CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

malware-analyst

Expert malware analyst specializing in defensive malware research, threat intelligence, and incident response. Masters sandbox analysis, behavioral analysis, and malware family identification. Handles static/dynamic analysis, unpacking, and IOC extraction. Use for malware triage, threat hunting, incident response, or security research.

Quality

68%

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/malware-analyst/SKILL.md
SKILL.md
Quality
Evals
Security

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 mixes genuinely useful material (triage commands, a complete YARA rule, an IOC taxonomy) with generic template boilerplate, mislabeled 'file identification' sections, and long catalogs of techniques and tools Claude already knows. The phase structure is broken (starts at Phase 3) and lacks validation steps, and nothing is offloaded to reference files.

Suggestions

Cut the boilerplate 'Use this skill when' / 'Do not use this skill when' / 'Instructions' sections (they misdescribe the skill as 'file identification' and add no guidance), and trim the technique/tool catalogs to only non-obvious, analyst-specific details.

Fix the workflow numbering: label the opening command block as Phases 1–2 (identification and triage) and add explicit validation checkpoints, e.g., 'verify the unpacked binary runs and imports resolve before disassembly' and 'test the YARA rule against known samples and clean files'.

Move the Common Malware Techniques, Tool Proficiency, IOC Extraction, and Reporting Framework catalogs into references/ files (e.g., references/techniques.md, references/reporting.md) and keep SKILL.md as a concise phase-by-phase overview with one-line pointers to them.

DimensionReasoningScore

Conciseness

The '## Instructions' section ('Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes.') is empty boilerplate, the 'Use this skill when / Do not use' sections are mismatched 'file identification' template filler, and the technique/tool catalogs (e.g., 'Anti-debugging - IsDebuggerPresent', 'Wireshark - Network packet capture') restate knowledge Claude already has — several padded sections with no instructional value.

2 / 5

Actionability

The triage block gives real commands ('file sample.exe', 'strings -a sample.exe', 'rabin2 -i sample.exe') and the YARA rule is complete and syntactically valid, but static analysis is direction-only ('Load in disassembler: IDA Pro, Ghidra...'), the dynamic phase is a checklist with no commands, and tool sections list tools without any usage examples.

3 / 5

Workflow Clarity

Phases are sequenced ('### Phase 3: Static Analysis', '### Phase 4: Dynamic Analysis') but the numbering starts at 3 — Phases 1–2 headers are missing and the opening bash block is unlabeled — and there are no validation checkpoints or feedback loops (e.g., verifying an unpacked sample or testing the YARA rule against known samples).

3 / 5

Progressive Disclosure

There are no bundle files and no external references at all; ~240 lines of catalog content (technique tables, tool lists, the report template) that clearly belongs in separate reference files is fully inlined in SKILL.md, matching the anchor for inlined content that should be split out.

2 / 5

Total

10

/

20

Passed

Description

83%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.

A strong description: it names the domain, lists many concrete capabilities, and closes with an explicit 'Use for' clause containing natural trigger phrases. Its only weaknesses are persona-fluff verbs ('Expert', 'Masters'), a few missing common synonyms, and slightly broad triggers like 'security research'.

DimensionReasoningScore

Specificity

Lists several concrete domain actions — 'static/dynamic analysis, unpacking, and IOC extraction', 'sandbox analysis, behavioral analysis, and malware family identification' — but the 'Expert malware analyst' / 'Masters' persona framing is fluff rather than action verbs, leaving minor gaps versus the comprehensive 5 anchor.

4 / 5

Completeness

Both what and when are explicitly answered: capabilities are enumerated, and 'Use for malware triage, threat hunting, incident response, or security research' provides concrete trigger phrases matching the 5 anchor pattern.

5 / 5

Trigger Term Quality

'Use for malware triage, threat hunting, incident response, or security research' covers natural user phrasings well, but misses common variations like 'reverse engineering', 'suspicious file', 'virus', and any file extensions (.exe, .dll), so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

The malware-analysis niche and 'malware' triggers are distinct, but 'incident response' and 'security research' are broad enough to overlap with general security or threat-intelligence skills, indicating minor overlap risk rather than minimal.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

rmyndharis/antigravity-skills

Path

skills/malware-analyst/SKILL.md

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.