Comprehensive patterns and techniques for analyzing compiled binaries, understanding assembly code, and reconstructing program logic.
41
27%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/binary-analysis-patterns/SKILL.mdQuality
Discovery
32%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 identifies a specific technical domain (binary/assembly analysis) but remains too high-level in its action descriptions and completely lacks explicit trigger guidance ('Use when...'). It would benefit significantly from concrete actions, natural user-facing keywords, and clear selection criteria.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about reverse engineering, disassembling binaries, reading assembly code, or analyzing executables.'
Include natural trigger terms users would say: 'reverse engineering', 'disassemble', 'decompile', 'malware', 'ELF', 'PE', '.exe', 'x86', 'ARM', 'IDA', 'Ghidra'.
Replace vague 'patterns and techniques' with specific concrete actions like 'disassemble executables, identify function boundaries, trace control flow, analyze calling conventions, reconstruct data structures'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (reverse engineering/binary analysis) and some actions ('analyzing compiled binaries', 'understanding assembly code', 'reconstructing program logic'), but these are fairly high-level and not concrete specific actions like 'disassemble ELF executables, identify function boundaries, decompile control flow structures'. | 2 / 3 |
Completeness | Describes what the skill covers at a high level but completely lacks any 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause should cap completeness at 2, and since the 'what' is also somewhat weak, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'binaries', 'assembly code', and 'program logic', but misses many natural terms users would say such as 'reverse engineering', 'disassembly', 'decompile', 'malware analysis', 'ELF', 'PE', 'IDA', 'Ghidra', 'x86', 'ARM', or file extensions like '.exe', '.so'. | 2 / 3 |
Distinctiveness Conflict Risk | The domain of binary analysis and assembly code is fairly niche and unlikely to conflict with most other skills, but the vague phrasing ('patterns and techniques') could overlap with general programming or security analysis skills without clear boundaries. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as a comprehensive assembly language reference manual rather than a focused, actionable skill for Claude. It spends most of its token budget on patterns Claude already knows (calling conventions, basic control flow, string operations) without providing novel, project-specific guidance. The workflow section is too high-level to be useful, lacking concrete commands, validation steps, and feedback loops for what is inherently a complex, multi-step process.
Suggestions
Drastically reduce the assembly reference content (calling conventions, control flow, data structures) — Claude already knows these. Focus on project-specific patterns, unusual conventions, or non-obvious gotchas.
Expand the 'Analysis Workflow' section with concrete tool commands (e.g., `file`, `readelf`, `strings`, `objdump` invocations), explicit validation checkpoints, and error recovery steps.
Split the monolithic content into separate reference files (e.g., `x86-patterns.md`, `arm-patterns.md`, `ghidra-scripts.md`) and make SKILL.md a concise overview with clear pointers to each.
Complete the placeholder code (e.g., the `auto_rename` IDAPython function) and ensure all code examples are fully executable rather than partial.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines, much of which covers fundamental assembly concepts (calling conventions, prologue/epilogue, basic control flow patterns) that Claude already knows well. The x86-64, ARM, and data structure sections are essentially a reference manual restatement rather than novel, project-specific knowledge. | 1 / 3 |
Actionability | The assembly examples are concrete and well-annotated, and the Ghidra/IDA scripting snippets are executable. However, the skill reads more like a reference document than actionable task guidance — it doesn't tell Claude what to do in a specific workflow, just catalogs patterns. The Ghidra Java snippet and IDAPython code are useful but incomplete (e.g., the auto_rename function has a `pass` placeholder). | 2 / 3 |
Workflow Clarity | The 'Analysis Workflow' section lists 7 high-level steps but provides no validation checkpoints, no feedback loops, and no concrete commands for each step. For a complex, multi-step domain like binary analysis, the workflow is too vague — 'Initial triage: File type, architecture, imports/exports' gives no specific tools or commands to run. | 1 / 3 |
Progressive Disclosure | The skill references `resources/implementation-playbook.md` but no bundle files are provided, making this reference unverifiable. The content is a monolithic wall of assembly patterns that could benefit from being split into separate reference files (e.g., x86 patterns, ARM patterns, tool scripts), with the main SKILL.md serving as a concise overview with pointers. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
9d0b37c
Table of Contents
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.