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 skills add mindspore-ai/akg --skill kernel-designergit 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/kernel-designer)<a href="https://agentmods.dev/skills/mindspore-ai/akg/kernel-designer"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/kernel-designer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mindspore-ai/akg/kernel-designer"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/kernel-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 49 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 57 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00081 | $0.02625 |
| Opus 5 | $0.00041 | $0.01313 |
| Sonnet 5 | $0.00016 | $0.00525 |
| Haiku 4.5 | $0.00008 | $0.00263 |
Grade A, and why
kernel-designer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
算子算法草图设计 Skill
设计原则：
- 设计清晰的、可理解的算法流程
- 遵循 DSL 和硬件特性的最佳实践
- 考虑目标硬件架构的优化机会（并行度、内存访问模式）
- 标注优化点和权衡决策
草图应具备：高层抽象（关注算法逻辑和优化策略，而非实现细节）、易于理解（便于 Coder 转换为可执行代码）、包含优化提示（标注并行化、内存优化、循环展开等机会）。
工作模式
本 skill 根据输入自动判断工作模式：
| 模式 | 触发条件 | 行为 |
|---|---|---|
| 首次设计 | 无 inspirations |
加载参考文档 → 分析任务 → 生成草图 |
| 进化优化 | 有 inspirations |
加载参考文档 → 分析历史草图性能 → 生成优化后的草图 |
| Hint 模式 | enable_hint_mode 且 task_desc 含 hint 标记 |
加载参考文档 → 分析任务 → 生成草图 + 参数空间配置（JSON 输出） |
设计流程
Step 1: 加载参考文档
根据 arch、dsl 和 task_desc 参数，用 read 工具读取参考文档。
本 skill 加载后，
<base_url>标签提供 skill 目录路径（记为$SD）。所有参考文档路径基于$SD/references/。
1.1 Sketch DSL 规范（必选）
始终加载：
$SD/references/designer-skills/sketch-design/SKILL.md
1.2 Hint 模式指南（条件加载）
当 enable_hint_mode 为 true 且 task_desc 中包含 hint 标记（@hint:、@range_hint、@elemwise_hint 等）时加载：
$SD/references/designer-skills/hint-mode/SKILL.md
⚠️ 参考文档路径下的文件虽然名为
SKILL.md，但在此上下文中它们是参考内容文件。请使用read工具按文件路径读取，不要使用skill工具加载。
1.3 硬件规格
路径：$SD/references/hardware/{文件名}
| arch 前缀 | 文件名 |
|---|---|
a100 |
CUDA_A100.md |
h20 |
CUDA_H20.md |
l20 |
CUDA_L20.md |
rtx3090 |
CUDA_RTX3090.md |
ascend910b1 |
Ascend910B1.md |
ascend910b2 |
Ascend910B2.md |
ascend910b2c |
Ascend910B2C.md |
ascend910b3 |
Ascend910B3.md |
ascend910b4 |
Ascend910B4.md |
ascend310p3 |
Ascend310P3.md |
ascend910_9362 |
Ascend910_9362.md |
ascend910_9372 |
Ascend910_9372.md |
ascend910_9381 |
Ascend910_9381.md |
ascend910_9382 |
Ascend910_9382.md |
ascend910_9391 |
Ascend910_9391.md |
ascend910_9392 |
Ascend910_9392.md |
ascend950dt_95a |
Ascend950DT_95A.md |
ascend950pr_950z |
Ascend950PR_950z.md |
ascend950pr_9572 |
Ascend950PR_9572.md |
ascend950pr_9574 |
Ascend950PR_9574.md |
ascend950pr_9575 |
Ascend950PR_9575.md |
ascend950pr_9576 |
Ascend950PR_9576.md |
ascend950pr_9577 |
Ascend950PR_9577.md |
ascend950pr_9578 |
Ascend950PR_9578.md |
ascend950pr_9579 |
Ascend950PR_9579.md |
ascend950pr_957b |
Ascend950PR_957b.md |
ascend950pr_957d |
Ascend950PR_957d.md |
ascend950pr_9581 |
Ascend950PR_9581.md |
ascend950pr_9582 |
Ascend950PR_9582.md |
ascend950pr_9584 |
Ascend950PR_9584.md |
ascend950pr_9587 |
Ascend950PR_9587.md |
ascend950pr_9588 |
Ascend950PR_9588.md |
ascend950pr_9589 |
Ascend950PR_9589.md |
ascend950pr_958a |
Ascend950PR_958a.md |
ascend950pr_958b |
Ascend950PR_958b.md |
ascend950pr_9591 |
Ascend950PR_9591.md |
ascend950pr_9592 |
Ascend950PR_9592.md |
ascend950pr_9599 |
Ascend950PR_9599.md |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 177 lines · 81 tokens per session scan A 51cac3071d11
kernel-designer is a skill published in the GitHub repository mindspore-ai/akg (259 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 2,625 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…