watching-gmail
Skill12 starsChanged 36 days agoMITView on GitHub
Monitor Gmail inbox for new emails, classify by priority, and create task files. Use when setting up email monitoring, processing unread messages, or configuring email-based task creation. NOT when sending emails (use sending-emails skill).
- Reads credentials
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 5
Use when setting up email monitoring, processing unread messages, or configuring email-based task creation.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Gmail Watcher Skill
Monitors Gmail inbox and creates task files in Obsidian vault.
Quick Start
python scripts/run.pyConfiguration
Required in config/:
credentials.json- Google OAuth client credentialstoken.json- Auto-created on first run
Environment variables:
GMAIL_POLL_INTERVAL- Seconds between checks (default: 60)DRY_RUN- Test mode (default: false)
Priority Classification
| Priority | Keywords |
| Urgent | urgent, asap, emergency, critical |
| High | important, invoice, payment, deadline |
| Medium | question, request, update |
| Low | thanks, fyi, newsletter |
Verification
Run: python scripts/verify.py
In this repository60 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- browser-useSkill
- browsing-with-playwrightSkill
- building-chatgpt-appsSkill
- building-chat-interfacesSkill
- building-chat-widgetsSkill
- building-mcp-serversSkill
- building-nextjs-appsSkill
- building-rag-systemsSkill
- configuring-better-authSkill
- configuring-dapr-pubsubSkill
- containerizing-applicationsSkill
- context7-efficientSkill
- context-degradationSkill
- context-fundamentalsSkill
- context-optimizationSkill
- creating-skillsSkill
- deploying-cloud-k8sSkill
- deploying-kafka-k8sSkill
- deploying-postgres-k8sSkill
- designing-nextjs-uiSkill
- digital-fte-orchestratorSkill
- doc-coauthoringSkill
- docxSkill
- evaluationSkill
- fetching-library-docsSkill
- generating-ceo-briefingSkill
- installing-skill-trackerSkill
- internal-commsSkill
- managing-calendarSkill
- managing-odooSkill
- managing-servicesSkill
- memory-systemsSkill
- multi-agent-patternsSkill
- nextjs-devtoolsSkill
- nx-monorepoSkill
- operating-k8s-localSkill
- operating-production-servicesSkill
- pdfSkill
- posting-facebookSkill
- posting-instagramSkill
- posting-linkedinSkill
- posting-twitterSkill
- pptxSkill
- project-designerSkill
- researching-with-deepwikiSkill
- scaffolding-fastapi-daprSkill
- scaffolding-openai-agentsSkill
- sending-emailsSkill
- skill-creatorSkill
- streaming-llm-responsesSkill
- styling-with-shadcnSkill
- systematic-debuggingSkill
- theme-factorySkill
- tool-designSkill
- watching-filesystemSkill
- watching-whatsappSkill
- working-with-documentsSkill
- working-with-spreadsheetsSkill
- xlsxSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.