anti-reversing-techniques

AUTHORIZED USE ONLY: This skill contains dual-use security techniques. Before proceeding with any bypass or analysis: > 1.

Quality

21%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-anti-reversing-techniques/SKILL.md

Quality

Content

38%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 well-organized with sensible safety framing and a confirmation gate, but it provides only vague, non-executable guidance and points to a resources/implementation-playbook.md file that does not exist in the bundle. Actionability and progressive disclosure are the weakest areas.

Suggestions

Add concrete, executable guidance: specific commands or tool examples for common anti-reversing tasks (e.g., a snippet for detecting anti-debug checks with a named tool) rather than abstract instructions like 'Identify protection mechanisms'.

Either create the referenced `resources/implementation-playbook.md` with the detailed techniques or remove the dangling reference; currently both the inline pointer (line 55) and the Resources section (line 59) point to a missing file.

Add explicit validation checkpoints to the workflow (e.g., 'Confirm artifact hash unchanged after analysis', 'Re-run detection step to verify no modification') since this skill touches potentially fragile binaries.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-sectioned, but it repeats the AUTHORIZED USE ONLY / authorization guidance twice (the blockquote gate and the "AUTHORIZED USE ONLY" list) and restates scope three times across sections, which could be tightened.	3 / 5
Actionability	Guidance is high-level and abstract — "Identify protection mechanisms and choose safe analysis methods", "Document findings" — with no concrete commands, tool invocations, or executable examples, only describing rather than instructing.	2 / 5
Workflow Clarity	A rough four-step Instructions sequence exists plus a mandatory confirmation gate, but there are no explicit validation checkpoints or feedback loops for the actual analysis steps; the gate provides a checkpoint for authorization but not for the technical workflow.	3 / 5
Progressive Disclosure	The body references `resources/implementation-playbook.md` (twice) for detailed techniques, but no such bundle file or directory exists, so the navigation points to nothing and the 'detailed techniques' are inaccessible — structure is present but the referenced resource is missing.	2 / 5
	Total	10 / 20 Passed

Description

3%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 frontmatter description is malformed — truncated mid-sentence at "> 1." — so it conveys only a boilerplate authorization warning and no actual skill capability or trigger. It fails on specificity, trigger terms, and completeness entirely.

Suggestions

Fix the truncated description: complete the sentence and state concrete actions the skill performs (e.g., 'Identifies and analyzes anti-debugging, anti-disassembly, and obfuscation techniques in protected binaries').

Add an explicit 'Use when...' trigger clause naming natural terms users would say (e.g., 'Use when reverse engineering or analyzing a protected binary, unpacking malware, or debugging obfuscated code with authorization').

Use third-person capability voice and avoid leading with the legal warning; move authorization context into the body so the description focuses on what the skill does.

Dimension	Reasoning	Score
Specificity	The description is truncated mid-sentence ("...Before proceeding with any bypass or analysis: > 1.") and names no concrete actions or capabilities, only a generic dual-use security warning — pure abstract language matching the score-1 anchor.	1 / 5
Completeness	It answers neither "what does this do" nor "when should Claude use it": the sentence is cut off before any capability or trigger clause, and there is no "Use when..." guidance, capping completeness well below 3.	1 / 5
Trigger Term Quality	It contains only legal/safety jargon ("AUTHORIZED USE ONLY", "dual-use security techniques", "bypass or analysis") with none of the natural terms users would actually say when they need this skill (e.g., "reverse engineering", "anti-debugging", "unpacking").	1 / 5
Distinctiveness Conflict Risk	"dual-use security techniques" is very broad and would overlap with many security skills; it is not entirely generic (it signals offensive/bypass context) but has high overlap risk, fitting between the 1 and 3 anchors.	2 / 5
	Total	5 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: boisenoise/skills-collections
Path: skills/antigravity-anti-reversing-techniques/SKILL.md
Commit: 19c310e

Reviewed: about 22 hours ago

Table of Contents

Discovery Implementation Validation

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.