hardware-security

Use for authorized hardware and embedded interface security research including UART/JTAG discovery, debug pad triage, secure boot overview, and offline firmware extraction support.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/hardware-security/SKILL.md

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.

A concise, well-structured, safety-aware overview with good progressive disclosure and a verified reference file. It loses points on actionability and workflow clarity because the workflow reads as high-level directives rather than executable steps with inline validation checkpoints for its destructive-risk operations.

Suggestions

Convert the workflow checkboxes into concrete, executable actions (e.g. specific baud-rate probing commands, the exact USB-TTL wiring/connection steps, the flashrom/binwalk command for extraction) so guidance is copy-paste ready.

Add inline validation checkpoints within the workflow for risky steps (e.g. 'verify read-only before write', 'SHA256 after extraction' placed at the extraction step rather than only in the final checklist).

Show the concrete JTAG lock-detection method (how IDCODE enumeration determines lock state) so the '评估是否锁定' step is actionable rather than descriptive.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense — short labeled sections, a compact toolchain table, and a one-level-deep reference — with no padding or explanation of concepts Claude already knows; nearly every token earns its place.	3 / 3
Actionability	Guidance is concrete in places ('万用表找 GND/VCC/TX/RX', '枚举 IDCODE', tool list) but the workflow steps are checkbox directives rather than executable commands, and key specifics (baud-rate values, connection wiring) are only implied.	2 / 3
Workflow Clarity	The workflow is a clearly sequenced checkbox list with a safety-first (read-only) opening, but for risky operations like JTAG enumeration and firmware extraction it lacks explicit validate/verify checkpoints between steps; the verification is deferred to a separate self-check section rather than inline.	2 / 3
Progressive Disclosure	The SKILL.md is a concise overview that points to one real, one-level-deep reference (references/debug-interface-triage.md, verified to exist) plus sibling skill folders, with clear sectioning and no nested/deep references.	3 / 3
	Total	10 / 12 Passed

Description

85%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.

A strong, third-person description with a clear 'Use for...' trigger and several specific capabilities. Its only weakness is trigger-term naturalness: the terms are technically apt but lean toward domain jargon over everyday user phrasing.

Suggestions

Add one or two natural-user phrasings alongside the jargon (e.g. 'debug port', 'dump firmware', 'console access') to broaden trigger coverage.

Consider naming the target devices explicitly (e.g. routers, IoT boards, embedded devices) so the trigger reads more like what a user would actually say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'UART/JTAG discovery, debug pad triage, secure boot overview, and offline firmware extraction support' — each a distinct, specific capability rather than vague language.	3 / 3
Completeness	Explicitly answers both 'what' (the four enumerated research activities) and 'when' via the opening 'Use for authorized hardware and embedded interface security research...' trigger clause.	3 / 3
Trigger Term Quality	Includes relevant technical terms a user might say ('UART', 'JTAG', 'firmware extraction', 'secure boot'), but is heavier on domain jargon than on natural colloquial phrasings and lacks common variations like 'debug port' or 'dump firmware'.	2 / 3
Distinctiveness Conflict Risk	The 'authorized hardware and embedded interface security' niche with UART/JTAG/debug-pad triggers is a clear, distinct scope unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zhaoxuya520/reverse-skill
Path: skills/hardware-security/SKILL.md
Commit: 6aa1362

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.