agentleFS
andrerodriguesopsandrerodriguesops/gtm-engine/.claude/skills/pipeline-analysis/SKILL.md

pipeline-analysis

Skill0 starsChanged 9 days agoMITView on GitHub

Deal-by-deal pipeline health: every open deal laid against MEDDPICC and scored with its deep blocker, an explicit NOT-a-blocker callout, and one named strategic move. Use for "pipeline analysis", "which deals are at risk", "what needs attention this week". Deal intelligence (what to DO), not a status digest (that is weekly-exec-update).

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Check the calendar and inbox for the last 14 days.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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 analysis

Read first

company-context, crm-records (stage ladder), sales-playbook.

For each open deal

  1. Pull the deal, contacts and roles, description log, open tasks.
  2. Check the calendar and inbox for the last 14 days. A meeting the client booked from their side never reaches the CRM.
  3. Score health 1–5 on: momentum (days since last real exchange), qualification depth, champion strength, next step dated, stage honesty (is the stage earned?).
  4. Lay the deal against MEDDPICC (sales-call-scorer/RUBRIC.md §B): for each letter, known, partial or unknown, from the calls and the log. The letters still unknown for the deal's stage are where the risk is.
  5. Name the deep blocker (root cause) and the MEDDPICC letter it sits in, what is NOT a blocker, and one move that closes that letter.

A deal whose record is known to be wrong gets fixed or a fix proposed now, not noted.

Output

PIPELINE — [date] — [N] open deals

[Deal] — [stage] — health [n]/5 — [days since last touch]d
  MEDDPICC: M✓ E? D✓ D? P✗ I✓ C✓ C?
  Blocker: [letter] ...
  Not a blocker: ...
  Move: [owner] [action] by [date]

Sort by (value × risk). Lead with the three deals where one move changes the outcome.

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.