anti-reversing-techniques
AUTHORIZED USE ONLY: This skill contains dual-use security techniques. Before proceeding with any bypass or analysis: > 1.
22
11%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-anti-reversing-techniques/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially non-functional as a skill description. It reads as a truncated authorization disclaimer rather than a description of what the skill does or when it should be used. It provides no concrete actions, no trigger terms, and no guidance for skill selection.
Suggestions
Replace the disclaimer text with a clear statement of what the skill actually does, listing specific concrete actions (e.g., 'Performs penetration testing analysis, identifies vulnerabilities in web applications, reviews security configurations').
Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks about security auditing, vulnerability scanning, penetration testing, or security assessment').
Move any authorization disclaimers to the skill body rather than the description field, which should be reserved for capability and trigger information that helps Claude select the right skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions or capabilities. It mentions 'bypass or analysis' but these are vague and not tied to any specific domain or task. The text is mostly a disclaimer/warning rather than a functional description. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it.' There is no 'Use when...' clause, no explanation of capabilities, and the text appears to be a truncated disclaimer rather than a functional skill description. | 1 / 3 |
Trigger Term Quality | There are no natural keywords a user would say when needing this skill. Terms like 'dual-use security techniques' and 'AUTHORIZED USE ONLY' are not trigger terms users would naturally use in requests. | 1 / 3 |
Distinctiveness Conflict Risk | The description is too vague to be distinguishable from any other security-related skill. 'Bypass or analysis' could overlap with numerous security, penetration testing, or code review skills without any clear niche. | 1 / 3 |
Total | 4 / 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 is almost entirely a policy/authorization wrapper with no actionable technical content. The actual instructions are four vague steps that describe what to do at a high level without any concrete techniques, tools, commands, or examples. The skill depends entirely on a referenced playbook that is not provided in the bundle, making it non-functional as a standalone skill.
Suggestions
Add concrete, executable examples of at least basic analysis techniques (e.g., specific tool commands for static analysis, disassembly, or common anti-debugging detection patterns) directly in the SKILL.md.
Replace the vague 4-step workflow with a detailed, sequenced process including specific tools (e.g., Ghidra, radare2, x64dbg), concrete commands, and explicit validation checkpoints (e.g., 'verify the binary runs in a sandboxed environment before proceeding').
Either provide the referenced `resources/implementation-playbook.md` bundle file or inline the essential technical content so the skill is usable without external dependencies.
Consolidate the repeated authorization/safety guidance into a single concise block to reduce redundancy and free up token budget for actual technical content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The authorization preamble and safety disclaimers are extensive and somewhat repetitive (e.g., 'confirm authorization' appears in multiple sections). The 'Use this skill when' and 'Do not use this skill when' sections overlap with the authorization block. However, given the sensitive nature of the topic, some redundancy is justified. | 2 / 3 |
Actionability | The instructions are entirely abstract and procedural ('Identify protection mechanisms and choose safe analysis methods') with zero concrete code, commands, tool names, or executable examples. There is nothing copy-paste ready or specific enough for Claude to act on without the referenced playbook. | 1 / 3 |
Workflow Clarity | The four numbered steps are vague directives ('Identify protection mechanisms', 'Document findings') with no validation checkpoints, no feedback loops, and no concrete sequencing. For a skill involving potentially destructive or sensitive operations, the lack of explicit verification steps is a significant gap. | 1 / 3 |
Progressive Disclosure | The skill references `resources/implementation-playbook.md` for detailed techniques, which is a reasonable one-level-deep reference. However, no bundle files are provided, meaning the referenced file doesn't exist, and the SKILL.md itself contains almost no substantive content—it's essentially an empty shell pointing to a missing resource. | 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 | |
- Repository
- boisenoise/skills-collections
- Commit
e41e34a
- 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.