agent-management

Create, manage, and orchestrate AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list agents", "delete agent", "hibernate agent", "wake agent", "install plugin", "show agent", "restart agent", or any agent lifecycle management task.

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./cli-tool/components/skills/ai-maestro/agent-management/SKILL.md

Quality

Content

76%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 lean, highly actionable command reference with real flags and copy-paste examples. Its main weakness is the absence of validation/verification guidance around destructive and batch operations, which the rubric caps at workflow_clarity 3.

Suggestions

Add a verification step after destructive operations (e.g., run 'aimaestro-agent.sh show <agent>' or confirm status after delete/restart) to provide an explicit feedback loop.

Sequence a small worked workflow (e.g., create -> set task -> install plugin -> hibernate/wake) with checkpoints instead of only flat command tables.

Trim or relocate the 'Full AI Maestro Experience' cross-skill marketing section to keep the body focused on agent management.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with command tables and executable examples; minor padding in the intro line and the 'Full AI Maestro Experience' section that repeats cross-skill context.	4 / 5
Actionability	Fully executable, copy-paste-ready commands with concrete flags (--dir, --task, --tags, --confirm, -o) and examples covering create, hibernate, wake, plugin install, and export.	5 / 5
Workflow Clarity	Commands are grouped by lifecycle/plugin/import but lack sequenced workflows or validation checkpoints; destructive operations (delete --confirm) have no verify/feedback step, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	Well-organized into clear sections with no unnecessary external references for a single-purpose reference skill; the closing cross-skill section is mild off-topic organization noise.	4 / 5
	Total	16 / 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, well-structured description that names the tool, enumerates concrete actions, and provides explicit, natural-language trigger phrases covering both 'what' and 'when'. Minor room to add synonyms and tighten 'manage/orchestrate'.

Dimension	Reasoning	Score
Specificity	Lists several concrete lifecycle actions (create, manage, orchestrate, hibernate, wake) and names the AI Maestro CLI specifically, though 'manage'/'orchestrate' are slightly generic, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what (create/manage/orchestrate agents via the AI Maestro CLI) and when (Use when the user asks to 'create agent', 'list agents', etc.) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural quoted trigger phrases users would say ('create agent', 'list agents', 'hibernate agent') with good coverage, but lacks broader synonyms beyond the enumerated set.	4 / 5
Distinctiveness Conflict Risk	Clearly scoped to the AI Maestro CLI agent lifecycle with distinct triggers, with only minor overlap risk against other generic agent-management skills.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: davila7/claude-code-templates
Path: cli-tool/components/skills/ai-maestro/agent-management/SKILL.md
Commit: d4f034a

Reviewed: 5 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.