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 grasscaograss/AwesomeWeldoneSkills --skill coarse-compensation-fitgit clone --depth 1 https://github.com/grasscaograss/AwesomeWeldoneSkillsWrote 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/grasscaograss/awesomeweldoneskills/coarse-compensation-fit)<a href="https://agentmods.dev/skills/grasscaograss/awesomeweldoneskills/coarse-compensation-fit"><img src="https://agentmods.dev/badge/skills/grasscaograss/awesomeweldoneskills/coarse-compensation-fit/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/grasscaograss/awesomeweldoneskills/coarse-compensation-fit"><img src="https://agentmods.dev/badge/skills/grasscaograss/awesomeweldoneskills/coarse-compensation-fit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00147 | $0.01559 |
| Opus 5 | $0.00073 | $0.00779 |
| Sonnet 5 | $0.00029 | $0.00312 |
| Haiku 4.5 | $0.00015 | $0.00156 |
Grade A, and why
coarse-compensation-fit 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 11d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
粗定位补偿拟合
目标
根据点云点与世界点对照数据,拟合适合当前项目的粗定位补偿参数,并给出:
- 推荐补偿模型
- 配置参数
- 参数含义
- 误差统计
- 外推稳定性分析
当前项目补偿链路
当前粗定位链路:
- 相机原始结果
VisionPositionCompensation:相机坐标系 → 世界坐标系GantryQuadraticCorrection:龙门补偿(当前代码里实际是位置相关旋转+平移的 9 参数模型)
当前代码模型位于:
src/Weldone.Application/Coarse/GeneralCoarsePositioningAppService.cssrc/Weldone.Domain/Settings/CoarseVisionSetting.cs
当前 GantryQuadraticCorrection 的 9 参数含义:
[0] a0: 旋转角基准值(rad)[1] a1: 旋转角随X变化的斜率(rad/mm)[2] a2: 旋转角随Y变化的斜率(rad/mm)[3] b0: X平移基准值(mm)[4] b1: X平移随X变化的斜率[5] c0: Y平移基准值(mm)[6] c1: Y平移随X变化的斜率[7] c2: Y平移随Y变化的斜率[8] dz: Z平移常量(mm)
补偿公式:
theta(x,y) = a0 + a1*x + a2*y
tx(x) = b0 + b1*x
ty(x,y) = c0 + c1*x + c2*y
z' = z + dz
补偿矩阵:
Rz(theta) + [tx, ty, dz]
输入数据格式
优先读取用户提供的桌面文本文件,常见格式:
实际位置:
P1: x, y, z
...
点云中的点:
P1: x, y, z
...
或:
点云变换点1: x,y,z
世界点1: x,y,z
需要保证点号一一对应。
工作流程
第一步:读取数据
读取用户提供的文件,提取:
- 点云点
P[i] - 世界点
W[i]
第二步:基础诊断
必须先做以下分析:
- 逐点误差:
d = W - P - 误差分布:按 X 区域看 dX/dY/dZ
- 距离一致性检查:任意点对的 cloud_dist / world_dist 比值范围
判断原则:
- 如果距离比例严重异常(如 0.2、0.5 这类极端值),先提醒用户数据可能混了不同坐标系或异常点
- 如果距离比例稳定(如 0.9~1.02),可以进入拟合
第三步:至少比较以下三种模型
A. 单一刚体矩阵
误差模型:
dx = -theta*y + tx
dy = theta*x + ty
dz = 常量
输出:
- theta (deg)
- tx, ty, dz
- 等效 4x4 矩阵
- mean / max error
B. 位置相关旋转+平移(当前推荐模型)
误差模型:
theta(x,y) = a0 + a1*x + a2*y
tx(x) = b0 + b1*x
ty(x,y) = c0 + c1*x + c2*y
输出:
- 9 个参数
- 每个参数物理含义
- mean / max error
- 外推合理性(是否发散)
C. 线性仿射矩阵
矩阵元素随位置线性变化,用于和 B 对比。 如果 B 明显更好,优先推荐 B。
第四步:做外推稳定性测试
必须用一个“超出训练范围”的测试点做外推检查,例如用户当前关心的点,或者自己选一个边界外点。
检查内容:
- 输出位置偏移是否离谱
- 矩阵元素是否仍接近合理范围(对仿射模型)
- 是否存在明显发散
原则:
- 精度略高但外推会爆炸的模型,不推荐
- 精度略低但稳定的模型,更适合现场使用
第五步:给结论
结论必须包含:
- 推荐哪个模型
- 为什么推荐
- 参数列表
- 参数含义(尤其要说明工人主要调哪些参数)
- 如果需要,给出建议写入
CoarseVisionSetting.json的数组
输出模板
推荐模型
- 模型名:
- 原因:
误差对比
- A:mean / max
- B:mean / max
- C:mean / max
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.
- 11d ago First seen · 187 lines · 147 tokens per session scan A 5563d225f112
coarse-compensation-fit is a skill published in the GitHub repository grasscaograss/AwesomeWeldoneSkills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 147 tokens to every session and 1,559 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.