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"
86
83%
Does it follow best practices?
Impact
Pending
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 purpose as a model reference table for multi-agent-shogun and provides 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 describing concrete actions the skill performs. The specificity of capabilities could be improved with clearer action verbs.
Suggestions
Rephrase the capability description using concrete action verbs, e.g., 'Lists available AI CLI tools, compares models across tools, identifies required subscriptions, and shows Bloom max capability ratings.'
| 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 model capabilities', 'list subscription requirements', or 'recommend optimal model selection'. | 2 / 3 |
Completeness | Clearly answers both 'what' (reference table for AI CLI tools, models, subscriptions, and Bloom max capability for choosing models in multi-agent-shogun) and 'when' (explicit trigger terms provided with 'Trigger:' prefix covering multiple natural phrasings). | 3 / 3 |
Trigger Term Quality | Excellent coverage of 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 this information. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — it targets a very specific niche (model reference table for multi-agent-shogun) with specific trigger terms. Unlikely to conflict with other skills due to the narrow domain of AI CLI tool model comparison and the specific product name. | 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, actionable model comparison data in clean table format. Its main weakness is moderate verbosity — the Bloom's Taxonomy table and 'When to Use' section add tokens without much value since Claude already understands Bloom's levels and the triggers are in frontmatter. The tables themselves are excellent and the agent assignment recommendations add real value.
Suggestions
Remove the Bloom's Taxonomy quick reference table — Claude already knows Bloom's levels, and this adds ~10 lines of redundant content.
Remove or significantly trim the 'When to Use' section since it largely duplicates the trigger phrases in the frontmatter.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient as a reference table, but includes some unnecessary padding like the 'When to Use' section with example phrases (which duplicates the frontmatter triggers) and explanations Claude already knows like Bloom's Taxonomy definitions. The tables themselves are lean and well-structured. | 2 / 3 |
Actionability | The skill is a reference table, and it provides fully concrete, specific guidance: exact model names, exact subscription tiers, exact Bloom level assignments, exact pricing, and specific agent-to-model mappings. The instruction to 'output the reference tables below directly to the user' is unambiguous. | 3 / 3 |
Workflow Clarity | This is a single-purpose reference skill (display tables), so the workflow is trivially clear: output the tables. The 'Next Step' section provides a clear follow-on action. No multi-step process or destructive operations are involved, so no validation checkpoints are needed. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and tables, and references `/shogun-bloom-config` as a next step. However, the inline content is quite long (~100 lines of tables) and the Bloom's Taxonomy quick reference and the full capability summary table could potentially be split out. The cross-reference to bloom-config is good but the skill itself is somewhat monolithic. | 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
3dafe0a
- 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.