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).

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

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

Quality

Content

85%

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

The content is a clear, actionable decision framework with a well-sequenced workflow and explicit validation checkpoints, scoring at the top on actionability, workflow clarity, and progressive disclosure. Its only weakness is mild redundancy across the framing sections that keeps conciseness at level 2 rather than fully lean.

Suggestions

Merge the Overview, The Scenario, and the Evaluate Consequences framing into a single concise section to remove the repeated short-term-vs-long-term tradeoff and tighten token efficiency.

Trim or fold the full Classical-Chinese source quote plus its translation into one line where the translation alone already conveys the principle, reducing overlap with the Decision Process step.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-organized, but it re-explains the coercion scenario and repeats the short-term-vs-long-term tradeoff across the Overview, Scenario, and Evaluate Consequences sections, which could be tightened to remove overlap; it does not pad with concepts Claude already knows, so it clears level 2 but does not reach the fully lean level-3 anchor.	2 / 3
Actionability	The framework gives concrete, directly usable guidance: specific decision options ('Option A: Honor the agreement despite coercion', 'Option B: Renounce the agreement and eliminate the coercer'), a named principle with source text and translation, and a worked historical example with a concrete outcome, matching the fully actionable level-3 anchor for an instruction-only skill.	3 / 3
Workflow Clarity	The Decision Process is a clear five-step sequence (Acknowledge -> Analyze -> Evaluate -> Apply -> Execute) culminating in a dedicated Validation section with three explicit checkpoints, including verifying outcomes materialized, which matches the level-3 anchor of clear sequencing with validation steps and feedback checks.	3 / 3
Progressive Disclosure	This is a short single-purpose skill (under 50 lines, no bundle files), with well-organized sections (Overview, Scenario, Decision Process, Outcomes, Historical Example, Validation); per the rubric's simple-skills note this earns level 3 without external file references.	3 / 3
	Total	11 / 12 Passed

Description

75%

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-structured with an explicit 'Use when' trigger and a clearly distinct, narrow niche, which together carry the completeness and distinctiveness dimensions. Specificity and trigger-term quality are strong but not maximal, since it names one core action rather than a list of concrete actions and relies on a specialized historical reference over broadly natural phrasings.

Suggestions

List a couple more concrete actions beyond 'fulfilling coerced promises' (e.g., assessing whether an agreement was coerced, communicating adherence to other parties) to lift specificity toward the level-3 anchor.

Pair the Duke Huan reference with more common natural phrasings users would actually say (e.g., 'forced promises', 'coerced agreements', 'keeping commitments under pressure') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain ('agreements made under duress or coercion') and an action ('fulfilling coerced promises to build long-term diplomatic credibility'), but it stops at a single action rather than listing multiple specific concrete actions like the level-3 anchor.	2 / 3
Completeness	It explicitly answers both 'what' ('fulfilling coerced promises to build long-term diplomatic credibility rather than seeking short-term revenge') and 'when' ('Use when deciding whether to honor agreements made under duress or coercion'), matching the level-3 anchor with an explicit trigger clause.	3 / 3
Trigger Term Quality	It surfaces relevant terms a user might say ('agreements made under duress or coercion', 'diplomatic credibility', 'honor agreements'), but leans on a niche historical reference (Duke Huan of Qi) rather than broad natural phrasings; it is missing common variations, so it is above level 1 but below the full coverage of level 3.	2 / 3
Distinctiveness Conflict Risk	The trigger ('agreements made under duress or coercion') carves out a clear, narrow niche unlikely to fire for unrelated skills, and the named historical model further distinguishes it, matching the level-3 clear-niche anchor.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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
Path: kg/ontology/ontology-v1/skus/procedural/skill_072/SKILL.md
Commit: 79c272f

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.