CtrlK
BlogDocsLog inGet started
Tessl Logo

protocol-reverse

Use for authorized reverse engineering of custom binary protocols, Protobuf/gRPC, WebSocket frames, and PCAP-driven protocol recovery.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

72%Weight 40%Scale 1-3

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

A lean, well-routed protocol-reverse-engineering skill with a clear phased workflow and a properly structured one-level-deep reference. It is held back by an instruction-heavy body that defers executable decoding code to the reference and by implicit rather than explicit mid-workflow validation checkpoints for its risky replay operations.

Suggestions

Add at least one copy-paste-ready decoding example (e.g., the struct.unpack frame parser from the reference) inline in Phase 2 so the body is actionable without opening the reference.

Insert an explicit validation/feedback checkpoint in Phase 3 before replay (e.g., 'decode a harmless field first; if the layout does not parse, re-align on magic/length before retrying') to convert implicit checkboxes into a validate→fix→retry loop.

In Phase 4, gate the 'MUST 产出' artifacts behind an explicit verification step (re-run the decode command against a second sample to confirm reproducibility) before declaring the task complete.

DimensionReasoningScore

Conciseness

The body uses lean checklist-style prompts ("□ 对齐多个同类消息", "□ 长度字段:大端/小端"), short concrete commands, and never explains concepts Claude already knows (no "what is Protobuf" padding). It matches anchor 3 (lean and efficient; every token earns its place) rather than anchor 2, which would require unnecessary explanation.

3 / 3

Actionability

Quotes: "tshark -r cap.pcap -T fields -e frame.number -e ip.src -e tcp.payload", "protoc --decode_raw", and a tool table with bootstrap info. There is one concrete executable command plus specific tool guidance, but the body's instruction is mostly checklist prompts while the fully executable Python decoding skeleton is deferred to references/protocol-workflow.md, matching anchor 2 (some concrete guidance but incomplete / missing key details) rather than anchor 3's copy-paste-ready code.

2 / 3

Workflow Clarity

Quotes: a clear 4-phase sequence ("Phase 1 — 采集与分诊" through "Phase 4 — 产物"), authorization gating ("auth 未 granted 禁止对目标 ACT"), and a final "任务完成自检" checklist. The sequence is clear with a final verification step, but mid-workflow validation is implicit checkboxes with no explicit validate→fix→retry feedback loops for the risky replay operations ("重放:仅在授权 scope 内"), so per the destructive-operations cap it matches anchor 2 rather than anchor 3.

2 / 3

Progressive Disclosure

Quotes: "references/protocol-workflow.md — 帧布局与 Protobuf 速查". The body is an overview (routing, phases, toolchain) and the detailed cheat sheet lives one level deep in the verified-existing reference file, matching anchor 3 (clear overview with well-signaled one-level-deep references; content appropriately split). No nested 2+ level references are present.

3 / 3

Total

10

/

12

Passed

Description

90%Weight 40%Scale 1-3

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 concise, well-targeted description with strong natural trigger terms, explicit "Use for" guidance, and a distinct niche. Its only weakness is that the stated actions are largely a single reverse-engineering concept applied to named targets rather than multiple distinct concrete operations.

DimensionReasoningScore

Specificity

Quotes: "reverse engineering of custom binary protocols, Protobuf/gRPC, WebSocket frames, and PCAP-driven protocol recovery". It names many concrete targets but the actions collapse to essentially one concept (reverse engineering / protocol recovery), so it matches anchor 2 ("names domain and some actions, but not comprehensive") rather than anchor 3's multiple distinct concrete actions like extract/fill/merge.

2 / 3

Completeness

Quotes: "Use for authorized reverse engineering of ... protocol recovery". The explicit "Use for..." clause provides trigger guidance (when) while the enumerated targets answer what, satisfying anchor 3 (clearly answers both what AND when with explicit triggers). Not capped at 2 because an explicit trigger clause is present.

3 / 3

Trigger Term Quality

Quotes: "reverse engineering", "binary protocols", "Protobuf", "gRPC", "WebSocket", "PCAP", "protocol recovery". These are exactly the natural terms a user would say when requesting this skill, matching anchor 3 (good coverage of natural terms).

3 / 3

Distinctiveness Conflict Risk

Quotes: "authorized reverse engineering of custom binary protocols, Protobuf/gRPC, WebSocket frames, and PCAP-driven protocol recovery". The highly specific protocol niche plus the "authorized" qualifier make it unlikely to trigger for the wrong skill, matching anchor 3.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
zhaoxuya520/reverse-skill
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.