five-difficulties-state-assessment

Use when evaluating whether a political contender can seize power successfully. Applies the five-difficulty framework: 有宠无人, 有人无主, 有主无谋, 有谋而无民, 有民而无德. Compares against Duke Huan of Qi and Duke Wen of Jin as successful benchmarks.

Quality

83%

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

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.

A compact, well-structured single-purpose analytical skill that clearly presents the five-difficulty framework and a verification checklist without over-explaining. Its main weakness is actionability: it states criteria and a decision rule but does not illustrate application with a worked example.

Suggestions

Add a brief worked example applying the five difficulties to one contender (e.g., a named historical figure) to make the assessment procedure concrete and copy-paste-ready in spirit.

Tighten the 'Expected Outcome' section or fold it into the Decision Rule, since 'Accurate prediction of political success or failure based on structural conditions' adds little actionable detail.

Optionally make the assessment procedure explicit as a short numbered list (gather contender profile → score each of the five → compare to Duke Huan/Duke Wen → apply decision rule) before the Verification section.

Dimension	Reasoning	Score
Conciseness	The body is lean with tight bullet definitions for each difficulty and no padding about concepts Claude already knows; minor trim opportunities exist in the opening overview line (which restates the description) and the somewhat generic 'Expected Outcome' section.	4 / 5
Actionability	It provides the five named conditions with definitions and a concrete decision rule ('If a contender fails on multiple difficulties, success is nearly impossible'), but lacks a worked example showing how to apply the framework to a specific contender, leaving key application details implicit.	3 / 5
Workflow Clarity	The 'Verification' section sequences three explicit checkpoints (assess all five, validate against historical benchmarks, confirm multi-failure is disqualifying); this is an analytical rather than destructive/batch skill, so the missing-feedback-loop cap does not apply, though the primary assessment procedure is less spelled out than the verification steps.	4 / 5
Progressive Disclosure	The skill is under 50 lines, self-contained with no need for external references, and well-organized into clearly headed sections (Overview, The Five Difficulties, Decision Rule, Expected Outcome, Verification), satisfying the simple-skill exception.	5 / 5
	Total	16 / 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.

A well-constructed description with an explicit 'Use when' trigger, clear statement of what the skill does, and a highly distinctive niche anchored by named historical benchmarks. It is third-person and concise; the only gap is a lack of synonym coverage for the trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain ('political contender can seize power') and several specific actions ('Applies the five-difficulty framework', 'Compares against Duke Huan of Qi and Duke Wen of Jin as successful benchmarks'), but the actions are analytical rather than a comprehensive list of concrete operations.	4 / 5
Completeness	Explicitly answers both 'what' (applies the five-difficulty framework and compares against historical benchmarks) and 'when' (Use when evaluating whether a political contender can seize power) with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('seize power successfully', 'political contender') with a clear 'Use when' trigger, but omits common synonyms like 'coup', 'usurp', or 'takeover'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (ancient Chinese statecraft framework with named classical benchmarks Duke Huan of Qi / Duke Wen of Jin) with distinctive triggers and minimal overlap with other skills.	5 / 5
	Total	18 / 20 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_100/SKILL.md
Commit: 6b836e3

Reviewed: 13 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.