CtrlK
BlogDocsLog inGet started
Tessl Logo

loyalty-defense-argument

Use when defending against accusations of disloyalty or treason. Employs a rhetorical framework of family service records, historical precedents of wrongful execution (Bigan, Wu Zixu), and principle-based appeals to preserve reputation.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

An efficiently written, single-file instruction skill with a clearly sequenced five-step method, concrete named examples, decision logic, and an explicit verification checklist. It assumes Claude's competence and avoids padding throughout.

DimensionReasoningScore

Conciseness

Lean bullet-point structure with no padding and no explanation of concepts Claude already knows; every section (Structure, Key Principles, Decision Points, Verification) earns its place. The minor Overview duplication of the description is not enough to drop it to the 'could be tightened' 2 anchor.

3 / 3

Actionability

For an instruction-only skill the guidance is concrete and specific: numbered steps, operationalized sub-bullets ("Quantify contributions (years, battles, territory)"), named examples (Guan Longpang, Bigan, Wu Zixu), and quoted principles to recite. It instructs rather than describes, satisfying the instruction-only bar despite having no code.

3 / 3

Workflow Clarity

The 5-step Structure is clearly sequenced, and the closing Verification section provides three explicit checkpoints (confirm credibility, validate precedents, ensure framing), matching the 'clear sequence with explicit validation steps' anchor. This is not a destructive/batch operation, so the feedback-loop cap does not apply.

3 / 3

Progressive Disclosure

A single, simple, single-purpose SKILL.md with no bundle directories and well-organized sections; per the simple-skills scoring note, clear organization without external file references earns 3 here.

3 / 3

Total

12

/

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 well-constructed description that names concrete capabilities and explicitly pairs a 'Use when' trigger with the what, in third person. The only weakness is thin trigger-term variation for a niche use case.

Suggestions

Broaden trigger terms to synonyms a user might naturally say, e.g. "Use when facing false accusations of disloyalty, wrongful treason charges, or betrayal claims."

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "family service records", "historical precedents of wrongful execution (Bigan, Wu Zixu)", and "principle-based appeals" — matching the multi-action anchor rather than the single-domain anchor at 2.

3 / 3

Completeness

Explicitly answers both what ("Employs a rhetorical framework of...") and when ("Use when defending against accusations of disloyalty or treason"), with the 'Use when' clause present, so it is not capped at 2.

3 / 3

Trigger Term Quality

"defending against accusations of disloyalty or treason" is a natural trigger, but coverage is a single phrasing with no common synonyms a user might actually say (e.g. "false accusations", "wrongful charges", "treason charge"), fitting the 'some relevant keywords but missing common variations' anchor rather than 3.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (rhetorical loyalty-defense with named historical precedents) with triggers unlikely to fire for any other skill, matching the 'clear niche with distinct triggers' 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.