CtrlK
BlogDocsLog inGet started
Tessl Logo

firmware-analyst

Expert firmware analyst specializing in embedded systems, IoT security, and hardware reverse engineering.

38

Quality

36%

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/firmware-analyst/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

46%Scale 1-5

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

This skill provides a comprehensive firmware analysis reference with good executable commands, but suffers from significant verbosity by including extensive tool catalogs, vulnerability class descriptions, and ethical guidelines that Claude already knows. The workflow structure is reasonable but lacks validation checkpoints and feedback loops. The monolithic format with no supporting bundle files means all content is crammed into one document when much of it should be progressively disclosed.

Suggestions

Remove or drastically reduce sections Claude already knows: vulnerability class descriptions (command injection patterns, memory corruption types), ethical guidelines, and tool descriptions. Keep only tool names and non-obvious usage flags.

Add explicit validation checkpoints between workflow phases, e.g., 'Verify extraction succeeded: check that extracted directory contains expected filesystem structure before proceeding to Phase 3.'

Split the content into separate files: move tool references, reporting templates, emulation setup, and vulnerability checklists into the referenced `resources/implementation-playbook.md` or similar bundle files.

Add conditional branching in the workflow for common decision points, e.g., 'If entropy analysis shows high entropy throughout → firmware is likely encrypted → see decryption approaches before extraction.'

DimensionReasoningScore

Conciseness

The skill is significantly verbose, listing many tools, vulnerability classes, and templates that Claude already knows. Sections like 'Common Vulnerability Classes' with basic command injection examples, memory corruption descriptions, and the extensive tool lists are knowledge Claude possesses. The ethical guidelines section is also largely unnecessary padding.

2 / 5

Actionability

The skill provides concrete, executable bash commands throughout the workflow phases (binwalk, unsquashfs, QEMU setup, Firmadyne). The commands are copy-paste ready with proper flags and arguments. Minor gaps exist in some areas where guidance is more descriptive than executable (e.g., Ghidra instructions are vague).

4 / 5

Workflow Clarity

The four-phase workflow (Identification → Extraction → File System Analysis → Binary Analysis) provides a clear sequence, and there's a checklist at the end. However, there are no explicit validation checkpoints or feedback loops between phases — no 'verify extraction succeeded before proceeding' or 'if entropy is high, suspect encryption and handle differently' branching logic.

3 / 5

Progressive Disclosure

The content is a monolithic wall of information with no separation into supporting files. It references `resources/implementation-playbook.md` but no bundle files exist. The tool lists, vulnerability classes, reporting templates, and emulation setup could all be split into separate reference files. Everything is inlined in one large document.

2 / 5

Total

11

/

20

Passed

Description

27%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.

This description reads as a persona statement ('Expert firmware analyst') rather than a functional skill description. It names a domain but fails to describe any concrete actions the skill performs and completely lacks trigger guidance for when Claude should select it. The use of 'specializing in' is vague fluff that doesn't help Claude distinguish when to use this skill.

Suggestions

Replace the persona framing with concrete actions: e.g., 'Analyzes firmware binaries, identifies vulnerabilities in embedded systems, reverse engineers hardware protocols, and examines IoT device security.'

Add an explicit 'Use when...' clause with trigger terms: e.g., 'Use when the user mentions firmware analysis, binary reverse engineering, embedded device security, flash dumps, .bin/.hex files, or IoT vulnerability assessment.'

Include specific file types, tools, or techniques to improve trigger term coverage: e.g., 'disassembly, JTAG, SPI flash, UART, Ghidra, binwalk, .bin, .hex, .elf'.

DimensionReasoningScore

Specificity

Names the domain (firmware analysis, embedded systems, IoT security, hardware reverse engineering) but provides no concrete actions. 'Specializing in' is vague and doesn't describe what the skill actually does.

2 / 5

Completeness

The 'what' is extremely vague (no concrete actions described, only domain expertise claimed), and there is no 'when' clause at all. It reads as a persona description rather than a skill description.

1 / 5

Trigger Term Quality

Includes some relevant keywords like 'firmware', 'embedded systems', 'IoT security', and 'hardware reverse engineering' that users might mention, but misses common variations and specific terms like 'binary analysis', 'disassembly', 'flash dump', '.bin', '.hex', 'JTAG', 'SPI'.

3 / 5

Distinctiveness Conflict Risk

The combination of firmware, embedded systems, IoT, and hardware reverse engineering narrows the domain somewhat, but the lack of specific actions means it could overlap with general security analysis or reverse engineering skills.

3 / 5

Total

9

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

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.