agent-manager-skill

Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

Quality

66%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent/skills/agent-manager-skill/SKILL.md

Quality

Discovery

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description effectively communicates specific capabilities for managing CLI agents through tmux with scheduling support. Its main weakness is the absence of explicit trigger guidance ('Use when...') and limited coverage of natural user language variations. The technical specificity is strong but may miss users who describe their needs in less technical terms.

Suggestions

Add a 'Use when...' clause with trigger scenarios like 'Use when the user wants to run multiple agents in parallel, manage background CLI processes, or schedule automated agent tasks'

Include natural language variations users might say: 'background agents', 'parallel processes', 'scheduled automation', 'agent orchestration', 'terminal management'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'start/stop/monitor/assign' agents, manage 'tmux sessions', and 'cron-friendly scheduling'. These are clear, actionable capabilities.	3 / 3
Completeness	Clearly answers 'what' (manage CLI agents via tmux with scheduling), but lacks an explicit 'Use when...' clause to guide Claude on when to select this skill.	2 / 3
Trigger Term Quality	Includes relevant technical terms like 'tmux', 'CLI agents', 'cron', and 'sessions', but missing common user variations like 'background processes', 'terminal sessions', 'scheduled tasks', or 'agent orchestration'.	2 / 3
Distinctiveness Conflict Risk	Highly distinctive with specific niche: 'tmux sessions', 'CLI agents', and 'cron-friendly scheduling' create a clear, unique domain unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Implementation

64%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a concise skill that provides actionable commands for agent management, respecting Claude's intelligence by avoiding unnecessary explanations. However, it lacks workflow guidance for common multi-step operations (start -> verify -> assign -> monitor) and could better signal where to find detailed configuration documentation. The skill would benefit from explicit validation steps and clearer navigation to supporting materials.

Suggestions

Add a brief workflow example showing the typical sequence: doctor -> start -> verify running -> assign -> monitor, with validation checkpoints between steps

Include expected output examples for key commands (especially 'doctor' and 'list') so Claude knows what success looks like

Replace 'see the repo for examples' with specific file references like 'See agents/example.yaml for configuration format'

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient, with no unnecessary explanations of concepts Claude already knows. Every section serves a clear purpose and the token budget is well-respected.	3 / 3
Actionability	Provides concrete, copy-paste ready commands which is good, but lacks context on what each command does beyond the command name. The heredoc example for 'assign' is helpful but there's no explanation of expected outputs or error handling.	2 / 3
Workflow Clarity	Commands are listed but there's no clear workflow sequence for common operations. Missing validation checkpoints - e.g., how to verify an agent started successfully, what to do if 'doctor' fails, or how to confirm task assignment worked.	2 / 3
Progressive Disclosure	References the external repo for agent configuration examples but doesn't clearly signal what additional documentation exists there. The 'see the repo for examples' is vague - could benefit from specific file references like 'See agents/README.md for configuration format'.	2 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: Dokhacgiakhoa/antigravity-ide
Commit: 332e58b

Reviewed: 17 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.