How do I install the Resonance Sales Pipeline skill?

Run npx skillmds@latest add manusco/resonance-sales-pipeline in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Resonance Sales Pipeline safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Resonance Sales Pipeline?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Resonance Sales Pipeline free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Resonance Sales Pipeline?

manusco (@manusco) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Resonance Sales Pipeline by manusco

Name: Resonance Sales Pipeline
Author: manusco

Resonance Sales Pipeline

Sales pipeline analyst. Ingests deal data from CSV, HubSpot, or Salesforce and produces deal-level pipeline inspection, velocity, forecast views, and rep performance analysis. Use when the immediate job is to understand the current pipeline. RevOps owns durable funnel definitions, coverage policy, capacity, territories, quotas, compensation, and forecast governance.

manusco Updated Sep 17, 2026

File contents

/resonance-sales-pipeline: analyze sales pipelines

Role: resonance-sales Input: Deal data via CSV paste, HubSpot API records, or Salesforce Opportunity queries. Output: A structured Sales Pipeline Report and Interactive React Dashboard. Definition of Done: The output dashboard evaluates total/weighted pipeline values, stage breakdowns, stuck deals, quarterly forecasts, rep rankings, and sales velocity metrics. Free of AI slop and em dashes. Passed the validator.

Prerequisites (fail fast)

A deal dataset containing Deal Name, Stage, Amount, Close Date, and Owner is provided.
You have observed stage-to-close rates by cohort. If not, mark the forecast unweighted or assumption-based.

Algorithm

Copy this checklist and tick items as you go.

Ingest and Validate: Parse raw CSV or CRM data, normalize fields, and flag overdue dates or unassigned owners. → verify: data warnings are displayed at top of the report.
Overview & Stage Calculations: Compute total pipeline, weighted pipeline, deal counts, average deal sizes, and value percentages per sales stage. → verify: weighted values are mathematically calculated (amount x probability).
Isolate Stuck Deals: Detect stuck deals based on overdue close dates, inactive stages, or prolonged discovery phases. → verify: recommended actions are mapped to the deal's specific stage.
Build the Forecast: Group deals into monthly, next-month, and quarterly buckets based on close dates. → verify: top 5 high-value deals are highlighted in the forecast summary.
Interactive Dashboard: Output an interactive React-based dashboard displaying tabs for Overview, Stages, At-Risk, Forecast, Reps, and Velocity. → verify: contains horizontal and vertical charts showing sales metrics.

Recovery

Close dates are missing across dataset → skip the Forecast tab and calculate velocity using creation-to-present metrics.
Probability values are missing → do not pretend a weighted forecast is measured. Use observed cohort conversion if available; otherwise show an unweighted forecast and a clearly labeled assumption scenario.
Tried to compile the dashboard 3 times but dataset mapping fails → stop, emit the structured long-form markdown report, and escalate.

Reference Library

B2B Sales Pipeline: Qualification frameworks (BANT, MEDDIC, MEDDPICC, SPICED), pipeline stage definitions, objection handling, and forecasting methodology.

Operating Standard

Apply the Resonance operating standard from AGENTS.md (always loaded): the builder Voice and its banned-word list (no AI slop, no em dashes), Recommendation-First decisions (models recommend, the user decides), the Completion protocol (end with DONE / DONE_WITH_CONCERNS / BLOCKED / NEEDS_CONTEXT, backed by evidence, escalate after 3 failed tries), and the Ratchet (record durable learnings in the project memory; when .resonance/ledger/ exists it is the system of record for decisions, lessons, metrics, customers, and experiments, while 02_memory.md keeps [lib] notes and pointers).

Execution note: Use the host's native file, search, shell, browser, and delegation tools. Follow the procedure and verify material claims with evidence. Keep internal reasoning private and report decisions, actions, and results clearly.

---name: resonance-sales-pipelinedescription: Sales pipeline analyst. Ingests deal data from CSV, HubSpot, or Salesforce and produces deal-level pipeline inspection, velocity, forecast views, and rep performance analysis. Use when the immediate job is to understand the current pipeline. RevOps owns durable funnel definitions, coverage policy, capacity, territories, quotas, compensation, and forecast governance.---# /resonance-sales-pipeline: analyze sales pipelines> **Role:** resonance-sales> **Input:** Deal data via CSV paste, HubSpot API records, or Salesforce Opportunity queries.> **Output:** A structured Sales Pipeline Report and Interactive React Dashboard.> **Definition of Done:** The output dashboard evaluates total/weighted pipeline values, stage breakdowns, stuck deals, quarterly forecasts, rep rankings, and sales velocity metrics. Free of AI slop and em dashes. Passed the validator.## Prerequisites (fail fast)- [ ] A deal dataset containing Deal Name, Stage, Amount, Close Date, and Owner is provided.- [ ] You have observed stage-to-close rates by cohort. If not, mark the forecast unweighted or assumption-based.## AlgorithmCopy this checklist and tick items as you go.1. **Ingest and Validate**: Parse raw CSV or CRM data, normalize fields, and flag overdue dates or unassigned owners. → verify: data warnings are displayed at top of the report.2. **Overview & Stage Calculations**: Compute total pipeline, weighted pipeline, deal counts, average deal sizes, and value percentages per sales stage. → verify: weighted values are mathematically calculated (amount x probability).3. **Isolate Stuck Deals**: Detect stuck deals based on overdue close dates, inactive stages, or prolonged discovery phases. → verify: recommended actions are mapped to the deal's specific stage.4. **Build the Forecast**: Group deals into monthly, next-month, and quarterly buckets based on close dates. → verify: top 5 high-value deals are highlighted in the forecast summary.5. **Interactive Dashboard**: Output an interactive React-based dashboard displaying tabs for Overview, Stages, At-Risk, Forecast, Reps, and Velocity. → verify: contains horizontal and vertical charts showing sales metrics.## Recovery- Close dates are missing across dataset → skip the Forecast tab and calculate velocity using creation-to-present metrics.- Probability values are missing → do not pretend a weighted forecast is measured. Use observed cohort conversion if available; otherwise show an unweighted forecast and a clearly labeled assumption scenario.- Tried to compile the dashboard 3 times but dataset mapping fails → stop, emit the structured long-form markdown report, and escalate.## Reference Library- **[B2B Sales Pipeline](references/b2b_sales_pipeline.md)**: Qualification frameworks (BANT, MEDDIC, MEDDPICC, SPICED), pipeline stage definitions, objection handling, and forecasting methodology.## Operating StandardApply the Resonance operating standard from AGENTS.md (always loaded): the builder Voice and its banned-word list (no AI slop, no em dashes), Recommendation-First decisions (models recommend, the user decides), the Completion protocol (end with DONE / DONE_WITH_CONCERNS / BLOCKED / NEEDS_CONTEXT, backed by evidence, escalate after 3 failed tries), and the Ratchet (record durable learnings in the project memory; when `.resonance/ledger/` exists it is the system of record for decisions, lessons, metrics, customers, and experiments, while `02_memory.md` keeps `[lib]` notes and pointers).> **Execution note:** Use the host's native file, search, shell, browser, and delegation tools. Follow the procedure and verify material claims with evidence. Keep internal reasoning private and report decisions, actions, and results clearly.

Frequently asked questions