agentsclimarketplace

Connection health monitor

Skill duandigi/duandigi-growth-marketing-skill/skills/connection-health-monitor

Evidence-first AI Agent Skills for growth marketing — multi-channel analytics (SEO, paid media, social, local search, CRM), secure account integration, AI evaluation, experimentation & approval-safe optimization for Claude Code.

Install
npx -y skills add duandigi/duandigi-growth-marketing-skill --skill connection-health-monitor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use this skill when diagnosing or monitoring whether external marketing-data connections are authorized, reachable, correctly mapped, fresh, complete, and safe to use.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.4 KB, as published. Nobody here has run it

Connection Health Monitor

Purpose

Distinguish business-performance problems from broken, expired, delayed, misconfigured, or partially authorized data connections.

Inputs

  • Connection status, last successful sync, token expiry, and refresh results
  • Provider response codes and quota information
  • Expected data cadence and asset mapping
  • Recent schema, permission, ownership, or account changes

If a required input is unavailable, label it unknown, state how it limits the decision, and create a collection, mapping, validation, or instrumentation task. Never invent credentials, assets, metrics, permissions, or business outcomes.

Workflow

  1. Check authorization state, token refresh, account ownership, and required capabilities.
  2. Verify provider reachability, quota, pagination, and the last complete data period.
  3. Compare expected and observed assets, rows, dimensions, and metric freshness.
  4. Classify failures as authorization, permission, mapping, quota, provider, schema, scheduler, or data-lag issues.
  5. Define retry, backoff, re-consent, fallback import, and escalation behavior.
  6. Block downstream AI evaluation when the missing data could reverse the conclusion.
  7. Return a provider-specific health state and remediation action.

Required output

Return a concise, decision-oriented result containing:

  • Connection health status: healthy, degraded, action required, or unavailable
  • Last complete data period and freshness lag
  • Failure classification and evidence
  • Automated recovery and human remediation steps
  • Downstream analyses that must be paused or caveated

Label material statements as confirmed, calculated, inferred, assumed, or unknown. Include the data period, last complete period, source lineage, and confidence whenever they can change the decision.

Guardrails

  • Do not label a marketing channel as declining when its connector is incomplete or stale.

  • Do not repeatedly retry authentication failures in a way that locks accounts or floods APIs.

  • Never include access tokens or private provider payloads in diagnostics.

  • Do not conceal partial syncs behind a healthy aggregate status.

  • Do not claim guaranteed growth or present an estimate as observed fact.

  • Do not reveal secrets, personal data, private provider payloads, or cross-project information.

  • When an action can spend money, publish, contact people, alter access, modify production, or delete data, prepare an approval request instead of executing automatically.

Completion check

Before finishing, verify that the output:

  • answers a specific business or implementation decision;
  • uses the correct organization, project, asset, date range, time zone, and currency;
  • separates performance problems from data, connection, and attribution problems;
  • includes evidence, uncertainty, affected scope, and a measurable next step;
  • respects least privilege, approval, audit, and rollback requirements;
  • is no longer than necessary for the decision.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.