shogun-model-switch

エージェントのCLI/モデルをライブ切替するスキル。settings.yaml更新→/exit→新CLI起動→ pane metadata更新を一発で実行。Thinking有無も制御。「モデル切替」「Sonnetにして」「Opusに変えて」「足軽全員切替」「Thinking切って」で起動。

Quality

82%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

64%

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

This is a well-structured, highly actionable skill with concrete bash commands covering all switching scenarios. Its main weaknesses are the lack of validation/verification steps after switching (especially given the data loss warning) and some verbose internal documentation that could be externalized or trimmed. The content effectively serves as an operational runbook but could be tighter.

Suggestions

Add a verification step after switch_cli.sh execution (e.g., check tmux pane metadata or capture output to confirm the new CLI is running with the expected model).

Move the 'What switch_cli.sh Does (internal)' section to a separate reference file or collapse it significantly—Claude doesn't need the full internal flow to execute the switch correctly.

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient with concrete commands and tables, but includes some sections that could be tightened—the Architecture ASCII diagram and the 'What switch_cli.sh Does (internal)' section explain internals that Claude doesn't need spelled out in this much detail for execution purposes. The display name mapping table is useful but the overall document is longer than necessary.	2 / 3
Actionability	Highly actionable with copy-paste ready bash commands for single switching, bulk switching, thinking control, and inbox-based switching. Every scenario includes concrete executable examples with specific agent IDs, model names, and flags.	3 / 3
Workflow Clarity	The Thinking ON/OFF section has a clear 3-step sequence, and the internal steps of switch_cli.sh are well-documented. However, there are no explicit validation/verification checkpoints—no step to confirm the switch succeeded, check the new model is running, or handle failures. For a potentially destructive operation (data loss warning in Constraints), this is a gap.	2 / 3
Progressive Disclosure	The content is reasonably structured with clear sections (Overview, Instructions, Constraints, Files), but the 'What switch_cli.sh Does (internal)' section is detailed internal documentation that could be in a separate reference file. The Files table references external files but no bundle is provided to verify. For a skill of this length (~120 lines), some content could be split out.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description that concisely communicates a specific multi-step workflow (settings update → exit → restart → metadata update) with clear trigger terms in natural Japanese. It covers both what the skill does and when to invoke it, with distinctive domain-specific terminology that minimizes conflict risk. The description uses appropriate third-person voice and avoids vague language.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: settings.yaml更新, /exit, 新CLI起動, pane metadata更新, and Thinking有無制御. These are clearly defined steps in a pipeline.	3 / 3
Completeness	Clearly answers both 'what' (live-switch agent CLI/model via settings.yaml update, exit, restart, pane metadata update, thinking control) and 'when' (explicit trigger phrases like 「モデル切替」「Sonnetにして」etc.). The trigger guidance is explicit.	3 / 3
Trigger Term Quality	Includes excellent natural trigger terms that users would actually say: 「モデル切替」「Sonnetにして」「Opusに変えて」「足軽全員切替」「Thinking切って」. These cover model switching, specific model names, bulk switching, and thinking toggle — all natural user phrases.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive — targets a very specific niche of live-switching agent CLI/models with tmux pane metadata updates. The trigger terms reference specific model names (Sonnet, Opus) and domain-specific concepts (足軽, pane metadata) making conflicts with other skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: yohey-w/multi-agent-shogun
Commit: 431b86a

Reviewed: 28 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.