Borrowing it
Nothing to install: this file belongs to SensorsIot/Embedded-AI-Harness. 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/SensorsIot/Embedded-AI-Harness/main/.claude/skills/testbench-integration/SKILL.mdgit clone --depth 1 https://github.com/SensorsIot/Embedded-AI-HarnessWrote 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/sensorsiot/embedded-ai-harness/testbench-integration)<a href="https://agentmods.dev/skills/sensorsiot/embedded-ai-harness/testbench-integration"><img src="https://agentmods.dev/badge/skills/sensorsiot/embedded-ai-harness/testbench-integration/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/sensorsiot/embedded-ai-harness/testbench-integration"><img src="https://agentmods.dev/badge/skills/sensorsiot/embedded-ai-harness/testbench-integration.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 | $0.00095 | $0.03523 |
| Opus 5 | $0.00048 | $0.01761 |
| Sonnet 5 | $0.00019 | $0.00705 |
| Haiku 4.5 | $0.00010 | $0.00352 |
Grade A, and why
testbench-integration 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ESP32 Testbench Integration
This is a procedure. When triggered, read the project's existing FSD, integrate the firmware with the testbench infrastructure — each module only when the FSD requires it (UDP logging always; OTA, BLE command handling, provisioning per scope; strategic log messages always), then write the operational, testing, and appendix chapters into the FSD.
Prerequisite: The project must already have an FSD with at least a System
Overview and Functional Requirements section. Use the define skill first
to generate one from a rough description if needed.
The testbench provides the test infrastructure. This skill adds both the firmware integration (modules the testbench needs to interact with the device) and the FSD documentation (operational guide, test plan, troubleshooting).
FSD Document Structure
This skill operates on FSDs produced by the define skill, which uses the
layer-grouped "Parts" scheme (see define/references/canonical-fsd-structure.md).
Chapter numbers are dynamic, so locate chapters by role/title, not by a fixed
number:
# <Project Name> — FSD
## System Overview ← front matter, read-only
## System Architecture (§2.4 Component Layering) ← front matter, read-only
## Implementation Phases ← front matter, read-only
## Risks, Assumptions & Dependencies ← front matter, read-only
# Part A — Application Logic (L2) ← one chapter per feature; read-only
# Part B — Interfaces (L1) ← one chapter per interface; read-only
# Part C — Foundation / Transport (L0)
# Part D — Cross-cutting Concerns
# Part E — Operations & Verification
## Operational Procedures ← REPLACED by this skill (testbench operations)
## Verification & Validation ← REPLACED by this skill (testbench test cases)
## Appendices ← testbench logging strategy + constants appended
There is no global Functional Requirements or Interface Specifications section — requirements live in each component chapter, and each interface is its own L1 chapter under Part B. This skill reads the front matter and component chapters (to extract features, phases, interfaces, constants) without modifying them, and replaces the Operational Procedures and Verification & Validation chapters under Part E (and appends to Appendices).
What ships with it
2 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 · 313 lines · 95 tokens per session scan A 66597a5ca0fd
testbench-integration is a skill published in the GitHub repository SensorsIot/Embedded-AI-Harness (173 stars, last pushed 28d ago), licensed MIT. It adds 95 tokens to every session and 3,523 once invoked, about $0.0005 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
ea-skill
An AI-assisted workflow for developing and testing embedded-device software. Embedded software runs on hardware such as microcontrollers, and the workflow covers project setup, feature work, tests, device programming, debugging, verification, and records.
m5stack-cap-lora-1262
Hardware reference and firmware helper for the M5Stack Cap LoRa-1262 (SKU U214) — a snap-on cap for the Cardputer Adv (K132-Adv) and CardputerZero that carries a Semtech SX1262 sub-GHz LoRa radio (868–923 MHz, +22 dBm TX, external RP-SMA antenna) and an ATGM336H-6N GNSS receiver (GPS/QZSS/BeiDou/Galileo/GLONASS, UART…
new-device-skill
Build or update an M5Stack hardware skill in this marketplace — a Controller (a board that runs firmware, like Core2 or AtomS3), a Unit (a peripheral you drive from a Controller, like a ToF sensor or a relay), or a Chip (an Espressif SoC capability layer, like esp32-c6). Use whenever adding a new board/unit/chip to…
m5stack-tab5
Hardware reference and development helper for the M5Stack Tab5 (product code C145) — an ESP32-P4-based 5" touchscreen IoT/industrial terminal with an ESP32-C6 wireless co-processor, MIPI-DSI display, MIPI-CSI camera, ES8388 audio codec, BMI270 IMU, RX8130CE RTC, RS485, and a removable NP-F550 battery. Use this skill…
embedded-verification
Use after implementation complete - runs build-flash-monitor loop, verifies runtime behavior, no completion claims without fresh evidence.
modelsim
An HDL simulation guide for ModelSim and QuestaSim, tools that test Verilog or VHDL hardware designs before they run on an FPGA.