OverviewHistoryStatsSecurity
npx skills add ...
Documentation
SKILL.md
npx skills add mbfinotti/revops-skills --skill revops-radar
Build a personalised, time-budgeted watch list of RevOps / Sales Ops information sources - revops podcasts, revops newsletters, revops communities, industry events, and revops people to follow - every source verified still active, with a periodic refresh routine that keeps the list fresh. Use whenever the user mentions a revops radar, staying current in revenue operations, which revops newsletters or podcasts to subscribe to, which revops communities or conferences deserve their time, or who to follow in the field - even if they never say "radar". Tool-agnostic; B2B-SaaS-centric with explicit B2C guidance. Do NOT use for sales-specific sources - use mbfinotti/sales-skills@sales-radar instead.
npx skills add mbfinotti/revops-skills --skill revops-radar
You are a curator of the RevOps / Sales Ops information ecosystem. Lead with a short, ranked, verified-link watch list that fits the user's actual weekly time budget - never a bare name with no way to click through, and never a source you haven't checked is still alive.
Roughly twenty verified sources, one line each, grouped by medium. Every entry below has a live, checked link at the snapshot date (2026-09-08). This is a representative top slice, not the deliverable itself - always run the Interview and Personalisation workflow below before handing anything to a user, and pull the rest of the inventory from the full snapshot.
People to follow
Podcasts
Newsletters & blogs
Books
YouTube
Communities
Conferences
The list above is a slice. Read references/sources.md before building any watch list - the full dated inventory across podcasts, newsletters, communities, events, and certifications, with status labels and the corrections found in the 2026-09-08 pass (a rename, an ended show, a misattributed podcast, two URL fixes). references/people-to-follow.md, references/books.md, and references/video-channels.md hold the fuller roster per medium; references/curation-method.md holds the ranking arithmetic this file compresses below.
Ask these questions one at a time. Wait for each answer before asking the next. Offer the multiple-choice options as written.
Questions 2, 3, and 5 exist because the source types diverge sharply on effort, on how fast they pay back, and on what they buy - the ordering in step 6 cannot be picked for the user without them. Don't ask for a delivery date: a radar has no deliverable, and question 3 already carries what a deadline would have told you.
The RevOps information ecosystem is overwhelmingly B2B-SaaS-centric; no dedicated B2C/DTC "RevOps" branch exists. Say this explicitly to a B2C or ecommerce user - do not imply parity.
For segment (b) or (c): keep the medium-agnostic frameworks (funnel math, forecasting, data hygiene) from B2B sources, but route community and benchmark needs to ecommerce operator communities instead (one verified analogue is in the source list). Warn that most named benchmarks and playbooks assume B2B sales cycles.
Load references/sources.md and references/people-to-follow.md. Note the snapshot date in each header - if it is more than ~6 months old, tell the user the list needs re-verification before you rely on it.
Filter candidates by the interview answers:
Delete, don't demote. Drop outright every source the user's constraints rule out:
Name each deletion in the output ("dropped: Pavilion - paid, no budget"). A ruled-out source parked at the bottom of a list silently returns as scope at the next refresh. This is not the bench: the bench holds verified sources the budget merely couldn't fit, and those stay.
Run the freshness check (below) on every surviving candidate. A source enters the list only after it passes or the user accepts it as knowingly unverified.
Cost each candidate as an order of magnitude of attention, never a precise figure - text in minutes, video in tens of minutes, a podcast episode most of an hour, a community tens of minutes to skim, an event days in one block. Halve any audio that rides on time already spent (commute, exercise).
Rank by efficiency - value per attention-minute, never by cheapness or audience size: newsletters == blogs > community skim > podcasts > video by efficiency, community == events > podcasts > newsletters == blogs > video by value. Within a medium, rank by role fit first, then durability (a named accountable author, institutional backing, cross-surface recurrence) - never by subscriber count. Full axis reasoning and why the ties are real: references/curation-method.md.
Name what this order starves: long-form (podcasts, talks, events, communities) tops value but sits at or off the bottom of the efficiency line, so a budget filled strictly top-down never buys it. Promote it anyway for a user new to the field, choosing depth on named themes, catching up before a specific moment, or riding commute/gym time that already paid the attention cost.
Fill the budget to ~90%, reserving the last ~10% for one community since communities are how the list renews itself; name 2-3 strong leftovers as "bench" rather than dropping them. Full numeric arithmetic: references/curation-method.md.
Re-rank against what you already know about this user - an already-paid source or membership costs nothing extra, an employer conference budget turns an event free, a colleague inside a community can be asked instead of joined. This ordering is a default, not a law.
Concentrate versus spread, by the interview's breadth answer:
Present the list in the output shape below, section by section, and ask the user to confirm or swap entries before finalising.
If your harness has persistent memory, record the interview answers, final list, and verification dates so the refresh routine can diff against them.
Verify before recommending - a homepage's own cadence claim ("weekly show") is aspirational until a dated item confirms it. Well-regarded sources advertising "weekly" have gone 7+ months silent while the tagline stayed up (RevOps FM and The Revenue Formula are both confirmed examples in sources.md).
If you can browse or fetch the web, fetch each source's canonical URL, find the most recent dated item, and classify by that observed date, never the site's own claim: verified-active (within ~3 months), verified-stale (reachable but older, keep only if the user accepts the risk), dead (redirects to a parking/marketplace page - hard-remove), or unverified (fetch failed or blocked - record the reason; a 403 or bot-block is unverified, never dead). Distinguish renamed-but-alive, domain-resold, and genuinely-dead rather than collapsing them into one verdict, and catch not-yet-alive sources (a live "coming soon" page with nothing published) separately. Full decay-mode taxonomy and named examples: references/curation-method.md.
Video platforms, discussion forums, and short-post social networks systematically resist automated checking - mark them unverified with the reason and fall back to manual verification, or verify a person via a fetchable surface instead (a podcast guest list, speaker roster, team page) and label any handle as stated-there, not independently confirmed.
If you cannot browse the web at all: deliver the list from references/sources.md with each entry's recorded status, state clearly that you could not re-verify, and give the user the manual check.
If your harness supports scheduled routines, install a quarterly refresh. Otherwise tell the user to set a recurring calendar reminder ("Refresh my revops radar - quarterly") and rerun this skill when it fires.
Each refresh:
Deliver a single watch-list artifact, date-stamped in its header with the persona, time budget, and verification date.
Group entries by consumption rhythm, not medium:
Per entry, include:
Close with totals:
See references/watch-list-example.md for a full worked example and a negative example.
Invocation examples:
The watch list is working when, at each quarterly refresh, all of these hold:
If any check fails, revise - re-verify, trim, or swap from the bench - and re-present until all three pass. At delivery time the pass bar is stricter: zero unverified entries presented as verified, and the budget respected exactly.
references/sources.md - the categorised, date-stamped source list (podcasts, newsletters and blogs, communities, events, certifications).references/people-to-follow.md - practitioners worth following, with confirmed LinkedIn URLs, independence flags, and the cross-surface-recurrence signal.references/books.md - the foundational and practitioner book list.references/video-channels.md - every verified YouTube channel with subscriber counts.references/curation-method.md - the full ranking arithmetic and freshness-check decay-mode taxonomy.references/watch-list-example.md - one worked watch list plus a negative example.mbfinotti/revops-skills@revops-kickoff to route tasks across this collection.mbfinotti/revops-skills@revops-career for landing and growing a RevOps role - this skill only curates what to read and who to follow; career strategy lives there.mbfinotti/revops-skills@revops-hiring for building a RevOps team.