CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

firmware-analyst

Expert firmware analyst specializing in embedded systems, IoT security, and hardware reverse engineering. Masters firmware extraction, analysis, and vulnerability research for routers, IoT devices, automotive systems, and industrial controllers. Use for firmware security audits, IoT penetration testing, or embedded systems research.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/firmware-analyst/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 delivers strong, concrete command-level guidance organized into a clear phase-based workflow, and the ethical guardrails are appropriate for this domain. However, it carries generic boilerplate sections, lacks explicit validation checkpoints and error-recovery loops within the workflow, and inlines ~310 lines of content (reporting templates, vulnerability catalogs, tool lists) that should be split into reference files for progressive disclosure.

Suggestions

Remove the generic 'Use this skill when', 'Do not use this skill when', and 'Instructions' boilerplate sections — they duplicate the frontmatter description and add no firmware-specific value.

Add explicit per-phase validation checkpoints and failure paths (e.g., 'if binwalk finds no signatures, check entropy output for encryption; if encrypted, attempt key extraction or hardware SPI dump') to create feedback loops in the workflow.

Split the reporting template, vulnerability-class catalogs, and tool proficiency lists into references/ files (e.g., REPORTING.md, VULNERABILITIES.md, TOOLS.md) and link to them from SKILL.md so the always-loaded context stays lean.

DimensionReasoningScore

Conciseness

The core is a dense, useful command reference, but generic filler sections ('Instructions: Clarify goals, constraints, and required inputs... Apply relevant best practices') add no skill-specific value, and one-line descriptions of tools Claude already knows (Ghidra 'Multi-architecture disassembly', IDA Pro 'Commercial disassembler', QEMU) could be trimmed — matching 'mostly efficient but includes some unnecessary explanation'.

3 / 5

Actionability

Mostly executable, copy-paste-ready commands cover common cases (binwalk -eM, unsquashfs, jefferson, QEMU chroot, firmadyne script pipeline), with only minor gaps: the placeholder 'wget http://vendor.com/firmware/update.bin' URL and comment-only Ghidra loading guidance keep it below fully-executable anchor 5.

4 / 5

Workflow Clarity

The Phase 1-4 workflow (Identification, Extraction, File System Analysis, Binary Analysis) is clearly sequenced, but validation checkpoints are only implicit (entropy analysis, the end-of-document checklist) and there are no feedback loops or error-recovery steps (e.g., what to do if binwalk identifies nothing or entropy indicates encryption), matching anchor 3 rather than anchor 4's 'most checkpoints present'.

3 / 5

Progressive Disclosure

Section headers organize the ~310-line body well, but everything is inlined in a single file with zero reference files — the reporting template, vulnerability-class catalogs, and tool proficiency lists clearly belong in separate reference files, fitting anchor 3's 'content that should be separate is inline' rather than anchor 2 (which requires minimal structure) or anchor 4 (which requires mostly-appropriate placement across files).

3 / 5

Total

13

/

20

Passed

Description

87%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.

A strong description: it uses third-person voice, states concrete capabilities with named device targets, and includes an explicit 'Use for...' trigger clause covering the main use cases. Keyword coverage is good though it misses a few natural synonyms, and capability coverage has minor gaps relative to the full body content.

DimensionReasoningScore

Specificity

Lists several concrete actions ('firmware extraction, analysis, and vulnerability research') across named device classes ('routers, IoT devices, automotive systems, and industrial controllers'), but 'analysis' is generic and coverage gaps exist (emulation, reporting, hardening), matching anchor 4 rather than the comprehensive anchor 5.

4 / 5

Completeness

Clearly answers 'what' (extraction, analysis, vulnerability research with concrete targets) and 'when' via an explicit 'Use for firmware security audits, IoT penetration testing, or embedded systems research' trigger clause with concrete phrases, matching anchor 5; anchor 4 would require a weaker or less specific 'when'.

5 / 5

Trigger Term Quality

Good natural keyword coverage ('firmware security audits', 'IoT penetration testing', 'embedded systems research', 'hardware reverse engineering'), but common variations like 'firmware analysis', 'dump/extract firmware', or 'pentest' are missing, so it fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The firmware/embedded/IoT security niche is clear with distinct triggers (routers, automotive systems, industrial controllers), making conflict with other skills minimal and matching anchor 5; only trivial overlap with generic security-testing skills keeps it from being ambiguous.

5 / 5

Total

18

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

rmyndharis/antigravity-skills

Path

skills/firmware-analyst/SKILL.md

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.