agentleFS
Sign inStart free
nitrosendnitrosend/claude/skills/nitrosend-analytics/SKILL.md

nitrosend-analytics

Skill3 starsChanged 7 months agoMITView on GitHub

Inspect Nitrosend account, campaign, flow, or message performance and turn live metrics into bounded recommendations. Use when: "email analytics", "campaign performance", "how are my emails doing", "email insights", "check my stats", "open rate", or "deliverability report".

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use live Nitrosend data as the source of truth.

    line 12
  2. Very specific:

    Prefer benchmarks and recommendations returned by nitro_get_insights, then compare with the same account's prior period and similar sends.

    line 29
  3. Distinctive:

    Treat opens as directional because mailbox privacy features can inflate or obscure them.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Analytics

Use live Nitrosend data as the source of truth. Do not apply fixed global "good", "warning", or "critical" thresholds from this skill.

Select Scope

  • Account overview: nitro_get_insights with scope: "account"
  • Campaign: scope: "campaign" plus entity_id
  • Flow: scope: "flow" plus entity_id
  • Individual message and events: scope: "message" plus entity_id

Supported periods for account, campaign, and flow insights are 7d, 30d, and 90d.

Interpret Responsibly

  1. Lead with delivery, volume, opens, clicks, unsubscribes, complaints, and the trend data the tool actually returns.
  2. Prefer benchmarks and recommendations returned by nitro_get_insights, then compare with the same account's prior period and similar sends.
  3. Treat opens as directional because mailbox privacy features can inflate or obscure them. Give clicks, conversions, replies, complaints, and revenue greater weight when available.
  4. State the sample size and period. Do not call a change meaningful when the evidence is too small or the compared periods differ materially.
  5. Label external industry ranges as contextual, source them freshly, and do not present them as Nitrosend product facts or guarantees.

Deeper Review

For a broader account review:

  1. Pull 30-day and, when useful, 90-day account insights.
  2. Query recent campaigns with nitro_query entity campaigns.
  3. Query relevant flows using statuses allowed by the live nitro_query schema, such as live or paused.
  4. Inspect audience and deliverability context from nitro_get_status and the returned insights rather than deriving unsupported counts.
  5. Prioritize one or two testable changes and define the metric and observation window before recommending a rollout.

Typical hypotheses include subject or sender clarity for weak opens, content hierarchy and CTA clarity for weak clicks, consent/frequency/targeting for unsubscribes or complaints, and flow coverage for missed lifecycle moments. These are hypotheses to test, not diagnoses from one metric alone.

Scheduled Reports

Recurring reports run only when a user has configured them through a host that actually exposes scheduling. Never imply that installing this plugin creates background jobs by itself.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.

Check your setup, free