shogun-agent-status

全エージェント（家老・足軽1-7・軍師）の稼働状態を一覧表示するスキル。tmux pane状態（稼働中/待機中/不在）とタスクYAML状態（task_id, status）と未読inbox数を統合表示。「稼働確認」「エージェント状態」「布陣確認」「agent status」で起動。

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

96%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.

A tight, well-structured single-purpose skill with an executable command, a clear output schema, and an interpretation matrix that makes the output actionable. The only gap is a referenced script path with no corresponding bundle file.

Suggestions

Either ship the referenced `scripts/agent_status.sh` in a scripts/ bundle or remove the unresolved script reference so progressive disclosure reaches 5.

Consider adding a one-line note on how to act on '要調査' (investigate) states to make the workflow fully self-contained.

Dimension	Reasoning	Score
Conciseness	Lean ~45-line body: Overview lists the three data sources, a single command, an output-column table, and a state-interpretation matrix — no padding and no explanation of concepts Claude already knows.	5 / 5
Actionability	Gives the copy-paste-ready command `bash scripts/agent_status.sh` plus a full output schema and an interpretation table covering all common state combinations, matching the level-5 anchor.	5 / 5
Workflow Clarity	The single action (run the script) is unambiguous and the state-interpretation table provides explicit decision guidance per combination; per the simple-skill rule this scores 5, and the operation is read-only so no destructive-validation cap applies.	5 / 5
Progressive Disclosure	Well-organized sections and under 50 lines, but the body references `scripts/agent_status.sh` while no scripts/ bundle directory exists in the skill — a referenced path that cannot be verified, a minor organization gap below the level-5 anchor.	4 / 5
	Total	19 / 20 Passed

Description

83%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, third-person description that clearly states what the skill does and when to invoke it, with concrete data sources and natural trigger phrases. It sits just below top marks on specificity and trigger breadth because the action is a single 'display' verb and a few synonyms are absent.

Suggestions

Add one or two more distinct action verbs (e.g. '検知して一覧化', '状態を判定') to lift specificity toward 5.

Include a couple more natural trigger variations or synonyms (e.g. 'エージェント確認', 'status check') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete data sources (tmux pane状態, タスクYAML task_id/status, 未読inbox数) and a concrete action (統合表示・一覧表示), but the single 'display/integrate' verb keeps it just below the multi-distinct-action level 5.	4 / 5
Completeness	Explicitly answers both 'what' (一覧表示するスキル integrating pane/task/inbox) and 'when' (「…」で起動 with concrete trigger phrases), matching the level-5 anchor.	5 / 5
Trigger Term Quality	Provides four natural trigger phrases users would actually say — 「稼働確認」「エージェント状態」「布陣確認」「agent status」 — covering Japanese and English synonyms; a few natural variations are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a narrow, distinctive niche (家老・足軽・軍師 multi-agent status) with domain-specific triggers; mostly distinct with only minor overlap risk against closely related agent-management skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: yohey-w/multi-agent-shogun
Path: skills/shogun-agent-status/SKILL.md
Commit: aff8dc8

Reviewed: 16 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.