More screenshots
Works with the AI tools you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsClient Discovery Automation Blueprint
Turn messy client discovery notes into a proof-labelled automation blueprint with process maps, feasibility gates, scope boundaries, data requirements, and pilot acceptance checks.
$12
Client Discovery Automation Blueprint
Example session with this skill installed
We are an operations consultancy reviewing discovery notes from a property-management client. They receive maintenance requests from tenants through a web form, phone calls, and emails. A coordinator manually copies each request into a shared spreadsheet, then messages an on-call technician. Urgent plumbing and electrical issues must be reviewed by the property manager before a technician is dispatched. The client wants “everything automated” within two weeks.
Supplied details
- The web form collects tenant name, unit, category, free-text description, and callback number.
- Phone and email requests are not standardized.
- The spreadsheet is described as the current tracking place, but no field list or record ID is supplied.
- The on-call technician roster changes weekly; its system of record is not supplied.
- The property manager approves urgent plumbing and electrical dispatches by phone today.
- The client says duplicate requests are common after tenants call and also submit the form.
- Success means the coordinator stops retyping ordinary web-form requests and managers still approve urgent dispatches.
Create an automation discovery blueprint. Do not choose a platform, configure a workflow, assume any system has an API, or estimate a project price. Show which opportunity is ready for a discovery pilot and what must remain conditional or manual.
- Read your context and instructions
- Compiled the client discovery automation
- Generated the UI component
Discovery Verdict
CONDITIONAL. A bounded discovery pilot for ordinary web-form maintenance requests is plausible because its submitted fields and the desired outcome are supplied. It cannot be treated as build-ready until the tracking record, a stable request identifier, technician-roster ownership, duplicate rule, and approval handoff are confirmed. Urgent plumbing and electrical dispatches must remain human-approved.
Evidence Ledger
| Label | Evidence or conclusion | Why it matters |
|---|---|---|
| Confirmed | The web form collects tenant name, unit, category, description, and callback number. | Defines the known source fields for ordinary requests. |
| Confirmed | A coordinator copies requests into a shared spreadsheet and messages an on-call technician. | Identifies retyping and notification as current manual work. |
| Confirmed | Urgent plumbing and electrical dispatches require property-manager review. | Prevents an unsafe automatic dispatch path. |
| Confirmed | Duplicate requests are common when tenants call and also submit the form. | A pilot needs a duplicate-review path. |
| Unknown | Spreadsheet columns, row ownership, and request ID. | The proposed target record and a stable identifier are not yet known. |
| Unknown | Where the weekly technician roster is maintained and who updates it. | Routing cannot be promised. |
| Recommendation | Start with ordinary web-form intake only. | It has the clearest supplied trigger and measurable manual-retyping reduction. |
Current-State Process
- A tenant submits a web form, calls, or sends an email.
- The coordinator interprets the request and retypes it into the shared spreadsheet.
- The coordinator identifies an on-call technician and messages that person.
- For plumbing or electrical issues described as urgent, the property manager reviews the dispatch by phone.
- A tenant may submit the form after calling, creating a potential duplicate.
Automation Opportunity Register
| Opportunity | Current friction | Proposed boundary | Human decision | Feasibility | Evidence gap |
|---|---|---|---|---|---|
| Create one reviewable intake item from an ordinary web-form request | Coordinator retypes known form fields. | Web-form requests only; no automatic dispatch. | Coordinator corrects missing or ambiguous information. | READY FOR DISCOVERY PILOT | Confirm tracking fields and one stable request key. |
| Route a request to the on-call technician | Roster lookup and notification are manual. | Recommend a technician only after roster ownership is confirmed. | Coordinator confirms recipient. | CONDITIONAL | Roster source, update owner, availability rule, and notification policy. |
| Dispatch urgent plumbing or electrical requests | Time-sensitive but approval is mandatory. | Create a review item only; do not dispatch. | Property manager approves dispatch. | KEEP MANUAL | Approval record, escalation timing, and outcome receipt. |
| Merge form, phone, and email requests | Duplicates are common across channels. | Flag potential duplicates for review. | Coordinator decides whether two requests are the same. | CONDITIONAL | Duplicate-match rule, matching fields, and audit requirement. |
Data, Ownership, and Approval Requirements
The pilot needs the spreadsheet field list, owner, and permitted write boundary; a stable request identifier or an agreed temporary correlation rule; the definition of an ordinary request; and the named coordinator who reviews duplicate or missing data cases. The technician roster and any messaging destination remain outside the first pilot until their source and owner are supplied. Urgent dispatch remains behind the property manager’s approval.
Scope Fence and Risks
Included pilot outcome: an ordinary web-form submission produces one traceable review item containing the supplied form fields, without automatic dispatch.
Excluded: phone and email parsing, technician routing, urgent dispatch, client notifications, pricing, and production deployment.
Risks: unverified spreadsheet structure, duplicate matching, and changing roster ownership. Each requires buyer confirmation before expansion.
Clarification Questions
- Which spreadsheet columns and row identifier are the authoritative tracking record?
- What exact category and wording make a request urgent?
- Who owns the technician roster, where is it maintained, and how often is it updated?
- Which fields may be used to flag a possible duplicate, and who makes the final merge decision?
- What observable record proves that the coordinator did not need to retype the request?
Pilot Recommendation and Acceptance Checks
Run one reversible, non-dispatch pilot with redacted ordinary web-form records after the field map is confirmed.
- Given a qualifying form submission, one review item contains the supplied tenant, unit, category, description, and callback data plus a traceable request key.
- Given a required field is absent, the item is marked for coordinator review rather than treated as complete.
- Given a potential duplicate, no second dispatch or notification is initiated; the case is visible for coordinator review.
- Given an urgent plumbing or electrical category, the pilot creates no dispatch and routes the case to the named property-manager approval step.
client-discovery-automation-blueprint.tsx
TSX · React component
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
A client says “we need automation,” but discovery notes often mix verified facts, hoped-for outcomes, missing access, policy constraints, and assumptions. Starting with a Make scenario or a quote too early turns those gaps into rework, scope creep, and unreliable promises.
Client Discovery Automation Blueprint converts supplied call notes, transcripts, emails, forms, and SOPs into a decision-ready package before implementation begins. It reconstructs the current process, labels evidence, finds repeatable work, and evaluates each candidate separately. The result makes clear what is ready for a small discovery pilot, what is conditional, what is not ready, and what should stay manual.
What you provide: the discovery material you already have. It can be a rough call transcript, CRM notes, an internal SOP, a form, or a description of the current process. Add field lists, system notes, approval rules, volumes, or success criteria when available.
What you receive:
- An Evidence Ledger that separates confirmed facts, assumptions, unknowns, and recommendations.
- A current-state process map with owners, inputs, outputs, decisions, and friction.
- An Automation Opportunity Register with a feasibility verdict for each candidate.
- Required data, stable identifiers, system-of-record, approval, exception, and manual-fallback requirements.
- A scope fence, risk register, and decision-focused clarification questions.
- The smallest reversible pilot recommendation with observable acceptance checks.
The skill is deliberately pre-implementation. It does not select Make, Zapier, n8n, or another vendor; claim an API or connector exists; configure workflows; access systems; quote a project; or promise a client outcome. That boundary makes the blueprint suitable for responsible discovery and a clean handoff to the implementation stage.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 17 days ago
- Passed all security checks, Safe to install