Identifies upsell and cross-sell opportunities within existing customer accounts. Analyzes product usage, feature gaps, team growth, industry benchmarks, and competitive pressure to surface revenue expansion plays scored by potential, effort, and likelihood. Generates an expansion-playbook.md with account-by-account opportunities, recommended pitch, timing, and approach.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Analyze a customer portfolio and identify every viable upsell, cross-sell, and expansion opportunity, then rank them by revenue potential, effort, and probability of success so the account team knows exactly where to focus. Optimize for total portfolio expansion revenue, not individual deal wins. Ground every recommendation in data signals, not wishful thinking.
references/data-inputs.md -- where to find account data, what to collect, and the product catalogreferences/account-profile.md -- per-account expansion profile and segment benchmarkingreferences/expansion-triggers.md -- seven trigger categories and the opportunity record templatereferences/scoring.md -- three-dimension scoring rubric, composite formula, and tier interpretationreferences/playbook-template.md -- the full expansion-playbook.md output structurereferences/rules-and-edge-cases.md -- behavioral rules and edge-case handlingCollect data. Locate customer data in the working directory and user-specified paths, then assemble the account fields and product catalog. See references/data-inputs.md. If no structured data exists, ask the user to describe their accounts and note reduced scoring confidence.
Profile and benchmark each account. Build an expansion profile per account and compare it against its peer segment to find under-penetration. See references/account-profile.md. Without external benchmarks, use the portfolio's top quartile as the benchmark.
Scan for triggers. Check every trigger category for each account. Record an opportunity only when a trigger fires AND a matching product/feature is available to sell. Capture each as a structured opportunity record. See references/expansion-triggers.md. Flag underutilization as a separate "activation opportunity," not an upsell.
Score and tier. Rate each opportunity on revenue potential, effort, and likelihood (1-10 each), compute the composite, and assign a tier. See references/scoring.md.
Generate the playbook. Write expansion-playbook.md to the working directory (or a user-specified path), sorted by tier and composite score, with pitch, timing, approach, and portfolio-wide insights. See references/playbook-template.md.
Apply the behavioral rules and edge-case handling throughout. See references/rules-and-edge-cases.md.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Audit websites for accessibility issues and WCAG compliance. Use when checking accessibility, fixing a11y issues, or ensuring WCAG compliance.
The English summary is being prepared. Showing the original description.
Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.
The English summary is being prepared. Showing the original description.
Use to test whether an AI agent, prompt, or skill actually works before or after it ships — build a small eval set, score runs, and catch regressions when the prompt or model changes. Trigger when the user asks whether a prompt is good, wants to compare models or versions, sees inconsistent agent output, or is about to put an agent in front of customers.
The English summary is being prepared. Showing the original description.
Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.
The English summary is being prepared. Showing the original description.
Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.
The English summary is being prepared. Showing the original description.
Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.
The English summary is being prepared. Showing the original description.