reply-team/jason-ai / skills/business/sdr-operations
sdr-operations
Verifiedoperations/20-measurement.yaml
View on GitHub# Family 20 — Measurement (10)
#
# Reading the numbers honestly. Every figure carries its measurement envelope — as-of, window,
# basis, denominator and detection method — because without it a number is not evidence.
#
# Schema, the derivation table and the meters: families.yaml.
family: 20
operations:
- name: engagement.summarize
core: true
intent: >
"How is this doing?" — one measure set over one scope, grouped the way the question actually
needs.
reach: read
reversibility: reversible
approval: auto
approval_departs: false
before_repeating: >
nothing at stake, but two runs are only the same number if as-of, window, basis, denominator and
detection method all match.
idempotency_key: none
per_item_results:
value: required
detail: one row per group, each with its own envelope.
cost: none
questions: []
- name: engagement_event.list
intent: >
"Show me the rows behind the number"
reach: read
reversibility: reversible
approval: auto
approval_departs: false
before_repeating: nothing at stake
idempotency_key: none
per_item_results: required
cost: none
questions: []
- name: funnel.summarize
intent: >
"The whole ladder, stage by stage, with each stage's declared denominator and how well each stage
can be known at all"
reach: read
reversibility: reversible
approval: auto
approval_departs: false
before_repeating: nothing at stake
idempotency_key: none
per_item_results: required
cost: none
questions: []
- name: opportunity.summarize
intent: >
"What came out the far end, and what was it worth — under which attribution model, on whose
authority?"
reach: read
reversibility: reversible
approval: auto
approval_departs: false
before_repeating: >
nothing at stake — and these values move retroactively, so a figure is only meaningful with its
as-of.
idempotency_key: none
per_item_results: required
cost: none
questions: []
- name: attribution.explain
intent: >
"Why was this outcome credited here, and what would a different model have said?"
reach: read
reversibility: reversible
approval: auto
approval_departs: false
before_repeating: nothing at stake
idempotency_key: none
per_item_results: required
cost: none
questions: []
- name: response_time.summarize
intent: >
"How fast do we actually pick things up" — an inbound lead from arrival to first human touch, a
reply from arrival to answer — by owner, route, source and hour of day.
reach: read
reversibility: reversible
approval: auto
approval_departs: false
before_repeating: nothing at stake
idempotency_key: none
per_item_results: required
cost: none
questions: [5]
- name: metric.describe
intent: >
"What does this measure actually mean here, what was it mapped from, what can it be grouped by,
and how much can it be trusted?"
reach: read
reversibility: reversible
approval: auto
approval_departs: false
before_repeating: nothing at stake; read it before planning anything around a measure
idempotency_key: none
per_item_results: required
cost: none
questions: []
- name: metric.compare
intent: >
"Two arms, side by side" — the counts, the sample size this comparison needs, the interval around
each rate, and whether there is enough data to say anything at all.
reach: read
reversibility: reversible
approval: auto
approval_departs: false
before_repeating: >
nothing at stake — but re-reading and stopping when it looks good invalidates the result, so the
intended sample size, the observed sample size and the number of reads are all returned.
idempotency_key: none
per_item_results: required
cost: none
questions: [13]
- name: export.request
intent: >
"Get me a bounded extract for reporting" — never the route for a subject access request, which is
`privacy_request.fulfill`.
reach: control
reversibility: reversible
approval: confirm_once
approval_departs: true
approval_reason: >
raised because an extract moves personal data out of the system where its handling rules are
enforced.
before_repeating: the state of the export already requested under this key
idempotency_key:
value: required
detail: a replayed export produces a second copy of personal data.
accepts_collection: false
per_item_results: not_applicable
cost:
value: metered
conditional: true
detail: metered where the extract consumes an allowance.
cost_basis: per call
meter: request
questions: [24]
- name: export.get
intent: >
"Collect the extract"
reach: read
reversibility: reversible
approval: auto
approval_departs: false
before_repeating: nothing at stake; the extract is stable once complete
idempotency_key: none
per_item_results: not_applicable
cost: none
questions: [24]
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |