reverse-skill-router

Routes reverse engineering, exploitation, penetration testing, malware, mobile, firmware, browser automation, documentation, and security tasks to the appropriate specialist skill. Use when a task spans modules or the correct reverse-skill entrypoint is unclear.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

85%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 well-structured master routing/control document with concrete commands, an explicitly sequenced workflow with validation gates, and clean one-level-deep navigation to sub-modules. Its only weakness is mild redundancy from explaining semantics and methodology Claude already knows.

Suggestions

Drop or shrink the '指令语义级别（RFC 2119）' glossary and the generic '工作思路' methodology section, since Claude already knows MUST/SHOULD/MAY and basic RE triage; keep only the contract-specific semantics.

Consolidate the routing-entrypoint instructions: the 'CRITICAL 路由执行契约' and '统一入口' sections overlap; merge them into a single numbered entry sequence to reduce repetition.

Move the large module table to a separate reference (e.g. routing.md) and keep only the top-level routing contract inline, improving token efficiency when only the contract is needed.

Dimension	Reasoning	Score
Conciseness	Mostly dense and information-rich (the module index earns its place), but includes concepts Claude already knows such as the RFC 2119 MUST/SHOULD/MAY glossary and generic 'work思路' methodology advice, keeping it just short of fully lean.	2 / 3
Actionability	Provides concrete executable commands ('scripts/master-route.ps1 -Hint "..."', 'scripts/case-init.ps1', the full bootstrap-reverse.ps1 invocation) and a concrete numbered next-step menu example that is copy-paste ready.	3 / 3
Workflow Clarity	The 'CRITICAL 路由执行契约' gives an explicitly sequenced NOW/NOW/NOW/NEXT/ACT/end flow with validation gates ('auth 未 granted 禁止对目标 ACT') and a closing completion self-check checklist with feedback loops.	3 / 3
Progressive Disclosure	Acts as a clear overview/router: the module table signals one-level-deep references to sub-skill SKILL.md files and reference docs (e.g. references/community-security-skills.md and the scripts bundle, both present), with content appropriately split across modules.	3 / 3
	Total	11 / 12 Passed

Description

100%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, concise description in third-person voice that states the routing capability, enumerates concrete task domains, and includes an explicit 'Use when' trigger. It is distinguishable and complete.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete task domains ('reverse engineering, exploitation, penetration testing, malware, mobile, firmware, browser automation, documentation, and security tasks') and the concrete routing action applied to them, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Answers both what ('Routes ... tasks to the appropriate specialist skill') and when with an explicit trigger clause ('Use when a task spans modules or the correct reverse-skill entrypoint is unclear').	3 / 3
Trigger Term Quality	Uses natural terms a user would say ('reverse engineering', 'penetration testing', 'malware', 'firmware', 'browser automation') with good coverage rather than opaque jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche as a meta-router for the reverse/security skill family with distinct triggers, unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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/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.