CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

salt-typhoon-earth-estries

Adversary-emulation profile for Salt Typhoon (G1045 / Earth Estries / GhostEmperor / FamousSparrow / UNC2286 / RedMike / OPERATOR PANDA), a PRC state-sponsored cyber-espionage actor targeting telecommunications and critical infrastructure worldwide.

Quality

71%

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/salt-typhoon/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 information-rich with strong concrete commands and good section structure, but it is verbose, lacks validation feedback loops for destructive network-device operations, and keeps all detail inline with no reference files.

Suggestions

Add explicit validate/verify-retry checkpoints to the emulation guidance (e.g., verify config diff and validate reachability before proceeding after router/SPAN changes).

Move the large TTP-by-tactic mapping, malware signature table, and detection rules into separate reference files (e.g., TTPS.md, TOOLING.md, DETECTION.md) and link to them one level deep.

Tighten the intro paragraph and de-duplicate campaign/tool mentions that recur across the Attribution, Campaigns, and Tooling sections.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids explaining basics Claude already knows, but the long intro prose and repetition of campaigns/tools across sections add padding that could be tightened.

3 / 5

Actionability

Concrete, executable commands appear throughout (guestshell enable, monitor capture ... eq 49, no vstack, copy bootflash:tac.pcap ftp://..., double-encoded WSMA paths), with minor gaps where steps reference 'the payload-builder' abstractly.

4 / 5

Workflow Clarity

The emulation plays are sequenced by tactic with concrete per-step commands, but the section lacks explicit validate/verify-retry checkpoints and involves destructive network-device operations, which caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Headers organize the content well, but no bundle files exist and the large TTP table, malware catalog, and detection detail are all inlined rather than split into one-level-deep reference files.

3 / 5

Total

13

/

20

Passed

Description

72%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 highly distinctive and trigger-rich for a named threat actor, but it omits an explicit 'Use when' clause, capping completeness, and the skill's concrete actions are only weakly enumerated.

Suggestions

Append an explicit 'Use when...' trigger clause naming the situations that call for this skill (e.g., emulating or detecting Salt Typhoon / Earth Estries TTPs in an authorized engagement).

Enumerate one or two concrete skill actions beyond 'profile for' (e.g., 'Map Salt Typhoon TTPs to MITRE ATT&CK and generate emulation/detection guidance').

DimensionReasoningScore

Specificity

Names the domain ('adversary-emulation profile', 'cyber-espionage actor') and concrete targeting ('telecommunications and critical infrastructure'), but the skill's own actions are summarized as a 'profile for' rather than enumerated, leaving coverage incomplete.

3 / 5

Completeness

Clearly states 'what' (an adversary-emulation profile for this actor) but provides no explicit 'Use when...' trigger clause in the description field, so per the cap, completeness cannot exceed 3.

3 / 5

Trigger Term Quality

Comprehensive natural terms including multiple actor aliases (Salt Typhoon, Earth Estries, GhostEmperor, FamousSparrow, UNC2286, RedMike, OPERATOR PANDA, G1045) plus 'PRC state-sponsored' and 'cyber-espionage' — exactly what an analyst would say.

5 / 5

Distinctiveness Conflict Risk

A named single-actor profile with many unique aliases occupies a clear niche with minimal overlap risk against other skills.

5 / 5

Total

16

/

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

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/shared/adversary-emulation/salt-typhoon/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.