agentleFS
Sign inStart free
saloprjsaloprj/dialogbrain-claude-plugin/skills/lead-report/SKILL.md

lead-report

Skill0 starsChanged 57 days agoMITView on GitHub

Answer "where are we losing leads" for a DialogBrain workspace — unanswered conversations, slow first replies, drop-offs by channel, with the actual threads behind the numbers and one written summary. Use for weekly reviews, funnel questions, or "how did support do this week".

The file

We split this skill into the rules it gives an agent

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

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not report a percentage without the count behind it.

    line 31
  2. Distinctive:

    Do not name a customer in the summary.

    line 32

≈ “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

Where leads are lost

Steps

  1. Fix the window (default: the last 7 days) and the channels in scope.
  2. Numbers first with analytics.query (question): conversations started, share with no reply from the business, median time to first reply, conversations with no message from the business in the last 48 h — per channel. Ask for one table.
  3. Then the threads: search.threads (query, only_unanswered true, since set to the window start, limit 20); search.messages (query, date_from, date_to) inside a thread when a number looks wrong. Read three real examples per problem, not just the count.
  4. One summary, written for the owner, not the analyst: what is lost, where, one sentence each, and the single change that would recover the most. Save it with artifacts.create (title, html). It answers with two links: app_url opens for workspace members in the app; url is the public page and exists only when you pass access_level "shared". Paste app_url for the owner. Pass "shared" and paste url only when the report is meant for someone outside the workspace — a private artifact has no public page, and its public link opens on nothing.
  5. Offer the fix as an action: an agent for the unanswered channel (create-agent skill), or a task for the person who owns it (tasks-board skill).

Do not

  • Do not report a percentage without the count behind it.
  • Do not name a customer in the summary; name the channel and the pattern.

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