CtrlK
BlogDocsLog inGet started
Tessl Logo

apt41-double-dragon

Adversary-emulation profile for APT41 (Double Dragon / Wicked Panda / BARIUM / Brass Typhoon, ATT&CK G0096), a Chinese dual-mandate espionage-and-cybercrime actor.

49

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/shared/adversary-emulation/apt41-double-dragon/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The profile is information-dense and well-structured with genuinely actionable emulation and detection guidance, but it is monolithic and verbose, lacks executable code and validation feedback loops, and keeps all detail inline rather than splitting large catalogs into reference files.

Suggestions

Split the TTP-by-tactic catalog and signature-tooling list into a reference file (e.g., references/ttp-map.md) and keep SKILL.md as a concise overview that links one level deep.

Add a short validation/verification checkpoint for the emulation chain, e.g., confirm C2 beaconing and detection coverage before moving to lateral movement or any impact stage.

Tighten the intro and campaign narratives to remove recap already covered by the description, keeping only TTP-relevant detail.

DimensionReasoningScore

Conciseness

The body is dense, factual intel (TTPs, tooling) that mostly earns its place and avoids explaining concepts Claude already knows, but the ~165 lines include narrative prose (intro recap, campaign histories) that could be tightened, so it is mostly efficient rather than lean.

2 / 3

Actionability

The emulation and detection sections name concrete tools, commands, event IDs, and a recommended chain, but guidance is prose direction rather than copy-paste executable code blocks, so it is concrete yet incomplete.

2 / 3

Workflow Clarity

A clear sequenced emulation chain is given with an explicit ROE/authorization gate, but there are no validate->fix->retry checkpoints, and the guideline caps destructive/batch operation workflows without validation feedback at 2.

2 / 3

Progressive Disclosure

The file is well-organized with clear section headers, but it is a single ~165-line monolithic document with no bundle references; the TTP catalog and tooling lists could be split into separate reference files, so content that should be separate is inline.

2 / 3

Total

8

/

12

Passed

Description

57%

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 specific and distinct about its named-actor niche, but treats the skill as a static "profile" noun rather than stating concrete actions, and lacks an explicit "Use when..." trigger clause, leaving completeness and trigger coverage incomplete.

Suggestions

Add concrete verbs describing what the skill does, e.g. "Maps APT41's TTPs to ATT&CK, guides authorized emulation of its campaigns, and surfaces detections for the blue cell."

Append an explicit trigger clause such as "Use when emulating APT41/Double Dragon activity or when the user mentions APT41, Wicked Panda, BARIUM, or Brass Typhoon."

Move key natural trigger phrases from metadata.when_to_use into the description so the description itself covers common user phrasings.

DimensionReasoningScore

Specificity

Names the actor, aliases, and ATT&CK ID and calls itself an "adversary-emulation profile," but does not enumerate concrete actions the skill performs (e.g., map TTPs, emulate campaigns, generate detections), so it is not comprehensive.

2 / 3

Completeness

It clearly answers "what" (an adversary-emulation profile for APT41) but provides no explicit "Use when..." trigger clause, so "when" is only implied — capping completeness at 2 per the rubric.

2 / 3

Trigger Term Quality

The description carries natural actor aliases ("APT41, Double Dragon, Wicked Panda, BARIUM, Brass Typhoon") a user would actually say, but the broader natural usage triggers ("emulate this actor") live only in metadata.when_to_use, so common variations are missing from the description itself.

2 / 3

Distinctiveness Conflict Risk

A named threat-actor niche with aliases and ATT&CK G0096 ID is a clear, distinct trigger set unlikely to conflict with other skills.

3 / 3

Total

9

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
PurpleAILAB/Decepticon
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.