CtrlK
BlogDocsLog inGet started
Tessl Logo

undermine-enemy-advisor

Use when neutralizing a capable enemy advisor or creating distrust between a rival ruler and their counselor. Deploys distraction tactics, manufactured suspicion, and defection incentives. Based on Qin's handling of You Yu and the Rong king.

71

Quality

86%

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

86%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 tight, well-structured counterintelligence procedure with concrete actionable steps and an explicit validation section. Its main weakness is that validation is framed as final checks rather than embedded feedback loops with retry guidance.

Suggestions

Convert the Validation section into inline checkpoints within the Steps (e.g., after step 3, verify the ruler's attention has actually shifted before creating suspicion), turning post-hoc review into a validate-and-branch feedback loop.

Add a short 'If validation fails' note for each checkpoint describing how to recover and retry, which would lift workflow clarity toward an explicit feedback-loop structure.

Tighten the Overview so it does not restate the frontmatter description verbatim, freeing tokens for the recovery guidance above.

DimensionReasoningScore

Conciseness

Lean and efficient body with no padding or over-explanation of concepts Claude already knows; every section earns its place and the skill assumes competence.

5 / 5

Actionability

Provides concrete, specific procedural guidance per step ('Send entertainment (music, performers)', 'Request the advisor stay longer than planned', 'Offer refuge if the advisor seeks to defect') with only minor gaps, appropriate for an instruction-only skill.

4 / 5

Workflow Clarity

A clear six-step sequence is paired with a Validation section of explicit checkpoints ('Verify that...', 'Confirm that...', 'Check that...'), but the validation reads as post-hoc review rather than inline feedback loops with error-recovery branches.

4 / 5

Progressive Disclosure

Under 50 lines with no need for external references, organized into clear sections (Overview, Steps, Decision Points, Expected Outcomes, Validation), satisfying the simple-skill exception for progressive disclosure.

5 / 5

Total

18

/

20

Passed

Description

87%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 well-crafted: it pairs an explicit 'Use when' trigger with concrete capability statements and a distinctive historical anchor, making it both findable and conflict-resistant. Specificity could rise slightly with more operational action verbs, but coverage is otherwise strong.

DimensionReasoningScore

Specificity

Names the domain and lists several concrete actions ('Deploys distraction tactics, manufactured suspicion, and defection incentives'), but the phrasing stays somewhat conceptual rather than fully operational, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what ('Deploys distraction tactics, manufactured suspicion, and defection incentives') and when ('Use when neutralizing a capable enemy advisor or creating distrust...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Contains natural domain phrases a user might say ('neutralizing a capable enemy advisor', 'creating distrust between a rival ruler and their counselor') with good coverage, though a few common variations or synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (enemy advisor, rival ruler/counselor, Qin's handling of You Yu and the Rong king) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

20

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.