CtrlK
BlogDocsLog inGet started
Tessl Logo

binary-mobile-reversing

APK/EXE/二进制:UniApp/DCloud/Flutter逆向,证书固定绕过,导出组件,内存破坏exploit链,IoT固件。Use when reversing APK/EXE, UniApp/Flutter, native .so, or memory-corruption exploits.

69

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is token-efficient and packed with concrete, executable commands, but its organization is weak: a single monolithic code block with sequences that lack explicit validation checkpoints, and four referenced bundle files that are not actually bundled. Fixing progressive disclosure and adding validation gates would materially raise its score.

Suggestions

Bundle the referenced files (references/uniapp-apk-reverse-engineering.md, references/uniapp-apk-reversing.md, scripts/js_rc4_deobfuscate.js, scripts/chengzi_decrypt.py) or remove the dead "参见:" citations so navigation is not broken.

Break the single monolithic code block into headed subsections (e.g. ## UniApp/DCloud, ## Flutter, ## Native .so, ## Memory exploitation, ## Generic mobile) so the overview is navigable rather than a wall of text.

Add explicit validation checkpoints to multi-step procedures — e.g. a "verify decoded string against known plaintext before batch-decoding" gate, and a "confirm primitive via checksec before building the ROP chain" step.

DimensionReasoningScore

Conciseness

The body is densely compressed with symbols, arrows, and abbreviations and contains no explanation of basic concepts Claude already knows; every line carries actionable specifics, matching the lean/efficient score-3 anchor.

3 / 3

Actionability

It provides concrete, executable commands with specific flags throughout (e.g. "apktool d / jadx", "strings -n8 libapp.so|grep 'https\?://'", "objection android sslpinning disable", "binwalk -Me", "checksec"), making it copy-paste ready.

3 / 3

Workflow Clarity

Sequences are present (the exploit-chain arrows and deobfuscation steps), but explicit validation checkpoints are mostly implicit — only the rotation-IIFE comma pitfall and "已知字符串对照" serve as feedback, so it sits at the score-2 anchor of steps listed with validation gaps.

2 / 3

Progressive Disclosure

The entire body is one monolithic code block (a wall of text) and all four cited bundle files — references/uniapp-apk-reverse-engineering.md, references/uniapp-apk-reversing.md, scripts/js_rc4_deobfuscate.js, scripts/chengzi_decrypt.py — do not exist, breaking navigation, matching the monolithic/dead-reference score-1 anchor.

1 / 3

Total

9

/

12

Passed

Description

100%

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 strong: it states concrete capabilities, includes an explicit "Use when..." trigger with natural keywords, and carves out a distinctive niche unlikely to conflict with other skills. Voice is appropriately imperative ("Use when") as in the canonical examples, with no first/second-person padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "UniApp/DCloud/Flutter逆向,证书固定绕过,导出组件,内存破坏exploit链,IoT固件" — naming specific reversing activities rather than vague language, matching the score-3 anchor of multiple specific concrete actions.

3 / 3

Completeness

It explicitly answers both what (the listed reversing/pinning/exploit actions) and when via an explicit "Use when..." trigger clause, matching the score-3 anchor.

3 / 3

Trigger Term Quality

The clause "Use when reversing APK/EXE, UniApp/Flutter, native .so, or memory-corruption exploits" uses natural terms a user would actually say (APK, EXE, UniApp, Flutter, native .so), giving good coverage.

3 / 3

Distinctiveness Conflict Risk

The niche is highly specific — UniApp/DCloud/Flutter, native .so, memory-corruption exploit chains, IoT firmware — making it unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 9 missing, 1 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
Ed1s0nZ/CyberStrikeAI
Reviewed

Table of Contents

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.