multi-route-military-convergence

Use when planning multi-column campaigns against distant targets like the Nanyue conquest. Maps multiple approach routes, assigns forces by type (regular, conscript, naval), sets convergence points, and accepts partial column failure.

Quality

82%

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

63%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 instruction skill with a clear sequenced workflow and verification checklist. Its main weaknesses are redundant benefit sections and several planning steps that stay too abstract to act on concretely.

Suggestions

Merge 'Advantages' and 'Expected Outcomes' into a single section to remove the redundancy between paired bullets (e.g. 'Enemy cannot concentrate defenses' / 'Enemy forces dispersed across multiple fronts').

Tighten vague steps like 'Assess enemy defensive capabilities' and 'Consider terrain, supply lines, and seasonal factors' by specifying what to assess or how to factor it (e.g. decision criteria or a concrete checklist).

Add a brief validate-and-adapt feedback loop in 'Execute and Adapt' that says what to do when a column stalls (re-route, reinforce, or mark failed) so the workflow closes the loop explicitly.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the 'Advantages' and 'Expected Outcomes' sections restate the same points (e.g. enemy cannot concentrate vs. enemy forces dispersed; partial failure survivability) and could be collapsed into one section.	3 / 5
Actionability	Concrete elements exist (the four named Nanyue routes, specific troop-type assignments) but many steps stay high-level ('assess enemy defensive capabilities', 'consider terrain, supply lines, and seasonal factors') without specifics to execute.	3 / 5
Workflow Clarity	A clear numbered 1–5 sequence is followed by a dedicated 'Verification' section with explicit checklist items; the only gap is the absence of a validate-then-fix feedback loop.	4 / 5
Progressive Disclosure	Under 50 lines with no external references needed and well-organized sections (Overview, Planning Steps, Advantages, Expected Outcomes, Verification), meeting the simple-skill exception for a top score.	5 / 5
	Total	15 / 20 Passed

Description

92%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 strong, third-person description that clearly states concrete capabilities and an explicit 'Use when' trigger tied to a recognizable example. The only gap is a handful of natural synonyms a user might phrase differently.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Maps multiple approach routes, assigns forces by type (regular, conscript, naval), sets convergence points, and accepts partial column failure' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (maps routes, assigns forces, sets convergence) and when ('Use when planning multi-column campaigns against distant targets like the Nanyue conquest') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage within the niche ('multi-column campaigns', 'distant targets', 'Nanyue conquest', 'convergence points'), but a few natural synonyms users might say (e.g. 'multi-route', 'pincer', 'converging armies') are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (multi-route military convergence) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 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_230/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.