CtrlK
BlogDocsLog inGet started
Tessl Logo

defensive-military-strategy

Use when facing a militarily superior enemy or planning attrition warfare. Employs deep fortification (深壁), supply line interdiction with light cavalry, and patient refusal of engagement to exhaust the enemy before launching a decisive counterattack during retreat.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

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 well-structured, concise instructional skill with a clear sequenced workflow and explicit validation checkpoints. Actionability is the weakest dimension: guidance is concrete in direction but lacks specific quantitative or tactical parameters.

Suggestions

Add concrete tactical parameters to key steps (e.g. recommended fortification depth, cavalry detachment size as a fraction of force, interdiction cadence) to make guidance more directly actionable.

Specify measurable exhaustion/retreat indicators in the validation checklist so the counterattack trigger is unambiguous.

DimensionReasoningScore

Conciseness

Lean and efficient with no padding or explanations of concepts Claude already knows; every section earns its place (steps, decision points, outcomes, validation).

3 / 3

Actionability

Steps are clear but guidance is conceptual rather than executable — no concrete commands, parameters, or units (e.g. cavalry force sizing, supply-interdiction radius, siege duration). For a strategy skill this is acceptable instruction-only guidance but lacks specific actionable detail.

2 / 3

Workflow Clarity

Six-step sequence is clearly ordered with monitoring gates ('Wait for enemy exhaustion') and a dedicated Validation section with three explicit checkpoints including feint-detection, matching the validate→fix pattern for risky decisions.

3 / 3

Progressive Disclosure

Under 50 lines, single-purpose, no external references needed; well-organized into Overview, Steps, Decision Points, Expected Outcomes, and Validation sections — simple-skill case scoring 3 per scoring notes.

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 strong, specific description with an explicit 'Use when' trigger and concrete capability list. Trigger-term coverage is slightly formal but otherwise it reads naturally and is distinct from other skills.

Suggestions

Add a few natural user-facing trigger variations (e.g. 'outnumbered', 'defensive war', 'protracted siege') to broaden when-terms.

DimensionReasoningScore

Specificity

It lists multiple concrete actions: 'deep fortification (深壁)', 'supply line interdiction with light cavalry', 'patient refusal of engagement', and 'decisive counterattack during retreat' — concrete and comprehensive.

3 / 3

Completeness

Explicitly answers both what (deep fortification, supply interdiction, counterattack) and when ('Use when facing a militarily superior enemy or planning attrition warfare') with an explicit trigger clause.

3 / 3

Trigger Term Quality

Terms like 'militarily superior enemy' and 'attrition warfare' are plausible but somewhat formal/jargon-like; missing common natural variations a user might say (e.g. 'defensive war', 'outnumbered', 'siege', 'weaken the enemy').

2 / 3

Distinctiveness Conflict Risk

The niche is clearly distinct — defensive attrition strategy against a superior enemy — with specific triggers unlikely to overlap with unrelated skills.

3 / 3

Total

11

/

12

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.

Validation16 / 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.