Tessl • The package manager for agent skills

SkillPublic

anti-reversing-techniques

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

Quality

44%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/anti-reversing-techniques/SKILL.md

The canonical home for this skill is anti-reversing-techniques in rmyndharis/antigravity-skills

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 a lean, well-intentioned governance scaffold (authorization scope, use/do-not-use conditions, safety rules) but contains zero technical substance: no tools, commands, or techniques. All concrete material is deferred to a playbook file that is absent from the bundle, leaving the skill unusable as shipped.

Suggestions

Ship the referenced 'resources/implementation-playbook.md' (or inline the core techniques if no bundle file will exist), and remove the duplicated reference — it currently appears both before and inside the '## Resources' section.

Make the Instructions section concrete: name specific analysis approaches (e.g., detecting anti-debug checks, unpacking flows, deobfuscation strategies) instead of 'choose safe analysis methods'.

Add an explicit verification checkpoint to the workflow, e.g. confirm artifacts were not modified (checksum before/after) before documenting findings and recommendations.

Dimension	Reasoning	Score
Conciseness	The body is lean lists with no explanation of concepts Claude already knows. Minor trimmable redundancy: the opening authorization banner duplicates the frontmatter description, and the playbook reference is stated twice (before and inside the '## Resources' section).	4 / 5
Actionability	No code, commands, tool names, or technique specifics appear anywhere; lines like 'Identify protection mechanisms and choose safe analysis methods' describe rather than instruct. It sits below anchor 2 because even the high-level hints do not point at any executable method, and the file meant to hold the concrete detail is missing from the bundle.	1 / 5
Workflow Clarity	A coherent four-step sequence is present (authorize → identify protections → document → recommend), but no validation or verification checkpoints exist and each step is vague — matches the anchor-3 pattern of listed steps with missing checkpoints. Not 2 because the sequence itself is coherent and complete.	3 / 5
Progressive Disclosure	The sole reference, 'resources/implementation-playbook.md', does not exist in the bundle (no references/, scripts/, assets/, or resources/ directories are present), so the skill's only substantive content is unreachable; the reference is also duplicated. The nominal one-level structure is broken by the dangling path, which is worse than references that are merely unclear.	2 / 5
	Total	10 / 20 Passed

Description

25%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 malformed, truncated safety banner: it names the security domain but never states what the skill does, when to use it, or any concrete technique, and it ends mid-sentence with a stray blockquote artifact. It functions as a warning label rather than a skill description and would rarely trigger correctly.

Suggestions

Rewrite the description in third person stating concrete capabilities, e.g. 'Identifies and bypasses anti-reversing techniques (anti-debugging, obfuscation, packing) in protected binaries for authorized analysis.' Keep the authorization caveat to a short prefix and move the full banner into the body.

Add an explicit trigger clause: 'Use when performing authorized malware analysis, CTF challenges, or reverse engineering of protected binaries under written authorization.'

Fix the truncation: the current text ends mid-list ('Before proceeding with any bypass or analysis: > 1.'), which breaks parsing and wastes the description field.

Dimension	Reasoning	Score
Specificity	Names the domain ("dual-use security techniques", "bypass or analysis") but lists no concrete actions — the text is a truncated policy banner, not a capability statement. Not 1 because it is not purely abstract; not 3 because there is no list of 1-2 concrete actions.	2 / 5
Completeness	Has only a vague 'what' ("contains dual-use security techniques" never states what the skill does) and no 'when' clause at all — matches anchor 2 exactly. The text also ends mid-sentence ("Before proceeding with any bypass or analysis: > 1."), leaving any implicit trigger guidance truncated.	2 / 5
Trigger Term Quality	Only generic keywords appear ("bypass", "analysis", "security techniques"); natural trigger phrases a user would say ("reverse engineering", "malware analysis", "anti-debugging", "deobfuscation") are absent. Not 1 because the keywords are at least domain-relevant rather than jargon-only.	2 / 5
Distinctiveness Conflict Risk	"Dual-use security techniques" is very broad and would overlap with many similar security skills (penetration testing, malware analysis, exploit development, security review). Not 3 because nothing in the description carves out a distinct niche or trigger set.	2 / 5
	Total	8 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/anti-reversing-techniques/SKILL.md
Revision: 64adc55

Reviewed: 16 hours ago

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.

anti-reversing-techniques

Table of Contents

Is this your skill?