Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/mindspore-ai/akg/adaptive-evolvenpx skills add mindspore-ai/akg --skill adaptive-evolvegit clone --depth 1 https://github.com/mindspore-ai/akgWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mindspore-ai/akg/adaptive-evolve)<a href="https://agentmods.dev/skills/mindspore-ai/akg/adaptive-evolve"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/adaptive-evolve.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.01512 |
| Opus 5 | $0.00012 | $0.00756 |
| Sonnet 5 | $0.00005 | $0.00302 |
| Haiku 4.5 | $0.00002 | $0.00151 |
Grade A, and why
adaptive-evolve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
自适应进化工作流
概述
自适应进化工作流使用进化算法（Evolutionary Algorithm）进行算子优化，适合复杂的融合算子和性能关键的场景。
核心原理
进化策略
- 种群初始化: Designer生成多个候选设计
- 个体编码: Coder将设计转换为可执行代码
- 适应度评估: Verifier评估性能和正确性
- 选择与变异: 保留优秀个体，产生新变种
- 迭代优化: 多轮进化直到收敛
自适应机制
- 根据失败次数自动调整策略
- 动态切换编码风格（iterative ↔ aggressive）
- 智能调整种群大小
算法流程
Designer → 生成N个设计方案
↓
Coder → 编码为可执行代码（并发）
↓
Verifier → 评估适应度
↓
选择 → 保留前K个优秀个体
↓
变异 → 生成新候选
↓
[循环多轮] → 直到性能达标或迭代上限
配置参数
种群参数
population_size: 种群大小（默认：10）generations: 迭代代数（默认：20）elite_size: 精英数量（默认：2）
选择策略
selection_method: tournament, roulette, rankmutation_rate: 变异概率（默认：0.3）crossover_rate: 交叉概率（默认：0.7）
自适应策略
failure_threshold: 失败阈值，触发策略切换（默认：3）adaptive_population: 动态调整种群大小early_stopping: 提前停止条件
适用场景
✅ 推荐使用
- 融合算子: MatMul+ReLU+Bias等
- 性能敏感: 需要极致优化
- 复杂约束: 多维度优化目标
- 探索空间大: 设计空间广阔
❌ 不推荐使用
- 简单算子: 直接用standard-workflow更快
- 时间受限: 进化需要较长时间
- 确定性需求: 结果有随机性
性能对比
| 算子类型 | Standard | Adaptive-Evolve | 提升 |
|---|---|---|---|
| 简单MatMul | 5s | 60s | 10% |
| 融合算子 | 10s | 90s | 45% |
| 复杂Kernel | 20s | 180s | 80% |
结论: 复杂场景下，额外时间投入带来显著性能提升。
实现细节
Designer策略
# 初始种群生成
designs = designer.generate_initial_population(
size=population_size,
task_desc=task_description
)
# 变异操作
new_designs = designer.mutate(
parent_designs=elite_designs,
mutation_rate=0.3
)
Coder并发
# 并发编码
codes = await asyncio.gather(*[
coder.encode(design)
for design in designs
])
Verifier评估
# 适应度函数
fitness = verifier.evaluate(
code=code,
metrics=['accuracy', 'latency', 'memory']
)
fitness_score = 0.4*accuracy + 0.4*(1/latency) + 0.2*(1/memory)
成功案例
案例1: Flash Attention优化
- baseline: 标准实现 5.2ms
- evolved: 进化20代后 3.1ms (40%提升)
- 迭代: 12代收敛
案例2: 融合Conv+BN+ReLU
- baseline: 三个独立算子 8.5ms
- evolved: 融合优化 4.2ms (51%提升)
- 迭代: 18代收敛
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 196 lines · 23 tokens per session scan A 1a397a6b9f90
adaptive-evolve is a skill published in the GitHub repository mindspore-ai/akg (259 stars, last pushed 26d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,512 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.
tencent-docs
腾讯文档（docs.qq.com）-在线云文档平台，是创建、编辑、管理文档的首选 skill。涉及"新建/创建/编辑/读取/查看/搜索文档"、"保存文件"、"云文档"、"腾讯文档"、"docs.qq.com"等操作，请优先使用本 skill。支持能力：(1) 创建各类在线文档（文档/Word/Excel/幻灯片/思维导图/流程图/智能表格/收集表）(2) 管理知识库空间（创建空间、查询空间列表）(3) 管理空间节点、文件夹结构 (4) 读取/搜索文档内容 (5) 编辑操作智能表 (6) 编辑操作在线文档 (7) 文件管理（重命名、移动、删除、复制、导入导出）(8) 网页剪藏、本地文件/文档上云。.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
n8n:human-like-code-review
Reviews a GitHub pull request like a thoughtful human reviewer and writes the feedback to a markdown file. Prioritizes context, architecture fit, solution complexity, bugs, security edge cases, and missing tests. Use when given a PR URL to review, or when the user says /human-like-code-review.
wechat-article-pro
微信公众号文章发布专业版。功能：1)联网搜索热点信息 2)AI生成微信公众号封面图 3)撰写3000-5000字深度文章 4)使用公众号AI配图功能自动生成并上传封面 5)参考刘润公众号风格写作 6)自动排版 7)不加话题标签.