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.

70

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

85%

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

A compact, well-organized procedural skill with a clear sequence and validation checklist. Its main weakness is that several steps read as strategic guidance rather than concrete, executable instructions.

Suggestions

Convert abstract mindset steps into concrete actions — e.g., replace 'Acknowledge that talented enemies are dangerous' with a specific reconnaissance step such as 'List rival states and rank their advisors by demonstrated competence'.

Add brief execution detail to the distraction and suspicion steps (e.g., what kind of performers, how long an 'extended stay' should be) so the guidance is copy-ready rather than directional.

Tie the Validation checklist back to specific steps so each checkpoint references the action it verifies, tightening the feedback loop.

DimensionReasoningScore

Conciseness

The body is lean and efficiently organized into short bullets with no padding or explanation of concepts Claude already knows, matching the level-3 'every token earns its place' anchor.

3 / 3

Actionability

Some steps are concrete ('Send entertainment (music, performers)'), but several are abstract mindset statements such as 'Acknowledge that talented enemies are dangerous' with no execution detail, fitting the level-2 'some concrete guidance but incomplete' anchor rather than fully actionable instruction.

2 / 3

Workflow Clarity

A clear six-step sequence is paired with an explicit Validation section that functions as a verification checklist, matching the level-3 anchor of clear sequence with explicit validation steps.

3 / 3

Progressive Disclosure

The skill is under 50 lines, needs no external references, and is organized into well-labeled sections (Overview, Steps, Decision Points, Expected Outcomes, Validation), meeting the level-3 simple-skill allowance.

3 / 3

Total

11

/

12

Passed

Description

85%

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 concise, well-structured description that clearly states both capability and trigger conditions with concrete actions. Its only weakness is the specialized historical-strategy vocabulary, which limits natural trigger-term coverage.

Suggestions

Broaden trigger-term coverage with more common phrasings a user might say (e.g., 'turn an enemy advisor', 'sow distrust in a rival court', 'flip a rival's counselor').

Consider dropping or de-emphasizing the historical provenance ('Based on Qin's handling of You Yu and the Rong king') from the description, as it adds little trigger value.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Deploys distraction tactics, manufactured suspicion, and defection incentives' — matching the level-3 anchor of several specific concrete actions rather than the level-2 single-domain example.

3 / 3

Completeness

Explicitly answers both 'what' (deploys distraction, suspicion, defection incentives) and 'when' via an explicit 'Use when...' trigger clause, matching the level-3 anchor.

3 / 3

Trigger Term Quality

Phrases like 'neutralizing a capable enemy advisor' and 'creating distrust between a rival ruler and their counselor' are relevant natural terms, but the vocabulary is specialized and lacks common variations, fitting the level-2 anchor.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear counterintelligence niche ('neutralizing a capable enemy advisor') with distinct triggers unlikely to overlap with other skills, matching the level-3 anchor.

3 / 3

Total

11

/

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.