// Business & Operations

Qualified Demand Ledger

Classify launch, outreach, checkout, payment, usage, and review-time evidence without counting views, deployments, sent messages, or owner tests as demand.

We earn a commission on eligible purchases after a new Agensi signup through these links. We also sell our own skills on Agensi.

Get it on Agensi Find another skill $5 one-time

Format: Agent skill, not a browser app. You need an AI agent that can load its instructions and use the required tools.

Package requirements: SKILL.md-compatible agents that can run a local Python helper. Python 3.10 or newer on Windows, macOS, or Linux. One documented UTF-8 JSON input containing 1 through 1,000 normalized events.

You get: A deterministic evidence classification with stable event buckets, findings, and JSON and Markdown reports with SHA-256 receipts.

Licence and purchase details

Review the package licence at the destination.

Review the offer and access method at your chosen marketplace. Agensi provides connected-agent access, not a download. Buying a skill does not include an AI-agent subscription or setup service.

Agensi access: This product’s bundled-script workflow through Agensi has not been verified here. Tests of other products do not establish this package’s compatibility. Local setup examples apply to separately obtained downloadable packages.

See tested hosts, versions and workflow limits.

What problem does Qualified Demand Ledger solve?

Commercial experiment reports often mislabel exposure, sent outreach, owner-controlled checks, and operational activity as demand or revenue.

Use it to

Audit whether a launch report mislabeled impressions or directory exposure as demand
Separate owner-controlled checkout and payment verification from external buyer behavior and revenue
Reconcile attributed clicks, buyer questions, checkout openings, installs, settlements, commissions, and recurring use
Produce a stable receipt before an agent claims a commercial experiment worked

What it returns

Deterministic commercial-evidence classification
Qualified demand, revenue, retention, exposure, operations, candidate, and exclusion buckets
Stable findings and bucket event IDs
JSON and Markdown reports with SHA-256 receipts

A representative input and result

fixture-backed sample

input A directory impression, an owner verification payment, an external buyer question with direct attribution, a verified settlement, and a recurring use event two days later for the same opaque actor and product.

result Exposure and owner activity remain outside demand and revenue. The buyer question counts as qualified demand, the settlement counts in its own currency, and eligible later use counts as retention with stable findings and receipts.

Access and approval boundaries

Terminal permission to run the bundled local Python classifier.
Read access to one user-selected UTF-8 JSON input.
Write access only to optional user-selected JSON and Markdown report paths.
No browser, network, credential, account, environment-variable, messaging, payment, or publication permission.

Known limitations

The ledger classifies caller-supplied normalized evidence and does not retrieve or authenticate analytics, payment, marketplace, or customer data.
Opaque actor tokens are required, but the helper cannot prove that every source label or evidence reference is free of personal data.
It does not merge or convert currencies.
Direct or verified attribution remains a caller-supplied claim unless backed by a protected external record.
A clean ledger is an accounting result, not a forecast of demand, revenue, retention, profitability, or product-market fit.

// choose with context

Is Qualified Demand Ledger the right skill?

Best fit

An operator needs to separate qualified demand and verified revenue from exposure, owner tests, sent outreach, directory activity, and other operational evidence.

It returns

A deterministic evidence classification with stable event buckets, findings, and JSON and Markdown reports with SHA-256 receipts.

Do not use it as

It does not retrieve or authenticate analytics, payment, marketplace, or customer records, contact buyers, or prove product-market fit.

Compatibility, access, version, and licence

Reads or accesses: Declared local scope: one owner-selected local JSON input, optional owner-selected JSON and Markdown output paths.
Compatibility: SKILL.md-compatible agents that can run a local Python helper. Python 3.10 or newer on Windows, macOS, or Linux. One documented UTF-8 JSON input containing 1 through 1,000 normalized events.
Version: 1.0.0
Licence: Review the package licence and seller terms at the linked destination.

What happens next

Open the Agensi listing, check the current offer and connect a supported agent. Agensi loads the skill through its connector; it no longer provides a download. Approve any purchase before use. Check Agensi’s current connection guide before changing an existing connection.

Questions

Does it connect to Stripe, Agensi, analytics, or my inbox?

No. It processes one local normalized JSON input and makes no network request.

Do impressions, views, reactions, deployments, or sent messages count as demand?

No. They remain exposure or operations even when numerous.

Can an owner-funded verification payment count as revenue?

No. Owner-controlled or non-external activity remains operations.

How does it count external revenue?

Only external settlement or commission evidence with strong attribution, positive amount, currency, and transaction or settlement identifier enters revenue.

How does it count retention?

Recurring use must have strong attribution and an eligible in-window, uniquely evidenced, external non-owner parent for the same opaque actor and product at least 24 hours earlier.

Does the SHA-256 receipt prove the events are true?

No. It proves which normalized input and report core were processed.

Does a clean report mean the product has demand?

No. It only means the supplied events were classified under the documented rules.