fleet-manager

Use when managing, triaging, restarting, escalating, or summarizing Codewhale fleet runs and workers.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

100%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.

An exceptionally well-structured operational skill: concise, fully actionable with typed commands and templates, a clear triage workflow with validation checklists and a feedback loop, and clean section-based navigation with no padding.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout: no concepts Claude already knows are explained, every section (Authority Boundary, Triage Loop, Restart vs Escalate, templates) earns its place, and guidance is tightly scoped to fleet-specific procedure.	5 / 5
Actionability	Fully executable guidance with specific typed commands ('codewhale fleet status/inspect/logs/artifacts/restart/resume/stop'), concrete Runtime API endpoints, and copy-paste-ready escalation and receipt templates covering the common cases.	5 / 5
Workflow Clarity	The Triage Loop is a clear 6-step sequence with an explicit 'Classify the state before acting' checkpoint, the Restart-vs-Escalate section provides validation checklists (restart only when all conditions hold), and a feedback loop (same failure repeats after restart -> escalate) covers error recovery.	5 / 5
Progressive Disclosure	Self-contained SKILL.md with no external references needed and clearly organized sections (Authority Boundary, Triage Loop, Restart vs Escalate, Safe Escalation Draft, Post-Run Receipt) giving easy navigation; no nested or buried references.	5 / 5
	Total	20 / 20 Passed

Description

87%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 with an explicit 'Use when' trigger and a clear product-specific niche. The only weakness is the generic verb 'managing' alongside otherwise concrete actions.

Suggestions

Replace or qualify the generic verb 'managing' with a more concrete action (e.g. 'reconciling leases' or 'coordinating') to lift specificity to full coverage.

Add a synonym or two (e.g. 'fleet jobs' or 'worker runs') to broaden natural trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Codewhale fleet runs and workers') and lists several concrete actions ('managing, triaging, restarting, escalating, or summarizing'), but 'managing' is generic, leaving minor coverage gaps versus a fully comprehensive action list.	4 / 5
Completeness	Explicitly answers both what (the five fleet-management actions) and when via a concrete 'Use when ...' trigger clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage with natural verbs a fleet operator would say ('triaging', 'restarting', 'escalating', 'summarizing') plus 'fleet runs' and 'workers', though it lacks synonym variations.	4 / 5
Distinctiveness Conflict Risk	The 'Codewhale fleet runs and workers' niche is product-specific with distinct triggers, giving minimal conflict risk with other skills.	5 / 5
	Total	18 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: Hmbown/Codewhale
Path: crates/tui/assets/skills/fleet-manager/SKILL.md
Commit: 21282f1

Reviewed: 6 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.