CtrlK
BlogDocsLog inGet started
Tessl Logo

embedded-iot-mentor

Mentor for embedded and IoT hardware projects. Helps select MCUs, dev boards, and toolchains, decides where sensor readings end up (phone, PC, dashboard, or alert), and gives time/cost estimates and a phased build plan from breadboard MVP to production PCB. Use when the user mentions embedded, IoT, microcontroller, ESP32, STM32, Arduino, Raspberry Pi Pico, firmware, PCB, KiCad, EasyEDA, PlatformIO, MQTT, Home Assistant, ESPHome, Grafana, an IoT dashboard, seeing sensor data on a phone, or asks for hardware tool recommendations, project planning, or cost/time estimates for an electronics project.

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, highly actionable instruction skill that assumes Claude's competence and splits detail sensibly into one real reference. It earns top marks on actionability and progressive disclosure, with only minor conciseness redundancy and the absence of explicit feedback loops holding workflow clarity and conciseness at 4.

Suggestions

Consolidate the overlap between 'Core style rules' and 'Anti-Patterns' — several anti-patterns (buy-ability, firmware-reuse-first, proxy measurement) restate core rules verbatim; cross-reference instead of repeating to reclaim tokens.

Tighten the 11-item clarifying-questions list by marking which are mandatory vs. situational, addressing the 'wall of ten questions turns people away' risk the skill itself flags.

Add one explicit validation checkpoint in the recommendation process — e.g., 'confirm the chosen part is orderable in the user's country before listing it' — to turn the implicit buy-ability check into a named feedback step.

DimensionReasoningScore

Conciseness

Largely lean and assumes Claude's competence (no explanations of what an MCU or Wi-Fi is), with tables and concrete rules throughout, but the 'Anti-Patterns' section restates several 'Core style rules' (buy-ability, firmware-reuse-first) and the 11-item clarifying-questions list could be tightened — minor trimming available.

4 / 5

Actionability

Highly actionable instruction guidance: named parts and boards (ESP32 DevKit, nRF52, Pico W), named ready-made firmware (ESPHome, Tasmota, WLED, Meshtastic), named tools (KiCad, EasyEDA, PlatformIO), and decision tables with primary+alternative+trade-off plus a concrete worked example (DS18B20/SHT31, Home Assistant, Nabu Casa tunnel).

5 / 5

Workflow Clarity

A clear sequenced process exists ('When called with no project details' 1-4 and 'Recommendation process' steps 1-6) with checkpoints like MVP exit criteria, 'stop after MVP unless asked', and 'Drop it when' output conditions, but there are no explicit validate-then-fix feedback loops, so it sits just below the top anchor.

4 / 5

Progressive Disclosure

SKILL.md is a well-structured overview (decision tables as the fast path) with a single one-level-deep, clearly-signaled reference to the verified-real 'references/hardware-selection.md' for datasheet-level facts, with explicit guidance on when to cite it; content is appropriately split and easy to navigate.

5 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: third-person voice, concrete multi-part capabilities, an explicit 'Use when' clause, and a dense set of natural trigger terms covering synonyms, tools, and file formats. No fluff or over-claims; every clause carries trigger value.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the domain — 'Helps select MCUs, dev boards, and toolchains, decides where sensor readings end up (phone, PC, dashboard, or alert), and gives time/cost estimates and a phased build plan' — giving comprehensive coverage of what the mentor does.

5 / 5

Completeness

Explicitly answers both 'what' (select hardware, route sensor data, give estimates and a phased plan) and 'when' via a concrete 'Use when the user mentions ... or asks for hardware tool recommendations, project planning, or cost/time estimates' trigger clause.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms and product names a user would actually say — 'ESP32, STM32, Arduino, Raspberry Pi Pico, firmware, PCB, KiCad, EasyEDA, PlatformIO, MQTT, Home Assistant, ESPHome, Grafana' — plus natural phrases like 'seeing sensor data on a phone'.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear embedded/IoT hardware niche with highly specific triggers (ESP32, STM32, KiCad, ESPHome, PCB) that are unlikely to fire for unrelated skills, keeping conflict risk minimal.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
alirezarezvani/claude-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.