shogun-bloom-config
Interactive wizard: guided questions with multiple-choice options about subscriptions, then outputs a ready-to-paste capability_tiers YAML + fixed agent model assignments. Trigger: "capability_tiers", "bloom config", "routing setup", "set up model routing", "ルーティング設定", "capability_tiers設定", "モデル設定", "サブスク設定", "model routing"
81
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/shogun-bloom-config/SKILL.mdQuality
Discovery
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 clearly communicates a specific, niche capability (interactive wizard for generating model routing configuration). It excels in providing explicit trigger terms in multiple languages and clearly distinguishes itself from other skills. The description is concise yet comprehensive, covering what the skill does and when to use it.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: guided questions with multiple-choice options about subscriptions, outputs ready-to-paste capability_tiers YAML, and fixed agent model assignments. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (interactive wizard that asks guided questions and outputs capability_tiers YAML + agent model assignments) and 'when' (explicit 'Trigger:' clause listing specific trigger terms). The trigger guidance is explicit and comprehensive. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including both English and Japanese variations: 'capability_tiers', 'bloom config', 'routing setup', 'set up model routing', 'model routing', plus Japanese equivalents like 'ルーティング設定' and 'モデル設定'. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a very specific niche: generating capability_tiers YAML for model routing in what appears to be a 'Bloom' system. The trigger terms are domain-specific and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability with fully executable YAML configurations and a well-structured wizard workflow with clear conditional branching and validation. However, it is severely hampered by its monolithic structure—all 6+ patterns with full YAML blocks, coverage tables, and agent recommendations are inlined, making it extremely token-heavy. The content would benefit enormously from splitting patterns into separate files and keeping only the decision logic and one example pattern in the main skill.
Suggestions
Extract each pattern (A-Free, A, B, C, D, E with sub-variants) into separate referenced files (e.g., `patterns/pattern-a.md`) and keep only the decision matrix and one example pattern inline in SKILL.md.
Create a shared YAML template with variable placeholders instead of repeating the full capability_tiers structure 8+ times—document only the differences between patterns.
Remove redundant coverage tables that repeat the same information already present in the YAML comments; a single consolidated reference table would suffice.
Consider condensing the E-1 through E-4 sub-variants into a parameterized table showing only the differing max_bloom values rather than 4 complete YAML blocks.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines, with extensive repetitive pattern tables, coverage tables, and YAML blocks that share significant structural overlap. Much of this could be condensed into a template with variable substitution rather than spelling out every pattern in full. The E pattern alone has 4 sub-variants each with full YAML blocks. | 1 / 3 |
Actionability | Every pattern provides fully copy-paste ready YAML configurations, specific model names, concrete AskUserQuestion call structures with exact parameters, and a clear decision matrix mapping answers to patterns. The Step 5 application instructions include exact file paths and bash commands. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Q1→Q2→conditional Q3→pattern mapping→output→application steps) with explicit conditional branching (Q3 only when both subscriptions exist), a validation step (validate_subscription_coverage), and clear next-step guidance. The decision tree at the end provides a quick mental model. | 3 / 3 |
Progressive Disclosure | All 6 patterns (with Pattern E having 4 sub-variants) are inlined in a single monolithic file. The pattern details, coverage tables, and YAML blocks for each configuration should be split into separate referenced files (e.g., patterns/pattern-e.md) with only the decision logic and a quick-start example kept in the main SKILL.md. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (518 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- 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.