pipeline-stage-definition-and-exit-criteria
Skill14 starsChanged 8 months agoMITView on GitHub
Define sales stages, exit criteria, and required proof that managers can inspect and RevOps can enforce. Use when the user asks to tighten stage hygiene, standardize progression rules, or connect qualification evidence to forecasting. For specific deal reviews, use deal-inspection-coach. For forecast summaries, use forecast-risk-brief.
In this repository38 other files it gives its agents.
- AGENTS.mdAGENTS.md
- account-brief-builderSkill
- battlecard-builderSkill
- call-insights-to-objectionsSkill
- call-review-coachSkill
- case-study-extractorSkill
- certification-program-builderSkill
- content-gap-analysisSkill
- content-governance-systemSkill
- deal-inspection-coachSkill
- discovery-and-demo-structureSkill
- discovery-rubric-auditorSkill
- enablement-house-styleSkill
- enablement-impact-storySkill
- enablement-metrics-and-instrumentationSkill
- enablement-program-designSkill
- enablement-routerSkill
- executive-briefing-builderSkill
- field-feedback-synthesizerSkill
- forecast-risk-briefSkill
- manager-coaching-cadenceSkill
- mutual-action-plan-builderSkill
- objection-library-builderSkill
- onboarding-program-builderSkill
- onboarding-to-value-playbookSkill
- one-pager-and-slide-outlineSkill
- partner-enablement-packageSkill
- product-launch-enablementSkill
- proposal-rfp-orchestratorSkill
- qbr-ebr-builderSkill
- quarterly-enablement-plannerSkill
- release-notes-to-seller-updatesSkill
- renewal-and-expansion-enablementSkill
- revenue-enablement-contextSkill
- roleplay-scenario-builderSkill
- talk-track-builderSkill
- value-prop-and-positioningSkill
- win-loss-synthesisSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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
- Distinctive: line 22
Ask only for the inputs that change the model:
- Distinctive: line 29
If history is missing, label the model a hypothesis.
- Distinctive: line 33
Read references/stage-exit-framework.md before writing stage cards or governance.
- Distinctive: line 67
Do not inspect a named live deal or produce a forecast brief here.
- Distinctive: line 75
No invented historical rates, thresholds, or CRM capabilities.
≈ “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.
Files
Pipeline stage definition and exit criteria
Define stages that reflect the buyer's progress and give managers consistent evidence for moving a deal forward.
A good stage says what the buyer decided and what proof a manager can inspect. If the user wants one live deal reviewed, use deal-inspection-coach. If they want a period forecast, use forecast-risk-brief.
Buyer-signal exit. "Discovery exits when the buyer names the problem, its cost, and why it is funded this cycle. Required proof: a buyer-authored problem statement or recorded confirmation from the economic buyer."
Activity checklist. "Discovery exits when the AE logs a discovery call and fills the MEDDPICC fields."
The assignment rule should yield one current stage, while allowing earlier evidence to remain true and legitimate regressions to be recorded.
Inputs
Reuse supplied context first. If a missing company fact would change the result, check the relevant sections of .enablement/context.md when available. Preserve source dates and approval limits.
Ask only for the inputs that change the model:
- Current stage map and who operates it
- Historical stage evidence for a representative period, if it exists
- Target motions and the qualification method in use
- The inspection and forecast problems this redesign must fix
If history is missing, label the model a hypothesis. Do not invent conversion rates, aging norms, or CRM behavior.
Supporting material
Read references/stage-exit-framework.md before writing stage cards or governance. Read references/source-system-guide.md when the output must later map into CRM fields and reporting.
Procedure
- Establish the baseline. Find stages that are vague, skipped, slow, frequently regressed, or weakly tied to outcomes. Record data gaps. Done when you can name the broken stages and what evidence you lack.
- Give each stage one buyer signal. One purpose. One reason to move. Done when you can say the buyer state in a sentence a manager would use in a deal review.
- Set entry, exit, and proof. Required proof blocks progression except through a documented exception. Recommended proof coaches; it does not block. Keep required proof to the minimum buyer-validated evidence that reduces that stage's named risk.
- Name the anti-patterns. Sent proposal, booked meeting, populated field, and seller assertion are activity until buyer evidence shows what changed. Write how managers handle exceptions.
- Map to the qualification method. Attach only the MEDDPICC, SPICED, or local checks that belong to this stage's risk. Do not reprint the whole framework on every card.
- Backtest before rollout. Apply the criteria to won, lost, no-decision, and open deals. Report how many would progress, remain, regress, or need an exception. If history cannot support that, define a pilot.
- Set inspection and rollback. Define the manager and RevOps review rhythm, pilot measures, rollback owner, and restoration path. Use historical or owner-approved thresholds; otherwise name who must set them. Separate changes in recorded stage from changes in actual buyer progress.
- Map to systems last. Design the operating logic first. Then recommend fields, notes, and dashboards. Do not move live opportunities or flip required fields without explicit approval.
What to return
For a stage repair, return the changed criteria and adjacent-stage effects. For a full model, include:
- Stage cards: name, buyer state, purpose, entry, exit, required proof, recommended proof, exception owner
- Historical baseline and backtest, including data limits
- Anti-patterns and exception rules
- Inspection cadence by role
- Qualification-method notes only where they change a gate
- CRM and reporting recommendations
- Transition, pilot, and rollback plan
- Assumptions, if you had to make any
Do not inspect a named live deal or produce a forecast brief here.
Quality bar
- A manager can pass or fail a deal against a stage without a side conversation.
- Required proof is minimal, buyer-validated, and distinct from coaching evidence.
- Stages are mutually exclusive enough to report.
- Backtest findings or an explicit pilot hypothesis are present.
- No invented historical rates, thresholds, or CRM capabilities.
- System changes stay recommendations.
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
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.

