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 pypto-case-reduction-sumgit 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/pypto-case-reduction-sum)<a href="https://agentmods.dev/skills/mindspore-ai/akg/pypto-case-reduction-sum"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/pypto-case-reduction-sum/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/pypto-case-reduction-sum"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/pypto-case-reduction-sum.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.00799 |
| Opus 5 | $0.00015 | $0.00400 |
| Sonnet 5 | $0.00006 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
pypto-case-reduction-sum 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 10d 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.
What it actually says
单轴归约:Sum Reduction(3D)
最简单的模式——不需要 loop/view/assemble,kernel 只有 3 行。
def create_sum_reduction_kernel(in_shape, out_shape):
@pypto.frontend.jit(runtime_options=..., debug_options=...)
def kernel(
x: pypto.Tensor(in_shape, pypto.DT_FP32),
) -> pypto.Tensor(out_shape, pypto.DT_FP32):
output = pypto.tensor(list(out_shape), pypto.DT_FP32)
pypto.set_vec_tile_shapes(1, 16, 256)
output[:] = pypto.sum(x, dim=1, keepdim=True)
return output
return kernel
forward:保持原始维度,不降维。
def forward(self, x):
assert x.dim() == 3
assert tuple(x.shape) == (16, 256, 256)
assert self.dim == 1
x = x.contiguous()
batch, _, dim2 = x.shape
return create_sum_reduction_kernel(
tuple(x.shape), (batch, 1, dim2)
)(x)
模式要点
- 保持输入原始维度,不 reshape → tile 参数个数 = input rank
- kernel 极简:
set_tile + sum + return,无需 loop/view/assemble pypto.amin/pypto.amax同理,只换 API- mean =
sum * (1.0 / size)(无内建 mean API) - 对
(16, 256, 256), dim=1的 3D 单轴归约,默认首选从(1, 16, 256)起步,再按32/64对照实测。 - 这里不要套用 loop 的“中段先试”习惯到 tile;该固定形状直接以
(1, 16, 256)作为默认实现。 - 对该固定形状,
(1, 32, 256)与(1, 64, 256)不作为默认模板,仅作为对照候选。
强约束(reduction_over_a_dimension 系列)
- 本系列题目的
get_init_inputs()返回值是本次固定参数(例如dim=1)。 - 注释里的
Example, change to desired dimension是题库说明,不是当前实现目标。 - 生成代码时:
- 保留
ModelNew.__init__(dim)签名; forward中assert self.dim == <固定值>;- kernel 使用固定常量
dim=<固定值>,不要写if dim == ...分支; - 固定 dim 场景下,
create_*_kernel不再接收dim运行时参数。
- 保留
反例(不要这样写):
def create_xxx_kernel(in_shape, out_shape, dim):
...
output[:] = pypto.amin(x, dim=dim, keepdim=True)
正例(固定 dim 写死):
FIXED_DIM = 1
def create_xxx_kernel(in_shape, out_shape):
...
output[:] = pypto.amin(x, dim=FIXED_DIM, keepdim=True)
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.
- 10d ago First seen · 75 lines · 30 tokens per session scan A 24a5d41ffb6f
pypto-case-reduction-sum is a skill published in the GitHub repository mindspore-ai/akg (259 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 799 once invoked, about $0.0002 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
pypto-case-matmul-2d
A documented example of 2D matrix multiplication using loop blocking over the M dimension and handling leftover elements. Matrix multiplication combines rows and columns of number grids to produce a new grid.
pypto-case-reduction-sum
A small example of summing values along one axis of a three-dimensional array while keeping the original number of dimensions.
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.