CtrlK
BlogDocsLog inGet started
Tessl Logo

reverser-firmware

Router / IoT firmware extraction pipeline — unpack nested filesystems, locate web server, identify backdoor credentials.

59

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/reverser/firmware/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%Weight 40%Scale 1-3

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

The content is concise and well-organized into a clear pipeline, but later steps mix executable commands with pseudocode-style commentary and the workflow lacks any verification checkpoints for its batch extraction operations.

Suggestions

Replace comment-as-instruction and function-call notation in steps 3–6 with concrete, runnable commands (or clearly mark them as tool calls with their exact syntax).

Add validation checkpoints after risky steps — e.g., verify the squashfs-root was found before continuing, and confirm binwalk extraction succeeded before mapping /etc.

DimensionReasoningScore

Conciseness

The body is lean — numbered sections, tight code blocks, and prose like 'CGI binaries under www/cgi-bin/ are the highest-yield targets' with no padding or explanation of concepts Claude already knows, matching the lean-and-efficient anchor.

3 / 3

Actionability

Sections 1–2 give executable shell commands, but sections 3–5 rely on comment-as-instruction ('# For each: bin_identify + bin_strings'), function-call notation ('cve_by_package(...)'), and prose ('Look for:'), so guidance is concrete but not fully executable.

2 / 3

Workflow Clarity

The seven steps are clearly sequenced, but this batch/extraction workflow has no validation or verification checkpoints (e.g., confirm extraction succeeded, handle missing rootfs), which caps workflow clarity at 2 per the destructive/batch guidance.

2 / 3

Progressive Disclosure

The body is under 50 lines with no external bundle files needed and is organized into well-labeled numbered sections, satisfying the simple-skill allowance for a top score on progressive disclosure.

3 / 3

Total

10

/

12

Passed

Description

67%Weight 40%Scale 1-3

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 is specific and occupies a distinct niche, but it omits an explicit 'Use when...' trigger clause and its keyword coverage is more jargon-heavy than naturally phrased, capping completeness and trigger quality at the mid level.

Suggestions

Add an explicit 'Use when ...' clause to the description (e.g., 'Use when extracting router or IoT firmware images, or when the user mentions binwalk, squashfs, or firmware backdoors').

Broaden trigger terms with natural phrasings users would actually say (e.g., 'router firmware', 'IoT device firmware', 'firmware backdoor') rather than only technical jargon.

DimensionReasoningScore

Specificity

Lists three concrete actions — 'unpack nested filesystems', 'locate web server', 'identify backdoor credentials' — matching the anchor for multiple specific concrete actions, not the narrower domain-only level below.

3 / 3

Completeness

It clearly states what the skill does but has no 'Use when...' clause in the description itself; trigger guidance lives only in metadata.when_to_use, which per the rubric caps completeness at 2.

2 / 3

Trigger Term Quality

'Router / IoT firmware extraction' are relevant natural terms, but coverage leans on jargon ('nested filesystems', 'backdoor credentials', 'binwalk') and misses common variations, so it is not the broad level-3 coverage.

2 / 3

Distinctiveness Conflict Risk

'Router / IoT firmware extraction' is a clear, narrow niche unlikely to trigger for unrelated skills, matching the clear-niche anchor rather than the overlapping level below.

3 / 3

Total

10

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
PurpleAILAB/Decepticon
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.