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

83%

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

Quality

Content

82%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.

A compact, well-structured triage skill with concrete guidance, clear sequencing, and real validation checkpoints. Weakest on actionability (no example tool invocations, vague extraction step) and progressive disclosure (plain reference signaling, slight reference/body overlap).

Suggestions

Add one or two executable command examples for the software tools Claude can run (e.g. `binwalk -e firmware.bin`, `flashrom -p ch341a_spi -r dump.bin`) to push actionability toward 5.

Add an explicit error-recovery branch to the workflow (e.g. 'if JTAG enumerates but is locked → fall back to SWD / read-only UART') to add the feedback loop the score-5 anchor expects.

Signal the reference as a descriptive link (e.g. 'See [debug-interface-triage.md](references/debug-interface-triage.md) for pinout/silk-screen triage') and de-duplicate the hashing/pin-finding steps that appear in both the body and the reference.

Dimension	Reasoning	Score
Conciseness	Lean checklist-style body with no concept explanations (no 'what is UART' padding), compact table, and brief references — every line is actionable and assumes Claude's competence, matching the score-5 anchor.	5 / 5
Actionability	Concrete actionable guidance with specific pins (GND/VCC/TX/RX), voltage levels (1.8/3.3/5V), IDCODE enumeration, and a tool-to-purpose table; per the instruction-only note absence of code is not penalized, but no example tool invocations (binwalk/flashrom) and a vague 'extract image → hand off' step keep it at 4 rather than 5.	4 / 5
Workflow Clarity	Clear sequenced workflow (NOW/NEXT/ACT plus the numbered 工作流 checklist) with explicit validation/safety checkpoints (read-only default, voltage match before connect, SHA256, task-completion self-check), so it is not capped at 3; missing explicit error-recovery feedback loops (e.g. 'if JTAG locked → try SWD') keep it at 4 rather than 5.	4 / 5
Progressive Disclosure	Well-organized sections and a real one-level-deep reference (references/debug-interface-triage.md, verified to exist) keep it above 3, but the reference is signaled as a plain code path rather than a descriptive link and its 5-line content overlaps the body, leaving minor organization gaps versus the score-5 anchor.	4 / 5
	Total	17 / 20 Passed

Description

83%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 specific, well-targeted description with concrete actions and clear niche triggers. The main gap is that the 'when' guidance is merged into the 'what' rather than stated as explicit user-mention trigger phrases, and keyword synonyms are thin.

Suggestions

Split the trigger into an explicit 'Use when the user mentions UART, JTAG, SWD, secure boot, debug pads, or needs to extract firmware from a physical device' clause to lift completeness toward 5.

Add natural synonyms users say ('dump firmware', 'get a root shell via serial', 'debug port') to broaden trigger-term coverage.

Keep a third-person action lead-in (e.g. 'Performs authorized hardware... ') before the 'Use for' clause to match the canonical good-example voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'UART/JTAG discovery, debug pad triage, secure boot overview, and offline firmware extraction support' — giving comprehensive coverage of the hardware interface niche, matching the score-5 anchor rather than 4 (which expects minor gaps).	5 / 5
Completeness	The 'Use for authorized hardware and embedded interface security research including...' clause supplies both a what and a when with embedded concrete triggers, but the when is blended into the what and not framed as explicit user-mention scenarios, fitting score 4 rather than the separately-stated 'Use when the user mentions...' of score 5.	4 / 5
Trigger Term Quality	Natural domain keywords (UART, JTAG, secure boot, firmware extraction, debug pad) a hardware-research user would say, but lacks synonyms/variations (e.g. 'dump firmware', 'root shell', 'debug port'), so it sits at good-but-not-comprehensive coverage rather than 5.	4 / 5
Distinctiveness Conflict Risk	Highly distinctive hardware-interface triggers (UART/JTAG, debug pad, secure boot) form a clear niche with minimal conflict risk; the 'extraction support' framing keeps it distinct from a sibling firmware-pentest skill.	5 / 5
	Total	18 / 20 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: 3ae5c59

Reviewed: 30 minutes 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.