Staged Pipeline Runner
Run a task as discrete stages, each validated before the next begins, so failures surface where they were caused.
Before & after
Same prompt, same agent — the only difference is the skill.
Sales pipelines are essential for forecasting and execution. To set up one that works for you, I should ask about your sales cycle length, deal stages, and what metrics matter most. Do you sell to consumers or enterprises? What's your typical sales process—demo, negotiation, contract? How many deals are you typically juggling? I'd suggest thinking about your funnel stages and tracking conversion rates at each. What CRM are you using, or do you need help choosing one?
SALES PIPELINE STRUCTURE & MANAGEMENT DEAL STAGES (6 total, customize per your process) STAGE 1: PROSPECT (Probability 10%) Deal entered → Inbound lead or cold outreach qualified Actions → Qualify fit (business size, budget, use case) Avg time → 2-5 days Example → Signed demo request STAGE 2: DISCOVERY (Probability 25%) Deal entered → Initial call or demo scheduled Actions → Understand pain points, map to product Avg time → 1-2 weeks Example → Scheduled call completed, next meeting set STAGE 3: PROPOSAL (Probability 50%) Deal entered → Quote/proposal sent Actions → Follow up, address objections, negotiate terms Avg time → 1-3 weeks Example → Waiting on internal approval from client STAGE 4: NEGOTIATION (Probability 75%) Deal entered → Contract terms discussed Actions → Legal review, final pricing confirmation Avg time → 1-2 weeks Example → Final terms agreed, awaiting signature STAGE 5: CLOSED WON (Probability 100%) Deal entered → Contract signed, payment received Actions → Onboarding kickoff, handoff to CS Avg time → Transaction complete Example → Customer live on platform STAGE 6: CLOSED LOST (Probability 0%) Deal entered → Deal no longer viable Actions → Document reason, attempt win-back Reason tracking → Budget, competition, timing, fit KEY METRICS TO TRACK Total pipeline value → Target 3x-4x quarterly revenue goal Stage conversion rate → Stage 1→2: 60%, 2→3: 50%, 3→4: 70%, 4→5: 80% Avg deal size → Actual vs. target Days per stage → Benchmark against historical Velocity → Deals closing per week (track momentum) WEEKLY REVIEW CHECKLIST Pipeline total → Enough deals at each stage? At-risk deals → Any stalled beyond avg stage time? Big wins coming → Next 30 days closing forecast Activity → Calls booked, proposals sent (leading indicators)
About this skill
name: pipeline description: Use when Structured Claude skill that gives Claude a repeatable workflow for pipeline.
Pipeline
One of 337+ skills in the original author's multi-agent claude-skills mega-collection (~19k GitHub stars). Packages the Pipeline workflow with its own instructions and validation so outputs stay consistent.
What you get
- Public GitHub repo (alirezarezvani/claude-skills)
- the pipeline skill folder with SKILL.md. Part of a 337-skill / 30-agent / 70-command install.
Customize your output
- Fork the repo and adapt the skill's instructions and references to your workflow.
Example output
Activates automatically when your request matches Pipeline; chains with the other skills, agents, and commands in the collection.
Best for
Creators, builders, and teams using Claude Code.
SKILL.md preview
---
name: pipeline
description: Use this skill when a multi-stage workflow needs to run as a pipeline with validation gates between stages instead of one undifferentiated pass.
version: 1.0.0
category: AI Agents / Development
author: AgentVolt
license: proprietary
tags:
- ai-agents
- development
---
# Pipeline
Runs a task as a sequence of discrete stages, each validated before the next begins, so failures surface at the stage that caused them.
## When to use
… (sign up to view the full skill)More ai & agents skills
View all AI & Agents skills →Skill Status Report
Scan every skill in a project and report which pass validation, which are stale, and which lack required metadata.
Skills Scaffolder
Scaffold a new skills directory — folder structure, metadata, a baseline validation pass — with the right conventions from day one.
Research Bundle
Run a multi-step research task as one pipeline: gather sources, extract findings, validate consistency, emit one structured bundle.
Workspace Admin
Administer a Cowork or Claude workspace — settings, access, configuration — with every change scoped and verified.