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Route AI4Math computational mathematics tasks to the appropriate bundled skill package.
Use when reproducing, deploying, diagnosing, tuning, visualizing, or reporting computational math research code with a coding agent
This skill should be used when the user asks to tune parameters, run hyperparameter search, optimize algorithm settings, or find the best configuration for a computational math method.
Use when classifying a computational math repository or task into a broad domain before choosing specialist Skills, references, runtimes, and validation evidence.
Use when a user starts an end-to-end computational math research-code reproduction, deployment, tuning, visualization, or reporting workflow with a coding agent.
This skill should be used when the user asks to detect what algorithm family a piece of code uses, identify optimization methods, or classify computational math approaches such as ADMM, PPA, proximal gradient, or primal-dual methods.
| name | algorithm-discovery-skill |
| description | This skill should be used when the user asks to search for external algorithms, find related implementations, discover alternative approaches, or look up papers and code for computational math optimization methods. |
Use this Skill when Codex needs to search external sources such as papers, project pages, and GitHub repositories for algorithm implementations relevant to a computational math task.
For end-to-end computational math research-code reproduction workflows, this Skill should be selected by computational_math_reproduction_workflow_skill rather than used as the first entrypoint.
skills/algorithm_discovery_skill/scripts/external_search.py is an optional helper for structured persistence or batch querying. It is not a workflow driver.
The helper can write algorithm_candidates.json with ranked candidates when Codex already has a structured task description and wants a repeatable artifact. Prefer native search in conversation unless the helper makes the evidence easier to reproduce.
