arm-cortex-expert

Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD).

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-arm-cortex-expert/SKILL.md

Quality

Content

60%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.

The body delivers high-value, domain-specific embedded guidance with mostly executable code patterns and a clear workflow, but it is undermined by generic template boilerplate and a monolithic structure with a broken external reference. It reads as a reference document crammed into SKILL.md rather than a lean overview pointing to bundle files.

Suggestions

Move the deep-dive sections (memory barriers, DMA/cache coherency, hardfault debugging, architecture table) into reference files under references/ and keep SKILL.md as a lean overview with clearly signaled one-level-deep links.

Fix or remove the broken 'resources/implementation-playbook.md' reference — the file does not exist in the bundle, and the path does not match the conventional references/ directory.

Delete the circular 'Use this skill when / Do not use this skill when' boilerplate and the generic 'Instructions' section; they restate the skill name without adding guidance, and replace the Cortex-M architecture table with a pointer to ARM documentation.

Dimension	Reasoning	Score
Conciseness	The safety-critical sections are genuinely non-obvious and token-worthy (M7 weak ordering, 32-byte cache-line alignment, W1C, per-platform gotchas), but the body is padded with circular boilerplate ('Working on @arm-cortex-expert tasks or workflows', a generic 'Instructions' section) and a Cortex-M architecture differences table that Claude already knows.	3 / 5
Actionability	Mostly concrete and executable: complete snippets for Rust statics/atomics, W1C register clearing, BASEPRI masking, and named platform-specific SPI APIs. Minor gaps — the mmio_read()/mmio_write() helpers are named but never defined, and the SPI driver 'example' describes a pattern rather than showing code.	4 / 5
Workflow Clarity	The 6-step Workflow (Clarify → Design → Implement → Validate → Optimize → Iterate) is clearly sequenced and includes a validate step plus a hardware-feedback iterate step. Checkpoints are implicit rather than explicit verification actions (no 'compile and flash', no 'verify on logic analyzer'), keeping it below a 5.	4 / 5
Progressive Disclosure	A ~300-line monolithic body inlines deep reference material (barrier patterns, DMA coherency, hardfault debugging, architecture tables) that belongs in separate files, and its sole external pointer — 'open resources/implementation-playbook.md' — is buried in the boilerplate Instructions section and does not exist in the bundle.	2 / 5
	Total	13 / 20 Passed

Description

65%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 specific and distinctive within a well-defined embedded niche, using natural platform keywords users would say. Its main weakness is the complete absence of a 'when to use' trigger clause and the lack of enumerated concrete capabilities, both of which cap completeness and specificity at the midpoint.

Suggestions

Add an explicit trigger clause, e.g. 'Use when writing or debugging firmware, peripheral drivers (I2C/SPI/UART/DMA), or hardfault handlers for ARM Cortex-M MCUs, or when the user mentions Teensy, STM32, nRF52, or SAMD.'

Enumerate 2-4 concrete actions (e.g. register-level driver implementation, DMA/cache coherency handling, hardfault debugging, FreeRTOS/Zephyr integration) instead of the generic 'firmware and driver development'.

Include common variation terms like 'bare-metal', 'embedded', and 'RTOS' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain clearly ('firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD)') with 1-2 concrete action categories (firmware development, driver development), but never enumerates specific capabilities like SPI/I2C driver implementation, hardfault debugging, DMA setup, or RTOS integration that the body actually covers.	3 / 5
Completeness	Has a clear 'what' (specialized firmware/driver development for ARM Cortex-M) but no 'Use when...' clause or equivalent trigger guidance; per the rubric guideline a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Good natural keyword coverage — 'firmware', 'driver development', 'ARM Cortex-M', 'Teensy', 'STM32', 'nRF52', 'SAMD' are all phrases users would naturally say. A few common variations are missing ('bare-metal', 'embedded', 'FreeRTOS', 'Zephyr', 'microcontroller' spelled out).	4 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers — the named MCU families (Teensy, STM32, nRF52, SAMD) and 'ARM Cortex-M' make it highly unlikely to fire for unrelated skills, with minimal overlap risk against general firmware or Linux-embedded skills.	5 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: boisenoise/skills-collections
Path: skills/antigravity-arm-cortex-expert/SKILL.md
Commit: 690de8f

Reviewed: 4 hours ago

Table of Contents

Discovery Implementation Validation

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.