CtrlK
BlogDocsLog inGet started
Tessl Logo

reverse-engineering

Provides reverse engineering techniques. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or solving it, including binaries, APKs, WASM, firmware, custom VMs, bytecode, malware-like loaders, and anti-debug or anti-analysis logic. Do not use it when the vulnerability is already understood and the remaining task is exploitation; use pwn instead. Do not use it for pure web workflows, log or disk forensics, or standalone crypto problems unless reversing the implementation is the real blocker.

61

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/reverse-engineering/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 a rich, actionable RE reference with concrete commands and a clear problem-solving workflow, but it carries substantial meta-process overhead in Chinese and, most seriously, advertises a large set of reference files that are missing from the bundle, undermining progressive disclosure.

Suggestions

Add the missing referenced files (tools.md, tools-dynamic.md, tools-advanced.md, anti-analysis.md, patterns*.md, languages*.md, platforms*.md, field-notes.md) to the bundle, or remove the dead links and consolidate detail into the four reference files that actually exist.

Trim the Chinese meta-process scaffolding (ACTION REQUIRED, 默认沙盒上下文, 路由上下文, 任务完成自检) and merge the three overlapping reference sections (Additional Resources, Deep-Dive Notes, 路由上下文) into one to reduce token overhead.

Make the memory-dumping and patching steps include an explicit validate→fix→retry feedback loop so destructive/state-changing operations clear the workflow-clarity cap toward the top anchor.

DimensionReasoningScore

Conciseness

The core technique blocks (Quick Wins, GDB PIE, Comparison Direction, encryption patterns) are reasonably lean, but large Chinese meta-process scaffolding ('ACTION REQUIRED', '默认沙盒上下文', '路由上下文', '任务完成自检') and three overlapping reference sections (Additional Resources, Deep-Dive Notes, 路由上下文) add padding that could be tightened; not a 2 because the actionable parts are efficient, not a 4 because the redundancy and process overhead are non-trivial.

3 / 5

Actionability

Provides many concrete, copy-paste-ready commands (pip/apt/brew install lines, 'strings binary | grep -E', 'b *main+0xca', 'aaa; afl; pdf @ main', analyzeHeadless) covering common cases, with only minor high-level gaps like 'Map control flow before modifying execution'; not a 5 because some workflow steps remain abstract rather than executable.

4 / 5

Workflow Clarity

The 8-step Problem-Solving Workflow gives a clear sequence and the closing '任务完成自检' checklist plus step 8 'Validate assumptions by comparing decompiler outputs' supply checkpoints, so most validation is present; not a 5 because feedback loops (validate→fix→retry) are implicit rather than explicit for state-changing operations like memory dumping and patching.

4 / 5

Progressive Disclosure

Sectioning is good and references are clearly signaled with descriptions, but scored against the actual bundle most referenced files (tools.md, tools-dynamic.md, tools-advanced.md, anti-analysis.md, patterns*.md, languages*.md, platforms*.md, field-notes.md) do not exist — only references/re-agent-workflow.md is present — so navigation is partly broken and reference sections overlap redundantly; not a 2 because structure and signaling are present, not a 4 because the bundle does not match the advertised file map.

3 / 5

Total

14

/

20

Passed

Description

82%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 a strong, well-bounded trigger: it states what the skill does, when to use it, and when not to use it with explicit hand-off targets. Its only weakness is that it enumerates target types rather than distinct concrete actions, leaving specificity slightly below the top anchor.

DimensionReasoningScore

Specificity

Names the domain ('reverse engineering techniques') and one concrete action ('understand how a compiled, obfuscated, packed, or virtualized target works') with comprehensive enumeration of target types, but does not list multiple distinct concrete actions like the anchor-5 examples; it is not a 4 because the action set is essentially single rather than 'several specific actions'.

3 / 5

Completeness

Explicitly answers both 'what' ('Provides reverse engineering techniques') and 'when' ('Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works'), and adds concrete negative triggers ('Do not use it when the vulnerability is already understood... use pwn instead'), matching the anchor-5 example that includes both what, when, and exclusion phrasing.

5 / 5

Trigger Term Quality

Strong natural keyword coverage ('reverse engineering', 'binaries', 'APKs', 'WASM', 'firmware', 'custom VMs', 'bytecode', 'anti-debug', 'anti-analysis') that users would actually say, but a few common extensions/synonyms (e.g. ELF, .exe, .bin, .so) are absent so it stops short of the anchor-5 comprehensive bar.

4 / 5

Distinctiveness Conflict Risk

Clear RE niche with distinct triggers and explicit boundaries against pwn, digital forensics, web workflows, and standalone crypto, giving minimal conflict risk as in the anchor-5 example.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 15 missing

Warning

Total

14

/

16

Passed

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.