ops-perf-evolution
v1.0.1Ascend C 算子性能进化优化 Agent Team。对已有 AscendC 内核或 ops 仓库算子进行多轮并行进化优化,包含 1 个 Orchestrator Agent 和 4 个路径专用 Subagent。
By CANNBotLicense: MIT4 GitHub starsUpdated last week
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 5 skill or MCP entries
- Source updated
- Sep 16, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install ops-perf-evolution for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install ops-perf-evolution@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/hicann/cannbot-skillsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins-community/ops-perf-evolution/.
Plugin files
├── .claude-plugin/plugin.json├── skills/evolution-knowledge/SKILL.md├── skills/evolution-report/SKILL.md├── skills/evolution-strategies/SKILL.md├── skills/evolution-world-model/SKILL.md└── skills/ops-evaluation/SKILL.md
Included Skills5
Domain knowledge base for AscendC evolution optimization covering hardware architecture, algorithm insights, API pitfalls, optimization patterns, and proven solutions for A3 (910B) architecture. 当进行 AscendC 进化优化需要查询硬件架构、算法洞察、API 陷阱、优化模式或已验证方案时使用。
进化优化完成后自动生成标准化 HTML 可视化报告(全自动脚本生成,含自检,支持 ops-evo 和 lingxi-evo 两种 pipeline)。当进化轮次结束或需要汇总基线与各轮变体的性能对比、决策树与资源消耗时使用。
AscendC kernel optimization strategy library with 61+ strategies across D/P/A/R/X series, supporting tiered retrieval, compatibility checking, and autonomous strategy discovery. 当需要为 AscendC kernel 选择优化策略、按瓶颈/算子族筛选策略、检查策略兼容性或登记进化发现的新策略时使用。
World model decision tree tools and reference documentation for evidence-driven AscendC kernel evolution, providing CLI operations (select, validate, summary, deep-profiling) and schema/operations reference. 当进行证据驱动的 AscendC 内核进化优化,需要初始化、选择、验证、更新世界模型决策树或查询其 schema/操作规范时使用。
从 ops-nn/cv/math/transformer 等算子仓库构建、部署并评估 AscendC 算子,比较基线与进化后的性能差异。当需要构建 ops 仓库算子、运行正确性验证与性能评测、或对比基线版本与进化版本差异时使用。
Plugin manifests1
{
"name": "ops-perf-evolution",
"description": "Ascend C 算子性能进化优化 Agent Team。对已有 AscendC 内核或 ops 仓库算子进行多轮并行进化优化,包含 1 个 Orchestrator Agent 和 4 个路径专用 Subagent。",
"version": "1.0.1",
"author": {
"name": "CANNBot"
},
"homepage": "https://gitcode.com/cann/cannbot-skills",
"repository": "https://gitcode.com/cann/cannbot-skills",
"license": "MIT",
"dependencies": [
"ops-perf-evolution-shared-skills"
],
"agents": [
"./AGENTS.md",
"./agents/lingxi-evo.md",
"./agents/ops-evo.md",
"./agents/lingxi-partial.md",
"./agents/ops-partial.md"
]
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[ops-perf-evolution on Agent Plugins Marketplace](https://pluginsmp.com/plugins/ops-perf-evolution)