military-campaign-authorization

Use when authorizing a military campaign or establishing battlefield discipline. Based on the Battle of Gan (甘之战), structures just-cause documentation, formal proclamation (誓), duty assignment, and post-battle accountability at ancestral shrines.

Quality

85%

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

85%

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

A concise, well-structured instructional skill with a clear sequenced workflow and an explicit validation section. The main weakness is actionability: several steps describe what to produce rather than giving a concrete, repeatable procedure to produce it.

Suggestions

Make each step more procedurally concrete — e.g., for 'Identify Just Cause', specify the exact fields to capture (enemy, transgression type, source of heaven's mandate) so the output is reproducible rather than open-ended.

Add a short worked example showing a completed just-cause statement and proclamation, so the model has a concrete template to mirror.

Tighten 'Decision Points' into explicit if/then rules (e.g., 'If the enemy submits before engagement: halt at step 2 and report; do not proceed to step 4').

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no padding, no explanation of background concepts the model already knows, and every section earns its place.	3 / 3
Actionability	Guidance is concrete and specific (named positions 'left, right, charioteer', named rituals '赏于祖'/'僇于社', named transgressions), but several steps remain directional rather than copy-paste actionable ('Document enemy's violations', 'Deliver formal declaration'). Not a 1 because the specifics are real and usable; not a 3 because there is no fully executable procedure a model could follow verbatim.	2 / 3
Workflow Clarity	A clearly numbered five-step sequence with a dedicated 'Validation' section providing explicit verification checkpoints (just cause documented, duties defined, rewards/punishments applied consistently), which is the feedback-loop pattern the rubric rewards.	3 / 3
Progressive Disclosure	A simple skill under 50 lines with no need for external references and well-organized sections (Overview, Steps, Decision Points, Expected Outcomes, Validation), which the scoring notes allow to score 3.	3 / 3
	Total	11 / 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 with an explicit 'Use when' trigger and a list of concrete capabilities, occupying a distinct niche. The only soft spot is trigger-term breadth, which is constrained by the exotic domain rather than by poor wording.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'just-cause documentation', 'formal proclamation (誓)', 'duty assignment', and 'post-battle accountability at ancestral shrines' — rather than vague language.	3 / 3
Completeness	Explicitly answers both 'what' (structures documentation, proclamation, duty assignment, accountability) and 'when' via a clear 'Use when...' trigger clause.	3 / 3
Trigger Term Quality	The 'Use when authorizing a military campaign or establishing battlefield discipline' clause gives relevant natural triggers, but the niche domain means coverage of common user phrasings is limited. Not a 3 because the trigger vocabulary is narrow and exotic rather than a broad spread of natural terms.	2 / 3
Distinctiveness Conflict Risk	The Battle of Gan / military-campaign-authorization niche is highly specific with distinct triggers, making it 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_010/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.