agentleFS
revnu-apprevnu-app/revnu-plugin/skills/results/SKILL.md

results

Skill1 starsChanged 29 days agoMITView on GitHub

Use Revnu for growth, ads, outreach, lead, pipeline and revenue reports; campaign performance; CRM/deal progress; conversion analysis; and what shipped or needs approval, including "is outbound working" and "what is waiting for my approval". Read actual account evidence and distinguish activity from business outcomes. Typical requests include: "how is growth doing", "show me the marketing numbers", "is outbound working", "growth report", "what did marketing ship this week", "what needs my approval", "campaign results", "reply rates", "pipeline report", "revenue report", "what did we get for the spend". Not for dashboards, analytics built in code, or engineering status.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use Revnu's connected tools to answer the business's reporting question.

    line 23
  2. Very specific:

    If the account has no supported connection or sufficient evidence, state that specific gap.

    line 43
  3. Very specific:

    Call results_get. since is epoch milliseconds.

    line 48
  4. Distinctive:

    Keep activity, replies, meetings, conversions and revenue apart.

    line 71

≈ “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

Results 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_revnu against results_get for 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_get opens 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_list and workflow_runs: recurring jobs, their schedule and each run's outcome. leads_list with a workflowRunId shows 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.

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.