shogun-model-list
All AI CLI tools × available models × required subscriptions × Bloom max capability. Reference table for choosing which models to use in multi-agent-shogun. Trigger: "model list", "what models", "model comparison", "which models can I use", "モデル一覧", "モデル比較", "どのモデルが使える"
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 description effectively communicates its niche as a model reference table for multi-agent-shogun, with excellent trigger term coverage in both English and Japanese. Its main weakness is that the 'what' portion reads more like a list of column headers ('AI CLI tools × available models × required subscriptions × Bloom max capability') rather than clearly stated actions or capabilities. The specificity of the domain and explicit trigger terms make it functional for skill selection despite the somewhat cryptic capability description.
Suggestions
Rephrase the capability portion to use concrete action verbs, e.g., 'Lists available AI CLI tools, their supported models, required subscriptions, and Bloom max capabilities. Helps choose optimal models for multi-agent-shogun configurations.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (AI CLI tools, models, subscriptions) and describes it as a 'reference table for choosing which models to use in multi-agent-shogun', but doesn't list specific concrete actions like 'compare models', 'list subscription requirements', or 'recommend optimal model configurations'. | 2 / 3 |
Completeness | Answers both 'what' (reference table for AI CLI tools, models, subscriptions, and Bloom max capability for multi-agent-shogun) and 'when' (explicit trigger terms listed). The 'Trigger:' clause serves as an explicit 'Use when' equivalent. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms in both English and Japanese: 'model list', 'what models', 'model comparison', 'which models can I use', 'モデル一覧', 'モデル比較', 'どのモデルが使える'. These are phrases users would naturally say when looking for model information. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific niche: it's about a reference table for model selection in 'multi-agent-shogun' specifically, covering CLI tools and subscriptions. The trigger terms are narrowly scoped to model listing/comparison, making conflicts with other skills unlikely. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%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 reference skill that provides concrete, specific model information in an easily scannable table format. Its main strength is actionability — exact model IDs, pricing, benchmarks, and clear agent assignments. Its main weakness is moderate verbosity: the Bloom's Taxonomy table and some explanatory notes add tokens without adding value Claude doesn't already have, and the inline content is somewhat long for a single SKILL.md with no bundle support.
Suggestions
Remove the Bloom's Taxonomy quick reference table — Claude already knows Bloom's taxonomy, and this adds ~10 lines of redundant content.
Remove or minimize the 'When to Use' section since it largely duplicates the frontmatter trigger phrases.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient as a reference table, but includes some unnecessary elements like the Bloom's Taxonomy quick reference (Claude already knows Bloom's taxonomy), the 'When to Use' trigger list (duplicates frontmatter), and some explanatory notes that could be trimmed. The tables themselves are well-structured and dense with information. | 2 / 3 |
Actionability | For a reference/lookup skill, this is highly actionable: it provides specific model identifiers (copy-paste ready), exact pricing, concrete subscription requirements, specific benchmark numbers, and clear agent-to-model assignments. The instruction to 'output the reference tables below directly to the user' is unambiguous. | 3 / 3 |
Workflow Clarity | This is a single-task skill (display reference tables), and the single action is completely unambiguous: output the tables to the user, no tool calls required. The 'Next Step' section provides a clear follow-on action. Per scoring notes, simple single-purpose skills can score 3 if the content is clear. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and logical grouping (by CLI tool, then a cross-CLI summary). However, at ~100 lines of tables, some of this could be split into separate files (e.g., detailed per-CLI breakdowns vs. the summary table). The reference to `/shogun-bloom-config` as a next step is good navigation, but no bundle files exist to offload content to. | 2 / 3 |
Total | 10 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- yohey-w/multi-agent-shogun
- Commit
bb19915
- 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.