gws-gmail-watch
Gmail: Watch for new emails and stream them as NDJSON.
Install with Tessl CLI
npx tessl i github:googleworkspace/cli --skill gws-gmail-watch70
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/skillEvaluation — 93%
↑ 2.06xAgent success when using this skill
Validation for skill structure
Evaluation results
79%
42%Gmail Inbox Archiver
Email archiving with output-dir and cleanup flags
gws gmail +watch command
0%
100%
--output-dir flag used
0%
100%
--cleanup flag used
0%
100%
--project flag used
50%
100%
--label-ids flag used
30%
100%
Correct NDJSON output format
0%
0%
--msg-format flag used
25%
0%
archive dir as argument
100%
100%
Cleanup on exit
100%
50%
README operational notes
90%
100%
Without context: $0.2164 · 1m 14s · 13 turns · 17 in / 4,328 out tokens
With context: $0.3141 · 1m 4s · 19 turns · 429 in / 3,526 out tokens
100%
69%Scheduled Email Digest Exporter
One-shot email pull with once and max-messages flags
gws gmail +watch command
0%
100%
--once flag used
0%
100%
--max-messages set to 25
0%
100%
--msg-format metadata or minimal
0%
100%
--label-ids UNREAD
0%
100%
--project flag used
0%
100%
Output redirected to file
100%
100%
NDJSON output documented
100%
100%
Scheduled job consideration
100%
100%
NOTES.md present
100%
100%
Without context: $0.2450 · 1m 12s · 14 turns · 18 in / 4,041 out tokens
With context: $0.2084 · 44s · 14 turns · 268 in / 2,327 out tokens
100%
33%Production Email Monitor with Resilient Reconnection
Reconnectable watch with subscription reuse and renewal
gws gmail +watch command
0%
100%
--subscription flag used
33%
100%
No --cleanup flag
83%
100%
--poll-interval 2
33%
100%
Output logged to file
100%
100%
7-day expiry documented
100%
100%
Reconnection via subscription
70%
100%
Restart instructions
100%
100%
RUNBOOK.md present
100%
100%
Without context: $0.4383 · 2m 9s · 19 turns · 135 in / 7,702 out tokens
With context: $0.3089 · 1m 6s · 18 turns · 21 in / 3,733 out tokens
- Evaluated
- Agent
- Claude Code
- Model
- Unknown
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.