agent-manager-skill

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

2.43x

Quality

73%

Does it follow best practices?

Impact

100%

2.43x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./docs/v19.7/configuration/agent/skills_external/antigravity-awesome-skills-main/skills/agent-manager-skill/SKILL.md

Evaluation results

100%

65%

Bootstrapping an Agent Orchestration Environment

Agent manager setup and health verification

Criteria

Without context

With context

Correct clone URL

100%

Correct script entry point

100%

Doctor command used

100%

tmux prerequisite mentioned

100%

python3 prerequisite mentioned

100%

agents/ directory documented

100%

setup.sh is executable shell script

100%

setup-guide.md exists

100%

70%

Daily Agent Startup Runbook

Listing and launching multiple agents

Criteria

Without context

With context

Correct script path

100%

list command used

100%

start EMP_0001 command

100%

start EMP_0002 command

100%

start EMP_0003 command

100%

Agent ID format

100%

startup.sh is a shell script

100%

runbook.md exists

100%

list precedes start

100%

41%

Automated Maintenance Delegation and Progress Tracking

Task assignment and agent monitoring

Criteria

Without context

With context

Correct script path in assign

100%

assign targets EMP_0002

100%

Heredoc syntax used

100%

Multi-line task content in heredoc

100%

monitor subcommand used

100%

--follow flag on monitor

100%

assign before monitor

50%

100%

delegate.sh is a shell script

100%

delegation-notes.md exists

100%

Repository: duclm1x1/Dive-Ai
Commit: 20ba150

Evaluated: about 1 month ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Bootstrapping an Agent Orchestration Environment Daily Agent Startup Runbook Automated Maintenance Delegation and Progress Tracking

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.