CtrlK
BlogDocsLog inGet started
Tessl Logo

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。

68

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

76%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.

Highly actionable and reasonably concise single-document skill with good section structure. The main gap is the absence of explicit validation/idle-check checkpoints inside the batch and destructive switch workflows.

Suggestions

Add an explicit validation/idle-check step before the bulk 'for i in $(seq 1 7)' loops (e.g. confirm each pane is idle via tmux capture before restarting) to lift workflow_clarity above the batch/destructive cap of 3.

Embed a verification checkpoint after switch_cli.sh runs (e.g. check pane metadata @model_name matches the requested model) so failures surface immediately.

Tighten the 'What switch_cli.sh Does (internal)' section or move it behind a reference, since the operational pipeline overlaps with the Architecture and Instructions sections.

DimensionReasoningScore

Conciseness

Largely lean — tables and code blocks, no padding about concepts Claude already knows — though the 'What switch_cli.sh Does (internal)' section and some overlap with the Instructions examples could be trimmed slightly.

4 / 5

Actionability

Provides copy-paste-ready bash commands covering single, bulk, Thinking, and inbox-driven cases with concrete agent ids and model names.

5 / 5

Workflow Clarity

The bulk 'for i in $(seq 1 7)' loop performs destructive/batch CLI restarts with no embedded validation checkpoint; per the rubric cap, batch/destructive workflows missing validation cannot score above 3, despite the wait-for-prompt step inside the script and the idle-check caution in Constraints.

3 / 5

Progressive Disclosure

Well-organized into clear sections (Overview, When to Use, Architecture, Instructions, internal, Files, Constraints) with a Files table mapping roles; no bundle reference files exist, so navigation is via headers, leaving minor organization room.

4 / 5

Total

16

/

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, specific description that states concrete actions, natural trigger phrases, and clear use conditions for a well-scoped niche. Only minor trigger-term variants are missing relative to the body.

DimensionReasoningScore

Specificity

Lists multiple concrete pipeline actions — 'settings.yaml更新', '/exit', '新CLI起動', 'pane metadata更新', and 'Thinking有無も制御' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (CLI/モデルをライブ切替 + pipeline + Thinking制御) and 'when' (concrete trigger phrases marked 'で起動').

5 / 5

Trigger Term Quality

Includes natural phrases users would 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') with synonym variation; a few natural variants from the body (e.g. 'CLI変えて', 'Codexにして') are absent.

4 / 5

Distinctiveness Conflict Risk

A narrow niche — live agent CLI/model switching with distinctive Japanese trigger terms — with minimal overlap risk against other skills.

5 / 5

Total

19

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

referenced_paths_exist

Referenced path issues: 12 missing

Warning

Total

13

/

16

Passed

Repository
yohey-w/multi-agent-shogun
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.