Tessl • The package manager for agent skills

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

80%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/SKILL.md

Quality

Content

81%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 is a well-organized router/index with strong actionability (real, verified scripts and commands), explicit workflow gates and a completion checklist, and clear progressive-disclosure navigation via its module table. Minor repetition and buried reference paths prevent the top score on conciseness and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is dense and directive (RFC 2119 levels, module table, bootstrap commands) and largely assumes Claude's competence, but the routing sequence is repeated in both the 'CRITICAL' section and '统一入口' and the illustrative menu example adds length, fitting the 'efficient; minor instances that could be trimmed' anchor rather than the lean anchor at 5.	4 / 5
Actionability	It provides concrete executable commands such as 'scripts/master-route.ps1', 'bash <skill-root>/scripts/bootstrap-reverse.sh 工具名 --start-services', and 'case-init', all verified to exist in the bundle; placeholders like '<skill-root>' and '<case>' keep it at 4 rather than the fully copy-paste-ready anchor at 5.	4 / 5
Workflow Clarity	The 'CRITICAL' section gives a numbered NOW/NOW/ACT/NEXT sequence with an explicit validation gate ('auth 未 granted 禁止对目标 ACT'), an error-recovery path for route misses ('必须先联网补充方法论并提议新增 skill'), and a completion self-check checklist, matching the anchor for clear sequence with explicit validation, feedback loops, and checklists.	5 / 5
Progressive Disclosure	The SKILL.md is a well-structured router overview with a module table acting as navigation and one-level-deep signaled references to verified bundle files (references/community-security-skills.md, scripts/master-route.*, scripts/bootstrap-manifest.json); some references are buried in prose and a few pointed-to paths (ops/, config/, field-journal/) are not in the provided bundle, keeping it at 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

70%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.

The description is third-person, answers both what and when, and lists strong natural trigger terms across the reverse-engineering/security domain. Its main limitation is that the 'what' is a single high-level routing action rather than a set of concrete capabilities, keeping most dimensions at 4.

Suggestions

Replace the single routing verb with 2-3 concrete actions (e.g., 'Routes ... and bootstraps tool dependencies, opens the matched skill, and runs case-init scoping') to lift specificity toward 5.

Add common synonyms or file-type triggers (e.g., '.apk', 'PE/.NET', 'firmware image', 'PCAP') to round out trigger-term coverage.

Tighten the 'when' clause with a concrete trigger phrase users would say (e.g., 'Use when a target type or toolchain is unclear or spans multiple reverse-engineering skills').

Dimension	Reasoning	Score
Specificity	Quotes 'Routes ... tasks to the appropriate specialist skill' — it names the broad domain list (reverse engineering, exploitation, penetration testing, malware, mobile, firmware, browser automation, documentation, security) but describes only one concrete action (routing), matching the anchor for naming a domain with 1-2 actions rather than the multiple-distinct-actions anchor at 4.	3 / 5
Completeness	It states a clear 'what' (routes tasks to the appropriate specialist skill) and an explicit 'when' ('Use when a task spans modules or the correct reverse-skill entrypoint is unclear'), satisfying both halves; the 'what' is high-level routing rather than concrete capabilities, so it sits at 4 rather than the concrete-both anchor at 5.	4 / 5
Trigger Term Quality	Phrases like 'reverse engineering, exploitation, penetration testing, malware, mobile, firmware' and 'Use when a task spans modules or the correct reverse-skill entrypoint is unclear' are natural user terms with good coverage, but no file extensions or common synonyms are included, fitting the 'good coverage, a few natural terms missing' anchor rather than the comprehensive anchor at 5.	4 / 5
Distinctiveness Conflict Risk	The 'reverse-skill entrypoint' framing carves a clear niche with distinct triggers and minimal conflict risk, but the inclusion of broad categories like 'browser automation, documentation, and security tasks' creates minor overlap with related skills, fitting the 'mostly distinct; minor overlap risk' anchor instead of 5.	4 / 5
	Total	15 / 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/SKILL.md
Commit: cab634b

Reviewed: 22 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.