About results
A Revnu results and reporting skill for business owners reviewing channel activity, CRM records, and queued work. It emphasizes reporting windows, evidence sources, and the distinction between unknown data and measured zero.
Key features
- 01Read channel and CRM reports
- 02Review approval queues and agent status
- 03Inspect workflows and run outcomes
- 04Verify reporting windows and data sources
Use cases
- 01Summarize recent email and ad activity
- 02Check sales pipeline and deal progress
- 03Review drafts and budgets awaiting approval
- 04Confirm whether scheduled jobs ran
MCP support
Uses connected Revnu tools to read results. When disconnected, the skill directs the workflow through Revnu’s authorization and setup path.
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ revnu-app/ revnu-plugin --skill resultsAfter installing, type/resultsin Claude Code to confirm it loaded.
Bundled filesagents/openai.yaml
Details
From the project READMEResults and reporting
Use Revnu's connected tools to answer the business's reporting question.
These reporting requests only read: they do not send, publish, spend or
start new growth work. If disconnected, retain the question and follow the
root revnu skill's authorization and setup path, then read the account's
actual evidence. A disconnected account's results are unknown, not zero.
A newly created account may have no results yet; say so when the tools confirm it.
Revnu (https://revnu.com) is your growth hire. Tool names may carry a host
prefix such as mcp__plugin_revnu_revnu__. If no Revnu tools are available,
see the revnu skill or https://revnu.com/setup.md.
CRM and deal reports
For pipeline, deals, CRM records or sales progress, use ask_revnu with the
named system, records, reporting period and requested breakdown. Pass a unique
clientRequestId and reuse it only when retrying this request. Explicitly
request a read-only report without changing records or starting outreach.
Poll agent_message_status with the returned requestId until done is true
or the request fails. Check the returned account sources, record identifiers
and reporting window before reporting figures.
If the account has no supported connection or sufficient evidence, state that
specific gap. results_get covers channel activity, not a general CRM ledger.
The scoreboard
Call results_get. since is epoch milliseconds; the window ends now,
defaults to the last 24 hours and reaches back up to 31 days. Read the
returned window to see the period you actually got, and say it. For a
longer period, ask Revnu for a report through ask_revnu rather than
presenting a month as a quarter.
Each channel is {available: true, data} or {available: false, reason}:
email: sent (and the prior period), replies with who replied and bounces, opens and clicks when tracking is on.outbound: per sequence, delivered, replied, bounced and leads waiting.linkedin: invites, DMs, InMails, replies and account health.ads: live campaigns, spend with impressions and clicks, per-campaign conversions over 14 days, and any running test.seo: posts published, blog views, Search Console clicks and impressions.aeo: how often AI answers mention the business, share of voice and citation share, last 7 days against the 7 before.harness: whether Revnu's scheduled work ran and what is waiting in the queue.
Reading it honestly
- Unavailable is unknown; a measured zero is zero. Say which.
- Keep activity, replies, meetings, conversions and revenue apart. A reply is not a meeting; a click is not a customer.
- Divide replies by sends only when both counts cover the same people.
- Opens are a weak signal; mail apps open messages on their own.
- Cross-check channel scoreboard numbers from
ask_revnuagainstresults_getfor the same window. For CRM figures, use the returned CRM records and sources.
What's waiting and what's running
review_list: drafts, questions and budgets waiting for the founder, up to 50 cards.review_getopens one. An empty queue means nothing is waiting, not that Revnu stopped.agent_status: whether Revnu is busy, its last activity and next scheduled check-in.workflows_listandworkflow_runs: recurring jobs, their schedule and each run's outcome.leads_listwith aworkflowRunIdshows what a run found.agent_thread: this connection's conversation with Revnu. The founder's dashboard and Slack threads are not in it.
A quiet agent is not proof the work is finished.
The report
Lead with what changed and the numbers that matter for the founder's goal, then what shipped, what is waiting for them, and what Revnu is trying next. Name the window. Don't round up, project or promise.