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.

72

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is embedded-iot-mentor in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

78%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-structured, actionable mentor skill with concrete decision tables and a worked example, scoring high on actionability and workflow clarity. The main gaps are mild repetition between the Core style rules and Anti-Patterns sections, and a referenced file (references/hardware-selection.md) that is cited but missing from the bundle.

Suggestions

Add the missing references/hardware-selection.md to the bundle, or remove the two citations to it and inline the needed power-budget arithmetic so no signaled reference dangles.

Trim the Anti-Patterns section so it does not restate rules already in 'Core style rules' (firmware-first, phone≠from-anywhere, regional buy-ability); keep only the distinct anti-patterns.

Add one concrete executable anchor (e.g. a PlatformIO init or a browser-flash command for ESPHome) so the toolchain guidance has a copy-paste starting point.

DimensionReasoningScore

Conciseness

Mostly efficient mentor guidance with concrete decision tables rather than concept explanations Claude already knows, but the Anti-Patterns section restates core style rules already covered above (firmware-first, phone/port-forward, regional buy-ability), adding mild repetition. Not 5 because of that duplicate framing; not 3 because the bulk of tokens are actionable, not padded.

4 / 5

Actionability

Highly concrete and specific for an instruction-only skill: named boards (ESP32 DevKit, nRF52, STM32 Nucleo), named tools (KiCad, PlatformIO, ESPHome, Meshtastic), decision tables, and a worked example with real parts (DS18B20, SHT31). Per the instruction-skill carve-out, absence of code is not penalized when guidance is this actionable and covers common cases.

5 / 5

Workflow Clarity

Clear sequenced process: clarify (one question at a time) → 6-step recommendation process → output-format table with 'cap' and 'drop it when' checkpoints and MVP 'exit criteria'. Not 5 because there are no explicit validate→fix→retry feedback loops, though that is largely appropriate for an advisory rather than destructive/batch skill.

4 / 5

Progressive Disclosure

The body signals a one-level-deep reference ('Datasheet-level facts ... live in references/hardware-selection.md') and is itself well-sectioned, but the referenced file is absent from the bundle (no references/ directory exists), so the signaled navigation is broken. Not 4 because a missing referenced file is more than a minor organization gap; not 2 because structure and signaling are otherwise present.

3 / 5

Total

16

/

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.

The description is exemplary: it states concrete capabilities, gives an explicit 'Use when' trigger list with natural synonyms and product names, and occupies a clear niche with low conflict risk. The only risk is mild verbosity from the long trigger enumeration, but that enumeration directly serves trigger quality.

DimensionReasoningScore

Specificity

Lists multiple concrete actions with comprehensive coverage: '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.' Not 4 because coverage is broad and specific rather than having minor gaps.

5 / 5

Completeness

Explicitly answers both 'what' (mentor that selects parts, routes data, estimates cost/time, plans phases) and 'when' via a 'Use when the user mentions...' clause with concrete trigger phrases. Clearly meets the top anchor on both axes.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including product names and synonyms: 'embedded, IoT, microcontroller, ESP32, STM32, Arduino, Raspberry Pi Pico, firmware, PCB, KiCad, EasyEDA, PlatformIO, MQTT, Home Assistant, ESPHome, Grafana'. Matches the anchor for full coverage of terms users actually say.

5 / 5

Distinctiveness Conflict Risk

Clear niche (embedded/IoT hardware) with distinctive triggers (specific MCUs, KiCad, ESPHome, Grafana) unlikely to fire for unrelated skills. Minimal conflict risk per the anchor.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

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.