agent-manager-skill
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
Install with Tessl CLI
npx tessl i github:sickn33/antigravity-awesome-skills --skill agent-manager-skill71
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillAgent success when using this skill
Validation for skill structure
Evaluation results
100%
90%Parallel Agent Orchestration Bootstrap
Agent orchestration script syntax
Correct clone URL
0%
100%
Script invocation path
0%
100%
list subcommand used
0%
100%
start subcommand used
0%
100%
EMP_XXXX agent ID format
0%
100%
assign with heredoc syntax
0%
100%
monitor --follow flag
0%
100%
doctor subcommand present
0%
100%
No alternate command path
100%
100%
Without context: $0.6177 · 3m 7s · 18 turns · 18 in / 11,086 out tokens
With context: $0.3749 · 1m 6s · 22 turns · 70 in / 3,702 out tokens
100%
74%New Team Member Onboarding: Multi-Agent System Setup
Setup runbook and agent config
tmux prerequisite
0%
100%
python3 prerequisite
100%
100%
Correct clone URL
0%
100%
Correct script path
0%
100%
doctor verification step
0%
100%
agents/ config directory
100%
100%
EMP_XXXX naming in config
0%
100%
list command in runbook
30%
100%
start command documented
0%
100%
No wrong tool path
0%
100%
Without context: $0.4273 · 1m 48s · 16 turns · 14 in / 5,995 out tokens
With context: $0.4374 · 1m 25s · 21 turns · 320 in / 5,099 out tokens
100%
55%Nightly Automated Agent Job Runner
Cron scheduling and task assignment
Correct script path
0%
100%
doctor before start
0%
100%
start subcommand
0%
100%
assign with heredoc
0%
100%
EMP_XXXX agent IDs
0%
100%
Valid cron expression
100%
100%
Cron calls wrapper script
100%
100%
Non-interactive wrapper
100%
100%
No wrong invocation path
100%
100%
Without context: $0.3660 · 59s · 16 turns · 1,719 in / 3,246 out tokens
With context: $0.3532 · 1m 13s · 20 turns · 109 in / 4,179 out tokens
- Evaluated
- Agent
- Claude Code
Table of Contents
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.