Content
82%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A highly actionable, token-efficient reference with concrete commands and executable code throughout, plus well-signaled one-level-deep bundle references. The main gaps are the absence of error-recovery loops and target-safety verification around active testing (fuzzing/replay), and some inline reference material (protocol signature tables, common-patterns lists) that either belongs in bundle files or restates knowledge Claude already has.
Suggestions
Add a verification step around Active Testing — e.g., confirm target availability and capture responses while fuzzing or replaying, and stop if the target stops responding — to provide the feedback loop the workflow currently lacks.
Move the full boofuzz example and the 'Common Protocol Signatures' table into a reference file, keeping SKILL.md as a leaner overview with the existing context-triggered links.
Trim the 'Common Patterns to Look For' list to patterns specific to this reverse-engineering workflow, since magic numbers, length fields, and checksums are knowledge Claude already has.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dominated by lean, commented command and code blocks with almost no padded prose. It is not 5 because sections like the "Common Protocol Signatures" table ("SSH - 'SSH-2.0' banner") and the "Common Patterns to Look For" list ("Magic numbers/signatures at message start", "Checksums/CRCs for integrity") restate protocol knowledge Claude already has and could be trimmed. | 4 / 5 |
Actionability | Nearly everything is copy-paste ready: capture commands ("tshark -i eth0 -b filesize:100000 -b files:10 -w capture.pcap"), display filters, executable scapy loops with checksum recalculation, and a complete boofuzz fuzzing script covering the common cases. The only non-executable item is a Burp Suite proxy comment, which is inherently GUI configuration, so this fits the fully-executable anchor rather than the minor-gaps anchor. | 5 / 5 |
Workflow Clarity | The "Analysis Workflow" section gives a clear 7-step sequence with a validation checkpoint ("6. Validate understanding: Implement parser/generator") and edge-case testing. It is not 5 because there are no error-recovery feedback loops (e.g., what to do when the parser rejects samples), and the Active Testing section (fuzzing, modified replay) includes no verification safeguards for the target system. | 4 / 5 |
Progressive Disclosure | Both bundle files are real and one level deep, clearly signaled with context triggers ("Before binary protocol or encryption analysis, read [parsers, structure identification, and TLS techniques](references/binary-encryption-analysis.md)"). It is not 5 because the pointers sit mid-document under Protocol Header Patterns rather than a navigable advanced section, and the 238-line body retains material (the full boofuzz script, the signature table) that could live in reference files. | 4 / 5 |
Total | 17 / 20 Passed |