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

70%

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

70%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-structured router/control contract with strong workflow sequencing, validation gates, and a completion checklist. Its main weaknesses are redundancy inflating length and references to files not present in the bundle (plus an inlined module table that duplicates an existing reference file).

Suggestions

De-duplicate the routing entry sequence — keep it in one place and reference it elsewhere — to tighten conciseness toward anchor 4-5.

Verify all referenced files (routing.md, tool-index.md, ops/*, field-journal/*) exist in the bundle or clearly mark them as living in downstream modules, so progressive disclosure is real rather than dangling.

Move the large inline module table into the existing references/domain-coverage-map.md and keep only a short pointer in SKILL.md to reduce inlining.

Dimension	Reasoning	Score
Conciseness	Mostly terse and table-driven, but ~190 lines with redundancy: the routing entry sequence is restated in both the 'CRITICAL' contract and '统一入口', and bootstrap capabilities are inlined; fits anchor 3 (could be tightened) below anchor 4.	3 / 5
Actionability	Provides concrete executable commands ('scripts/master-route.sh', bootstrap ps1/sh invocations with flags) and a real manifest, but uses placeholders like '<skill-root>'/'<case>' requiring substitution; fits anchor 4 (mostly executable, minor gaps) below anchor 5.	4 / 5
Workflow Clarity	Clear sequenced NOW→NOW→ACT→NEXT contract with explicit MUST/MUST NOT gates, an auth validation gate ('auth 未 granted 禁止 ACT'), evidence→finding→path feedback, and a completion self-check checklist; matches anchor 5 (explicit validation, feedback loops, checklists).	5 / 5
Progressive Disclosure	Points one level deep to many references (routing.md, tool-index.md, ops/*, references/community-security-skills.md), but several referenced files are absent from the bundle and the large inline module table duplicates references/domain-coverage-map.md; fits anchor 3 (some structure, references not all cleanly signaled) below anchor 4.	3 / 5
	Total	15 / 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 clearly states both what the skill does (routes tasks to specialist skills) and when to use it, with strong domain keyword coverage. It is held back by relying on a single generic action verb and by the inherent overlap risk of a broad meta-router.

Suggestions

Replace the single verb 'Routes' with several concrete routing actions (e.g., 'Routes, dispatches, and handsoff ... tasks') to lift specificity toward anchor 5.

Add common synonyms users actually say ('pwn', 'CTF', 'decompile', 'unpack APK') to broaden trigger-term coverage.

Sharpen the 'when' clause with concrete trigger phrases (e.g., 'Use when a task mentions CTF, exploitation, or firmware and the right module is unclear').

Dimension	Reasoning	Score
Specificity	Quotes 'Routes ... tasks to the appropriate specialist skill' — a single concrete action (routing) applied across a broad domain list, rather than multiple distinct concrete actions; fits anchor 3 (1-2 concrete actions) and below anchor 4 (several specific actions).	3 / 5
Completeness	Has both 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'), but the trigger could be broader; fits anchor 4, just below the concrete-trigger anchor 5.	4 / 5
Trigger Term Quality	Includes natural user terms 'reverse engineering', 'penetration testing', 'malware', 'firmware', 'browser automation' with good coverage, but misses common synonyms like 'pwn', 'CTF', 'decompile'; fits anchor 4 (good coverage, a few missing) above anchor 3.	4 / 5
Distinctiveness Conflict Risk	The meta-router niche ('task spans modules or the correct reverse-skill entrypoint is unclear') is distinct, though by design it overlaps with every specialist it routes to; fits anchor 4 (mostly distinct, minor overlap) above anchor 3.	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: 914f74a

Reviewed: 5 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.