binary-ninja-reverse

Use for authorized binary analysis in Binary Ninja, including HLIL/MLIL/LLIL inspection, strings/imports/exports, cross-references, types, patch review, Python API automation, and optional Binary Ninja MCP or localhost HTTP integration.

Quality

89%

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

86%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 concise, well-structured, and actionable with concrete commands and IL-specific guidance. The main gap is that feedback loops for destructive patch/write operations are referenced indirectly rather than as explicit validate-retry steps.

Suggestions

Add an explicit validate→fix→retry loop for byte patches and saved-file writes (e.g., re-open/re-decompile after patching and confirm the intended change before promoting), since these are destructive mutations.

Optionally include one short executable snippet showing a Python API automation pattern (e.g., iterating cross-references) to lift actionability from mostly to fully copy-paste ready.

Pin or note where time-sensitive facts (commit hash '8c5134ee…', metadata version '1.1.0', build '4000') should be re-verified, so they do not silently age into inaccuracy.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no concept-padding: every section (Start safely, Choose the integration, Analysis workflow, Output) carries actionable instruction and assumes Claude's competence, e.g. 'Use HLIL for readable logic, MLIL SSA for data flow'.	5 / 5
Actionability	Provides concrete executable commands (the pinned `npx -y binary-ninja-mcp@1.1.0 --host 127.0.0.1 --port 9009`), specific IL-usage guidance, and a named list of MCP capability families, but much of the GUI/interactive guidance is necessarily directional rather than copy-paste code.	4 / 5
Workflow Clarity	A clearly numbered analysis workflow with safety preconditions and validation practices ('Cross-check high-impact conclusions with a second evidence source', 'Work on a copy when applying patches') is present, though explicit validate->fix->retry feedback loops are implied rather than spelled out.	4 / 5
Progressive Disclosure	Well-organized into clearly labeled one-level sections with no nesting or buried references; with no bundle files and a compact body, the structure alone gives easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

92%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 specific, trigger-explicit, and clearly distinct from neighboring disassembler skills. It is slightly jargon-heavy in trigger terms but otherwise strong.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete capabilities — 'HLIL/MLIL/LLIL inspection, strings/imports/exports, cross-references, types, patch review, Python API automation, and optional Binary Ninja MCP or localhost HTTP integration' — giving comprehensive coverage rather than a generic domain label.	5 / 5
Completeness	Opens with an explicit 'Use for…' trigger clause and pairs it with a concrete, multi-part statement of what the skill does, answering both 'what' and 'when' clearly.	5 / 5
Trigger Term Quality	Strong natural terms for the niche ('binary analysis', 'Binary Ninja', 'cross-references', 'patch review', 'MCP'), but the list leans technical and lacks casual synonyms a user might say, stopping just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Scoped specifically to Binary Ninja with distinct IL-level and MCP triggers, leaving the ghidra/ida/radare2 niches to sibling skills and minimizing overlap.	5 / 5
	Total	19 / 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/binary-ninja-reverse/SKILL.md
Commit: 7e2097f

Reviewed: 4 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.