rev-unicorn-debug

Debug and emulate specific code fragments or functions using the Unicorn engine. Activate when the user wants to emulate a function with Unicorn, trace binary execution without running the full program, decrypt or decode data by emulating the algorithm, or bypass environment dependencies (JNI, syscalls, libc) during emulation.

Quality

92%

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

85%

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

A tight, well-organized reference that assumes Claude's knowledge and structures Unicorn emulation guidance into efficient tables with a clear iterative debug loop. The main gap is the absence of any executable code skeleton, which leaves the actionability just short of fully copy-paste ready.

Suggestions

Add a minimal executable Python skeleton (create Uc, map memory, register a UC_HOOK_CODE callback that sets PC=LR) so the hook pattern is copy-paste ready rather than prose-only.

Include one small worked example of a simulated libc stub (e.g., a bump-allocator malloc hook) to ground the environment-simulation table in runnable code.

Show the UC_HOOK_MEM_UNMAPPED auto-map callback signature so the auto-recovery guidance is directly implementable.

Dimension	Reasoning	Score
Conciseness	Lean reference material — tight tables for environment simulation, callbacks, and architecture, with no padding explaining what Unicorn, JNI, or syscalls are. Every section earns its tokens and assumes Claude's competence, matching the score-3 'every token earns its place' anchor.	3 / 3
Actionability	Provides concrete constants (UC_HOOK_CODE, UC_ARCH_ARM64, register/argument conventions) and a named hook pattern ('set PC = LR to skip the original function'), but contains no executable code block or copy-paste skeleton. This fits the score-2 anchor of concrete-but-incomplete guidance rather than the score-3 fully-executable-example anchor.	2 / 3
Workflow Clarity	The 'Iterative Debugging Workflow' is a clearly sequenced 5-step loop (Run → Read callback output → Diagnose → Fix → Re-run) with an enumerated diagnosis branch per fault type and an explicit feedback loop, matching the score-3 anchor for clear sequence with error-recovery feedback loops.	3 / 3
Progressive Disclosure	Self-contained single-file skill with well-organized sections (Core Principles, Environment Simulation, Callbacks, Workflow, Architecture Reference), no nested references, and no external files needed. The rubric's scoring note allows score 3 for self-contained skills with well-organized sections even without external references.	3 / 3
	Total	11 / 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.

A strong, specific description that names concrete emulation actions and provides an explicit 'Activate when' trigger covering multiple natural use cases. It is clearly distinguishable from other skills and free of fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Debug and emulate specific code fragments or functions', 'trace binary execution', 'decrypt or decode data by emulating the algorithm', and 'bypass environment dependencies (JNI, syscalls, libc)'. This matches the score-3 anchor listing several specific concrete actions rather than the single-domain score-2 anchor.	3 / 3
Completeness	Explicitly answers what ('Debug and emulate specific code fragments or functions using the Unicorn engine') and when ('Activate when the user wants to emulate a function with Unicorn, trace binary execution..., or bypass environment dependencies'). The explicit 'Activate when' trigger clause is the score-3 marker; without it completeness would be capped at 2.	3 / 3
Trigger Term Quality	Covers natural terms a reverse-engineering user would actually say — 'emulate a function with Unicorn', 'trace binary execution', 'decrypt or decode data', 'bypass environment dependencies (JNI, syscalls, libc)'. Not below 3 because it goes beyond a single generic keyword to enumerate real task phrasings.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Unicorn CPU emulation for reverse engineering) with distinct triggers, making it unlikely to fire for unrelated skills. It is more specific than the score-2 'Works with document files' style anchor.	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: P4nda0s/reverse-skills
Path: skills/rev-unicorn-debug/SKILL.md
Commit: a2baa31

Reviewed: about 2 hours 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.