CtrlK
BlogDocsLog inGet started
Tessl Logo

credibility-preservation-in-diplomacy

Use when deciding whether to honor agreements made under duress or coercion. Applies Duke Huan of Qi's model: fulfilling coerced promises to build long-term diplomatic credibility rather than seeking short-term revenge (愈一小快耳).

62

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./kg/ontology/ontology-v1/skus/procedural/skill_072/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-structured, actionable decision framework with explicit validation, weakened mainly by redundancy across overlapping sections and a heavy classical citation.

Suggestions

Merge the Overview and The Scenario into one concise framing to remove the repeated short-term-vs-long-term contrast.

Trim the full Chinese quotation to the key clause and keep a shorter gloss, cutting tokens without losing the principle.

Tighten Expected Outcomes to the one or two outcomes that are not already implied by the Decision Process.

DimensionReasoningScore

Conciseness

Mostly efficient but has noticeable redundancy between Overview, The Scenario, and Decision Process, and the full classical quote plus English translation consumes tokens that could be trimmed.

3 / 5

Actionability

Provides a concrete numbered 5-step process with named options (A/B), specific sub-actions ('Document the circumstances', 'Publicize your adherence'), and a worked historical example showing how to apply it.

4 / 5

Workflow Clarity

Steps are clearly sequenced and a dedicated Validation section supplies explicit verification checkpoints; falls short of 5 only because the validation is post-hoc verification rather than a validate-fix-retry feedback loop.

4 / 5

Progressive Disclosure

A single-purpose skill under 50 lines with no external references needed and well-organized section headers (Overview, Scenario, Decision Process, Outcomes, Example, Validation), matching the simple-skills exception.

5 / 5

Total

16

/

20

Passed

Description

75%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 cleanly states both trigger and purpose with strong distinctiveness, though its action vocabulary is narrow and the trigger terms are somewhat literary/niche rather than everyday phrasings.

Suggestions

Add a few plain-language synonyms users might actually say (e.g. 'broken promises', 'forced deals', 'backing out of a threatened agreement') alongside the classical framing.

List the concrete actions more explicitly (e.g. 'assess coercion, honor or renounce, publicize adherence') to lift specificity beyond a single binary decision.

DimensionReasoningScore

Specificity

Names the domain (coerced diplomatic agreements) and a couple of concrete actions ('fulfilling coerced promises to build… credibility', avoiding 'short-term revenge'), but it is fundamentally a single honor-vs-renege decision rather than a list of several capabilities.

3 / 5

Completeness

Explicitly answers 'when' ('Use when deciding whether to honor agreements made under duress or coercion') and 'what' (fulfilling coerced promises to build credibility rather than seek revenge) with a concrete trigger phrase.

5 / 5

Trigger Term Quality

Relevant keywords appear ('honor agreements', 'duress or coercion', 'diplomatic credibility', 'revenge') but common synonyms/variations are missing, and the classical Chinese tag '(愈一小快耳)' is not a phrase users would naturally say.

3 / 5

Distinctiveness Conflict Risk

Highly niche framing (Duke Huan of Qi, coerced diplomatic agreements) with distinct triggers and minimal realistic overlap with other skills.

5 / 5

Total

16

/

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.

Validation — 16 / 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.