CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

56

Quality

63%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/arm-cortex-expert/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 is a technically rich, well-organized reference with concrete executable code patterns for ARM Cortex-M firmware work, but it carries generic templated boilerplate with un-substituted placeholders, lacks explicit validation checkpoints in its workflow, and inlines reference material that could be split into bundle files.

Suggestions

Remove or replace the generic 'Use this skill when / Do not use this skill when / Instructions' boilerplate and the un-substituted '@arm-cortex-expert' placeholders with skill-specific guidance.

Add explicit validation/feedback checkpoints to the Workflow (e.g. compile + static-analysis gate after Implement, hardware-in-the-loop verify after Validate, with a fix-and-retry loop) rather than a descriptive 'Validate' step.

Split large reference blocks (the Cortex-M architecture-difference table, per-platform gotchas, and the full SPI driver example) into separate one-level-deep files under references/ with clearly signaled links from SKILL.md.

DimensionReasoningScore

Conciseness

The technical reference is dense and assumes competence (no basic-concept explanations), but the generic boilerplate 'Use this skill when / Do not use this skill when / Instructions' sections and un-substituted '@arm-cortex-expert' template placeholders add padding that could be trimmed, landing it at 3 rather than 4.

3 / 5

Actionability

Provides concrete, mostly copy-paste-ready code in both C/C++ and Rust (e.g. `__DMB()`/`__DSB()` wrappers, `__attribute__((section(".dtcm.bss")))` placement, `AtomicBool`/`Mutex<RefCell<>>` patterns, W1C register handling), with only minor gaps such as the SPI example being a pattern outline rather than a full executable driver.

4 / 5

Workflow Clarity

A sequenced 6-step Workflow is present (Clarify → Design → Implement → Validate → Optimize → Iterate), but the 'Validate' step is only descriptive ('example usage + notes on timing') with no hard validation checkpoint or fix-and-retry feedback loop for risky register/DMA operations, so checkpoints remain implicit.

3 / 5

Progressive Disclosure

The body is well-sectioned with clear headers, but it is a single ~294-line monolithic file with no bundle files or external references, inlining substantial reference material (the architecture-difference table, per-platform gotchas, full SPI example) that could live in separate one-level-deep files.

3 / 5

Total

13

/

20

Passed

Description

70%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 clearly conveys a distinct, well-scoped embedded-firmware niche with strong natural trigger keywords, but it reads as a persona/role statement rather than an action list and lacks an explicit 'Use when...' trigger clause, capping completeness at 3.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger situations, e.g. 'Use when writing firmware or peripheral drivers for ARM Cortex-M MCUs (Teensy, STM32, nRF52, SAMD), or debugging DMA/cache-coherency, interrupt, or memory-barrier issues.'

Lead with concrete actions the skill performs (e.g. 'Implements and reviews firmware and peripheral drivers...') rather than persona phrasing like 'Senior embedded software engineer' and 'Decades of experience', which reads as fluff.

Include a few more natural synonyms users might say (e.g. 'embedded', 'MCU', 'microcontroller', 'bare-metal') to round out trigger-term coverage.

DimensionReasoningScore

Specificity

Lists several concrete specialty areas — 'firmware and driver development', 'memory barriers', 'DMA/cache coherency', 'interrupt-driven I/O', and 'peripheral drivers' across named platforms — but the persona framing ('Senior embedded software engineer', 'Decades of experience') is role-description rather than a clean action list, leaving it just below the comprehensive-action anchor at 5.

4 / 5

Completeness

The 'what' is clearly stated (firmware/driver development for ARM Cortex-M with named expertise areas), but there is no explicit 'Use when...' trigger clause — the 'when' is only weakly implied, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Good natural-keyword coverage users would actually say — 'firmware', 'driver', 'ARM Cortex-M', 'Teensy', 'STM32', 'nRF52', 'SAMD', 'memory barriers', 'DMA' — but a few common variations (e.g. 'embedded', 'MCU', 'microcontroller' synonyms) are thin, so it sits at 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

The niche is sharply defined — ARM Cortex-M firmware/drivers for specific chip families (Teensy, STM32, nRF52, SAMD) — making it clearly distinguishable from other skills with minimal conflict risk.

5 / 5

Total

16

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
rmyndharis/antigravity-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.