Skills Guide

Watcher Management

VerifiedCaution

Manages watcher processes that monitor Gmail, WhatsApp, filesystem, and other external sources. Start, stop, monitor watcher scripts and manage process configuration.

Download and use
Sby Skills Guide Bot
DevOpsIntermediate
3/9/2026
Claude Code
#watchers#process-management#pm2#automation#obsidian

Recommended for

Backend developerClaude CodeDevOps engineerGit automationProductivitySolo / indie hacker

Automated summary

This skill manages the watcher processes that monitor external sources (Gmail, WhatsApp, a drop folder, a bank API) and drop detected items into an Obsidian vault.

Strengths

  • Provides a reusable BaseWatcher abstract class pattern (check_for_updates / create_action_file / run)
  • Ships a reference table of watchers with their source, check interval, and output folder
  • Includes PM2 commands (start, save, startup) to keep watchers alive and restart them on boot
  • Also covers troubleshooting watchers that have stopped working

Limitations

  • Assumes a specific vault layout with a /Needs_Action folder that is not configurable
  • Relies on external reference.md and examples.md files for detailed implementation
  • Does not cover health monitoring, alerting, or log rotation beyond what PM2/supervisord offer
When to use it

Use it when you need to start, stop, supervise, or debug the watcher scripts of a personal AI employee setup.

When not to use it

Avoid it when the task is building the source-side extraction or API authentication logic, which this skill does not address.

Security analysis

Caution
Quality score78/100

The instructions are legitimate operational guidance and contain no destructive, exfiltration, or obfuscated commands. However, the skill grants Bash and sets up long-running watchers over private communications and financial data, so it should be treated as powerful tooling that needs careful credential and process hygiene.

Findings
  • •Authorizes Bash and persistent process management (PM2/supervisord), including auto-start on boot via pm2 startup.
  • •Watchers are designed to access sensitive sources such as Gmail, WhatsApp, and bank APIs, so credential handling and log redaction are important.
  • •No explicit safeguards, allowlists, or path restrictions are specified for watcher scripts or vault output.
How this analysis is made

Examples

Start watchers with PM2
Start the Gmail and WhatsApp watchers with PM2 and make sure they come back up after a reboot.
Debug a stalled watcher
My filesystem watcher stopped writing files to /Needs_Action — check the process status and help me figure out why.
Add a new watcher
Create a new watcher for a bank API using the BaseWatcher pattern, writing to /Needs_Action every hour.

name: watcher-management description: Manages watcher processes that monitor Gmail, WhatsApp, filesystem, and other external sources. Use when starting, stopping, or monitoring watcher scripts, configuring process management, or troubleshooting watcher issues. allowed-tools: Read, Write, Edit, Bash, Glob, Grep

Watcher Management Skill

This skill manages the perception layer of the Personal AI Employee - the watcher processes that monitor external sources and feed data into the Obsidian vault.

Watcher Types

| Watcher | Source | Check Interval | Output Folder | |---------|--------|----------------|---------------| | Gmail Watcher | Gmail API | 2 minutes | /Needs_Action/ | | WhatsApp Watcher | WhatsApp Web | 30 seconds | /Needs_Action/ | | Filesystem Watcher | Drop folder | Realtime | /Needs_Action/ | | Finance Watcher | Bank API | 1 hour | /Needs_Action/ |

Base Watcher Pattern

class BaseWatcher(ABC):
    def __init__(self, vault_path: str, check_interval: int = 60):
        self.vault_path = Path(vault_path)
        self.needs_action = self.vault_path / 'Needs_Action'
        self.check_interval = check_interval

    @abstractmethod
    def check_for_updates(self) -> list:
        pass

    @abstractmethod
    def create_action_file(self, item) -> Path:
        pass

    def run(self):
        while True:
            items = self.check_for_updates()
            for item in items:
                self.create_action_file(item)
            time.sleep(self.check_interval)

Process Management

Use PM2 or supervisord to keep watchers running:

# Start with PM2
pm2 start gmail_watcher.py --interpreter python3

# Save and set to auto-start
pm2 save
pm2 startup

Reference

For detailed implementation, see reference.md

For watcher examples, see examples.md

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/watcher-management-mmio714p/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/watcher-management-mmio714p' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/watcher-management-mmio714p/download' --output '.skill-downloads/watcher-management-mmio714p/SKILL.md.part' && mv '.skill-downloads/watcher-management-mmio714p/SKILL.md.part' '.skill-downloads/watcher-management-mmio714p/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Write, Edit, Bash, Glob, Grep

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/watcher-management-mmio714p/SKILL.md' && test -s '.skill-downloads/watcher-management-mmio714p/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/watcher-management' && cp -R '.skill-downloads/watcher-management-mmio714p' '.claude/skills/watcher-management'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/watcher-management-mmio714p'

openskills read 'watcher-management-mmio714p'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/watcher-management-mmio714p/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Configure a Chat Channel with SecretRefs

DevOps

Set up chat channels using non-interactive commands, with secrets only as SecretRefs. Covers gather, mutate, repair, and prove steps for reliable delivery.

Claude CodeCodexintermediateSafe 387,940
Skills Guide Bot

Investigate ClickHouse CI Failures

DevOps

Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL. Fetches failed tests, classifies flaky vs real regression, and checks for existing issues/fixes.

Claude CodeadvancedSafe 49,516
Skills Guide Bot

Ansible PR Review

DevOps

Reviews an Ansible PR following the project's standardized process, including changelog checks, test coverage validation, and feedback tracking.

Claude CodeintermediateSafe 70,491
Skills Guide Bot