CtrlK
BlogDocsLog inGet started
Tessl Logo

counterintelligence-and-strategic-deception

Use when sowing discord between enemy commanders and their trusted advisors or conducting disinformation campaigns. Deploys substantial resources to spread defection rumors, stages differential envoy treatment, and exploits resulting trust breakdowns to degrade enemy decision-making.

72

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

70%

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

The content is well-organized with a clear sequenced workflow and an explicit validation section, though it is instruction-only without executable artifacts and contains minor padding in the Warning section. It appropriately serves as a self-contained simple skill.

Suggestions

Tighten the Warning section to concrete failure indicators (e.g., specific signs of detection) rather than general cautionary language.

Add specific, observable cues for step 1 (e.g., how to identify 'most capable and trusted ministers') to increase actionability of the targeting step.

Make the Validation steps more measurable where possible, e.g., define what counts as 'measurably declined' decision quality beyond the examples given.

DimensionReasoningScore

Conciseness

The body is reasonably lean with no unnecessary concept explanations Claude already knows, but the Warning section ('This strategy requires significant resources and careful execution. Poorly executed disinformation can be detected and backfire.') adds some general guidance that could be tightened.

2 / 3

Actionability

Steps are concrete and instructive (e.g., 'initially prepare elaborate reception, then deliberately downgrade to poor treatment'), but there is no executable code or commands; guidance is actionable for an instruction-only skill yet lacks the fully copy-paste-ready specificity of a top score.

2 / 3

Workflow Clarity

A clear five-step sequence is present with a dedicated Validation section containing explicit verification checkpoints (verify rumors reached decision-makers, confirm envoy treatment was noticed, assess decision-quality decline), providing feedback-style checks for a risky operation.

3 / 3

Progressive Disclosure

The skill is a single, self-contained instruction set under 50 lines with well-organized sections (Overview, Steps, Expected Outcomes, Warning, Validation) and no need for external references, so it scores 3 per the simple-skills scoring note.

3 / 3

Total

10

/

12

Passed

Description

100%

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, third-person, and clearly states both capability and trigger conditions, making it a strong example for this niche domain. It avoids vague fluff and uses natural trigger phrasing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('sowing discord between enemy commanders and their trusted advisors', 'stages differential envoy treatment', 'exploits resulting trust breakdowns') and a concrete resource scale ('40,000 catties of gold' implied via the body, though not in description), matching the multiple-specific-actions anchor.

3 / 3

Completeness

It explicitly answers both 'what' (deploys resources to spread rumors, stages differential envoy treatment, exploits trust breakdowns) and 'when' ('Use when sowing discord... or conducting disinformation campaigns').

3 / 3

Trigger Term Quality

Natural trigger terms users would say ('sowing discord', 'disinformation campaigns', 'defection rumors', 'trust breakdowns') provide good coverage of natural phrasings for this niche.

3 / 3

Distinctiveness Conflict Risk

The niche is highly specific (counterintelligence via inter-commander distrust) with distinct triggers unlikely to overlap with other skills, matching the clear-niche anchor.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
baojie/shiji-kb
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.