agentleFS
Sign inStart free
prosyo-aiprosyo-ai/gtm-skill/skills/pipeline-review/SKILL.md

pipeline-review

Skill13 starsChanged 24 days agoMITView on GitHub

Use this skill when a manager or founder needs to review the sales pipeline and forecast: \"review my pipeline\", \"prep for the forecast call\", \"which deals are at risk\", \"is our quarter going to land\". Checks pipeline coverage, stage health, deal aging, slipped close dates, missing next steps and single-threaded deals, scores every deal's risk with evidence, and produces a forecast (commit, best case, upside) with the actions that change the outcome this week.

13 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

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 7

    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:

    Use this weekly or before a forecast call.

    line 16
  2. Distinctive:

    No next step: no future activity scheduled.

    line 32
  3. Distinctive:

    Stale: no activity in 14+ days.

    line 33
  4. Distinctive:

    Every deal moved out of commit has a stated reason.

    line 66
  5. Distinctive:

    MUST base risk on evidence (activity, dates, contacts), not on rep confidence.

    line 73
  6. Distinctive:

    MUST flag past-due close dates and missing next steps.

    line 74
  7. Distinctive:

    NEVER change records in the CRM without approval.

    line 75

“Common” is measured: kept by at least 6 in 10 of the 13 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

Use this weekly or before a forecast call. It turns a pipeline export into an honest forecast and a short list of actions that move the number.

Inputs

  • Pipeline export: deal, owner, stage, amount, close date, created date, last activity, next step, contacts.
  • Quota or target for the period and what has closed so far.
  • Historical stage conversion rates if available.

The play

1. Check coverage

Open pipeline due this period ÷ remaining target. Healthy coverage depends on win rate; at a 25% win rate, 3-4x is typical. Read references/pipeline-health.md for the health checks, thresholds and the risk scoring table.

2. Run the health checks

  • Aging: deals in a stage longer than 1.5x the average for that stage.
  • Slips: close date moved 2+ times.
  • No next step: no future activity scheduled.
  • Stale: no activity in 14+ days.
  • Single-threaded: one contact engaged.
  • Close date in the past.
  • Stage mismatch: proposal stage without an economic buyer met.

3. Score deal risk

Each failing check adds risk points. High-risk deals in commit move to best case or out, with the reason.

4. Build the forecast

CategoryRule
CommitLow risk, verbal yes or clear paper process, close date backed by a plan
Best caseMedium risk, strong engagement, one open gap
UpsideEarly or high risk
RemoveDead, past due with no response, or no next step for 30 days

Weighted forecast = commit + (best case × historical conversion).

5. Choose the actions

Three to five actions that change the quarter: a deal that needs an executive call, a stalled proposal, a missing champion, pipeline generation if coverage is short.

Output format

Target: X | Closed: X | Gap: X | Coverage: Nx (healthy / thin)
Forecast: Commit X | Best case X | Upside X | Weighted X
Risks: <deal - risk score - failing checks - recommendation>
Actions this week: <action - owner - expected impact>
Pipeline hygiene: N deals with past close dates, N without next steps

What good looks like

  • Every deal moved out of commit has a stated reason.
  • The forecast says what would need to be true for best case to land.
  • Actions are specific, owned and dated.
  • The common mistake is reviewing deals by amount only; a small deal with a signed order form matters more for the forecast than a big deal with no economic buyer.

Rules

  • MUST base risk on evidence (activity, dates, contacts), not on rep confidence.
  • MUST flag past-due close dates and missing next steps.
  • NEVER change records in the CRM without approval; propose updates instead.

Example prompts

  • "Here's our pipeline export. Prep me for Monday's forecast call."
  • "Which of my 30 open deals are most at risk this quarter?"
  • "We need $400k more this quarter. Is the pipeline enough, and what should we do?"

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