military-campaign-assessment

Use when deciding whether to launch a military campaign or evaluating battle readiness. Applies Sun Wu's advice to King Helu of Wu: assess troop fatigue (民劳), alliance potential, enemy leadership weaknesses, and multi-pronged coordination.

Quality

77%

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_067/SKILL.md

Quality

Content

70%

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

The body is well-structured with a clear sequenced workflow and validation gates, and appropriately self-contained for its scope. Its weakness is actionability: the steps name what to assess without giving concrete, executable criteria or thresholds for making each judgment.

Suggestions

Add concrete, executable criteria to each step — e.g., define what "rested" means (days since last campaign, casualty replacement rate) or how to score enemy leadership weakness — so the assessment is reproducible rather than subjective.

Tighten the body by removing advisory filler (e.g., "Patience prevents costly failures") and folding "Expected Outcomes" into the decision criteria, since outcomes are implied by the Decision Points.

Give the Validation section explicit pass/fail thresholds (e.g., "troop fatigue index below X") instead of prose confirmations, so the go/no-go gate is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with terse bullets and no padding about concepts Claude already knows, but advisory lines like "Patience prevents costly failures" and the somewhat redundant "Expected Outcomes" section keep it just short of the fully lean top anchor.	2 / 3
Actionability	It uses concrete directive verbs ("Assess whether soldiers are rested or exhausted", "Identify states with grievances", "Coordinate attacks") but offers no executable heuristics, scoring thresholds, or worked criteria, leaving the guidance specific yet not fully actionable per the top anchor.	2 / 3
Workflow Clarity	A clear five-step sequence is paired with conditional "Decision Points" and a three-item "Validation" checklist that gates proceeding — an explicit checkpoint structure appropriate for the consequential launch/no-launch decision.	3 / 3
Progressive Disclosure	The skill is a single self-contained file under 50 lines with no external references and well-organized sections (Overview, Steps, Decision Points, Expected Outcomes, Validation), satisfying the simple-skill allowance for the top anchor.	3 / 3
	Total	10 / 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 clearly states both purpose and trigger context with concrete, distinguishable actions. The only soft spot is trigger-term breadth, which leans on specialized military vocabulary over everyday user phrasings.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "assess troop fatigue (民劳), alliance potential, enemy leadership weaknesses, and multi-pronged coordination" — matching the top anchor for several specific concrete actions.	3 / 3
Completeness	It explicitly answers both what (the assessment actions) and when ("Use when deciding whether to launch a military campaign or evaluating battle readiness"), satisfying the top anchor with an explicit trigger clause.	3 / 3
Trigger Term Quality	"deciding whether to launch a military campaign or evaluating battle readiness" are natural phrases, but the vocabulary is niche and lacks common variations a user might say, so it sits at the middle anchor rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	"military campaign", "battle readiness", and the Sun Wu / King Helu framing carve a clear niche with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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_067/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.