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).

68

1.19x
Quality

53%

Does it follow best practices?

Impact

93%

1.19x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/arm-cortex-expert/SKILL.md

The canonical home for this skill is arm-cortex-expert in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

46%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 contains genuinely valuable, domain-specific embedded guidance and some executable code, but it is over-long with redundant sections, its headline example is descriptive rather than complete code, its validation step is vague, and it fails progressive disclosure by inlining everything and pointing to a non-existent reference file.

Suggestions

Split the detailed reference material (architecture comparison table, platform gotchas, safety-critical barrier/DMA patterns) into files under references/ and replace the inlined bulk with one-level-deep links, fixing the broken 'resources/implementation-playbook.md' reference.

Replace the descriptive SPI 'Example' bullets with a complete, compilable driver skeleton (init, ISR, transaction API, example usage) to match the stated 'full solutions' objective.

Add a concrete validation checkpoint to the Workflow (e.g. build command, a compile-check or hardware-in-loop test step) with an explicit validate → fix → re-validate loop.

DimensionReasoningScore

Conciseness

Mostly efficient domain-specific guidance (DMA alignment, W1C, barriers, platform gotchas), but the ~290-line body has redundancy — Role & Objectives, Knowledge Base, and Core Competencies restate overlapping material — and over-explains concepts Claude already knows (NVIC priority basics, FPU lazy stacking), so it sits at 'mostly efficient but could be tightened' rather than lean.

3 / 5

Actionability

Several real executable blocks exist (W1C read/write, BASEPRI critical section, Rust atomic/Mutex patterns), but the headline SPI 'Example' section is descriptive bullets rather than code, the mmio_read/write/modify helpers are described but not shown, and no complete compilable driver is provided despite the 'complete, compilable firmware' objective — matching 'some concrete guidance but incomplete'.

3 / 5

Workflow Clarity

A 6-step Workflow is sequenced (Clarify → Design → Implement → Validate → Optimize → Iterate), but the validation step is vague ('example usage + notes on timing') with no concrete verification command or error-recovery feedback loop, placing it at 'steps listed but validation gaps; checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

All content is inlined into a single ~290-line SKILL.md with no bundle files present (no references/, scripts/, or assets/ directories), and the one external reference — 'resources/implementation-playbook.md' — does not exist (broken link), matching 'content that clearly belongs in separate files is inlined' despite the in-file section headers.

2 / 5

Total

11

/

20

Passed

Description

61%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 names a clear niche and concrete platforms with good natural keywords, but it omits any explicit 'when to use' trigger guidance and lists only minimal concrete actions. Adding a 'Use when...' clause with the platform names would lift both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when developing firmware or peripheral drivers for ARM Cortex-M MCUs (Teensy, STM32, nRF52, SAMD), or when the user mentions these platforms, I2C/SPI/UART drivers, DMA, or RTOS integration.'

List a few more concrete actions (e.g. 'writes register-level peripheral drivers, configures DMA and cache coherency, integrates FreeRTOS/Zephyr') to move specificity from 1-2 actions toward comprehensive coverage.

DimensionReasoningScore

Specificity

Names the domain ('firmware and driver development for ARM Cortex-M microcontrollers') and four concrete platforms (Teensy, STM32, nRF52, SAMD), but lists only one or two actions and is not comprehensive, fitting the 'names domain and 1-2 concrete actions' anchor rather than the 'several specific actions' level above.

3 / 5

Completeness

It clearly states what the skill does but contains no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 3 ('clear what but when is missing or only weakly implied').

3 / 5

Trigger Term Quality

Includes natural terms an embedded user would actually say — 'ARM Cortex-M', 'firmware', 'driver', 'Teensy', 'STM32', 'nRF52', 'SAMD' — giving good keyword coverage, but stops short of comprehensive synonyms/file-extension style coverage so it is not a 5.

4 / 5

Distinctiveness Conflict Risk

The specific platform list (Teensy, STM32, nRF52, SAMD) carves a clear niche with minor overlap risk against a generic embedded skill, but without explicit distinct triggers it is not a 5.

4 / 5

Total

14

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.