Borrowing it
Nothing to install: this file belongs to suharvest/sensecraft-solutions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/suharvest/sensecraft-solutions/main/.agents/skills/author-solution/SKILL.mdgit clone --depth 1 https://github.com/suharvest/sensecraft-solutionsWrote 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/suharvest/sensecraft-solutions/author-solution)<a href="https://agentmods.dev/skills/suharvest/sensecraft-solutions/author-solution"><img src="https://agentmods.dev/badge/skills/suharvest/sensecraft-solutions/author-solution/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/suharvest/sensecraft-solutions/author-solution"><img src="https://agentmods.dev/badge/skills/suharvest/sensecraft-solutions/author-solution.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 | $0.00096 | $0.07082 |
| Opus 5 | $0.00048 | $0.03541 |
| Sonnet 5 | $0.00019 | $0.01416 |
| Haiku 4.5 | $0.00010 | $0.00708 |
Grade A, and why
author-solution scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl/代码示例不要放在介绍页前半段;放到 guide.md 的部署完成、接口详情或验证步骤里。 How it starts
The opening of the file, as written. The whole thing — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Author Solution Skill
从原始资料(Wiki / 文档 / Git 仓库)创作一个符合 SenseCraft 方案契约的一键部署方案。
调用方式
/author-solution https://wiki.seeedstudio.com/xxx smart_factory
/author-solution ./raw_materials/ my_solution
/author-solution https://github.com/xxx/xxx # 自动生成 solution_id
$ARGUMENTS 包含:资料来源(URL 或本地路径)+ 可选的 solution_id。如果用户指定了某个 preset,只复现该 preset。
所有 device YAML 字段、guide.md Step/Target 语法、docker_deploy 派生规则等机器可读契约以 spec/CONTRACT.md 为唯一权威来源(配套 spec/*.json schema)。本 skill 只讲创作流程;遇到字段细节一律查 CONTRACT。
核心理念
- 目标用户:解决方案商(无开发能力)
- 最小工作单元:preset(而非整个 solution)
- 最简路径:去掉所有非必要步骤,让用户用最少操作完成部署
- 预配置优先:能提前配好的全部预配好,用户只需做「连接」和「点击」
- 部署 + 验证完整闭环:部署完不算完,要让用户立刻看到效果
每个 preset 必须至少有一个 verify 步骤(让用户立刻看到结果)。solutionctl validate 强制检查 verify step 存在。solution 类用 type=web_dashboard;technical 类用交互式 verify(image_predict / text_chat / voice_chat / http_debug 等)。可用的 verify/step 类型见 spec/CONTRACT.md「Deployer capabilities」表。
- 极少数纯硬件/纯云方案没有本地 dashboard 可指 → 在该 preset 上标
verify_exempt: true豁免(CI 会接受)。
选择 verify 验证方式 + 能力不够怎么拓展
(a) 怎么选 —— 看部署出来的东西是什么,对号入座:
| verify 类型 | 当部署的是… |
|---|---|
web_dashboard |
一个网页 UI / 看板(Grafana、Web 应用)—— 本质是「打开这个 URL」 |
image_predict |
视觉模型 —— 传一张图、看预测结果 |
text_chat |
LLM / 聊天 —— 输入 prompt、看回复 |
image_text_chat |
视觉语言模型(VLM)—— 图 + 文字 prompt |
image_text_to_image |
文生图 / 图生图 —— 输入提示词(或图),看生成的图 |
voice_chat |
语音助手 —— 说话、听 ASR/TTS |
robot_inspect |
机器人 / 机械臂 —— 实时观测面板,轮询机器人主容器的 /observation 端点显示关节/传感器状态 |
http_debug |
其他任意 HTTP 接口 —— 发请求看响应的通用调试器(通用兜底) |
任意步加 verify=true |
把一个非标准步骤(如手动 demo)标成 verify 步 |
这张是常用速查;权威完整清单(含每个类型的配置字段)以
spec/CONTRACT.md「Deployer capabilities」表为准。
(b) 没有合适类型怎么拓展(按优先级,前 3 条都不改引擎就能做):
- 先用通用兜底:服务暴露 HTTP API 但不是 chat/vision → 用
http_debug(任意请求/响应);只是要打开个页面 →web_dashboard(任意 URL)。这俩能覆盖绝大多数「没有专门类型」的情况。 - 自定义校验 / 健康检查:在 device YAML 的
actions.before/actions.after写run:脚本(设备上跑任意 shell,可sudo: true)—— 做部署前预检、部署后健康检查。参考solutions/gpt_oss_20b/devices/jetson_deploy.yaml的 "Validate Jetson runtime"。这是不改引擎就能拓展的主力。 字段名(actions/before/after/run/sudo)以spec/device.schema.json为准。 - 标记任意步:
{#id type=... verify=true}把任意步骤当成 verify 步。 - 以上都不满足(需要一个全新的交互式 verify 类型 / 新 UI 控件):这是引擎(闭源)侧能力,本仓库加不了 —— 要么用插件原型化(见
docs/plugin-development.md),要么提一个能力需求 issue说明你要的交互形态。
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 · 487 lines · 96 tokens per session scan A 3072dfd8ca85
author-solution is a skill published in the GitHub repository suharvest/sensecraft-solutions (2 stars, last pushed today), licensed Apache-2.0. It adds 96 tokens to every session and 7,082 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.