agentleFS
holaroluwaholaroluwa/outbound-skills/skills/pipeline-analyser/SKILL.md

pipeline-analyser

Skill0 starsChanged 48 days agoMITView on GitHub

Analyse a pipeline export or CRM data to flag at-risk deals, diagnose the root cause for each, and give the exact next action per deal. Use when the user shares a pipeline CSV or export or asks to "review my pipeline", "which deals are slipping", "what's stuck", or "what should I do on each deal". Surfaces stalls, single-threading, missing next steps, and bad close dates, and returns a prioritised action list.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    If the columns are messy, map them first and confirm the mapping with the user.

    line 13

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Pipeline Analyser

A pipeline is only worth the next actions it produces. This skill reads the data, finds what's quietly dying, and tells you exactly what to do about each one.

Input needed

  • A pipeline export or CRM data (CSV is fine). Useful columns: deal, stage, amount, close date, last activity date, owner, next step.

If the columns are messy, map them first and confirm the mapping with the user.

Method

  1. Flag at-risk deals using signals like: no activity in X days, a close date in the past or implausibly soon, stuck in a stage too long, no defined next step, single-threaded (one contact only), or pushed more than once.
  2. For each flagged deal, diagnose the root cause in one line: stalled champion, no next step, slipping date, ghosted, and so on.
  3. Give the exact next action for that deal: the specific move, not "follow up."
  4. Prioritise: which deals to touch today, which this week.

Output

  • A short health summary: counts (healthy / at-risk / dead-weight) and total at-risk value.
  • A list or table: deal, risk flag, root cause, exact next action, priority.

Lead with the highest-value at-risk deals, since that's where an hour of work returns the most.

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.