arm-cortex-expert

Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and peripheral drivers.

Quality

31%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent/skills/arm-cortex-expert/SKILL.md

Quality

Discovery

32%

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

This description reads more like a resume or persona description than a skill description. It focuses on credentials ('decades of experience', 'deep expertise') rather than concrete actions Claude will perform. The complete absence of a 'Use when...' clause and the first-person framing ('Senior embedded software engineer') significantly weaken its utility for skill selection.

Suggestions

Add an explicit 'Use when...' clause with trigger scenarios like 'Use when the user needs help with microcontroller firmware, embedded C code, peripheral drivers, or asks about Teensy/STM32/nRF52 development'

Replace the persona/credential framing with action-oriented language: 'Develops and debugs firmware for ARM Cortex-M microcontrollers, writes peripheral drivers, optimizes memory usage, handles DMA and interrupt configurations'

Include simpler trigger terms users might naturally say: 'embedded code', 'microcontroller programming', 'hardware drivers', 'bare metal', '.ino files', 'Arduino-style development'

Dimension	Reasoning	Score
Specificity	Names the domain (embedded/firmware) and lists technical areas (memory barriers, DMA/cache coherency, interrupt-driven I/O, peripheral drivers), but these are expertise areas rather than concrete actions the skill performs. No action verbs like 'writes', 'debugs', 'optimizes' are used.	2 / 3
Completeness	Describes expertise areas (what the persona knows) but lacks any 'Use when...' clause or explicit trigger guidance. Does not clearly answer 'what does this do' in terms of actions, and completely missing 'when should Claude use it'.	1 / 3
Trigger Term Quality	Includes relevant technical terms users might mention (Teensy, STM32, nRF52, SAMD, ARM Cortex-M, firmware, DMA), but these are fairly technical. Missing common user phrases like 'microcontroller code', 'embedded C', 'hardware programming', or simpler trigger terms.	2 / 3
Distinctiveness Conflict Risk	The specific microcontroller families (Teensy, STM32, nRF52, SAMD) and ARM Cortex-M focus provide some distinctiveness, but 'firmware and driver development' is broad enough to potentially overlap with other embedded or systems programming skills.	2 / 3
	Total	7 / 12 Passed

Implementation

29%

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

This skill has excellent structure and progressive disclosure with clear links to sub-skills for advanced topics. However, it severely lacks actionability—there are no code examples, concrete commands, or executable guidance despite being for firmware/driver development. The instructions are abstract and the workflow guidance is missing entirely.

Suggestions

Add at least one complete, compilable code example demonstrating a common task (e.g., basic I2C driver initialization with ISR setup)

Replace vague instructions ('Apply relevant best practices') with concrete step sequences for common workflows like 'Setting up a new peripheral driver'

Include a quick-start section with executable code showing platform-specific initialization (e.g., Teensy 4.x SPI DMA setup)

Add validation checkpoints for safety-critical operations mentioned in the skill (e.g., 'Verify DMA buffer alignment before transfer')

Dimension	Reasoning	Score
Conciseness	The skill contains some unnecessary verbosity in section headers and organizational framing (e.g., emoji headers, 'Use this skill when' boilerplate). The knowledge base and competencies lists are reasonably efficient but could be tightened.	2 / 3
Actionability	The skill provides no concrete code examples, commands, or executable guidance. It describes capabilities and topics at a high level but lacks any copy-paste ready implementations or specific instructions for actual tasks.	1 / 3
Workflow Clarity	No clear workflows or step sequences are provided. The instructions section is vague ('Clarify goals', 'Apply relevant best practices') without concrete steps. For a skill involving safety-critical embedded development, the absence of validation checkpoints is a significant gap.	1 / 3
Progressive Disclosure	The skill effectively uses progressive disclosure with a clear overview and well-signaled one-level-deep references to sub-skills for detailed topics (memory barriers, DMA coherency, etc.). Navigation to specialized content is straightforward.	3 / 3
	Total	7 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: Dokhacgiakhoa/antigravity-ide
Commit: 332e58b

Reviewed: 17 days 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.