Skip to content

mbfinotti/advertising-skills / skills/advertising-hiring

advertising-hiring

Verified

Build the complete hiring packet for a paid-advertising role - the rung decision (media buyer vs performance marketer vs growth marketer; creative strategist is its own role), an outcome scorecard, a 2-3 round interview loop with a judgment-first question bank, a time-boxed in-interview work sample, and a 30-60-90 ramp with staged spend authority. For the marketing leader or founder recruiting. Use for "hire a media buyer", "interview questions for a performance marketer", "paid media work sample", "scorecard for our first ad hire", or "30-60-90 for a new paid media hire". Does not source candidates, post jobs, run applicant tracking, or write offers, and does not cover the candidate side - that is the sibling mbfinotti/advertising-skills@advertising-career.

evals/evals.json

View on GitHub
{
  "skill_name": "advertising-hiring",
  "evals": [
    {
      "id": 1,
      "prompt": "We're Maren & Oak, a DTC home-goods brand doing about $9M a year. I've been running our Meta and Google accounts myself at roughly $80k/month combined, and we want to launch TikTok next quarter. I'm ready to make our first dedicated ad hire and I think the obvious move is a really strong Meta media buyer, since Meta is 70% of spend. Can you scope the role and write the requirements? Conversion tracking is mostly right I think - we've never actually reconciled it against Shopify. Panel would be me (founder) and our head of ops, and we can realistically run two rounds. I need someone producing this quarter, and I want this to be an in-house capability we keep long term.",
      "expected_output": "A role-scoping response that names the rung in writing, overrides the proposed single-channel specialist with the generalist performance-marketer default for a first hire, and delivers a scorecard-shaped role definition with mission, ranked dated outcomes, and competencies.",
      "files": [],
      "expectations": [
        "Names the rung as an explicit written decision before or at the head of the role definition",
        "Recommends the performance-marketer generalist rung, overriding the user's proposed Meta-specialist media buyer",
        "Grounds the override in the first-hire rule: the first dedicated hire owns measurement and channel choice, never a single channel",
        "Uses the unreconciled Shopify tracking as evidence the seat must own measurement",
        "States that a dedicated Meta buyer gets added alongside the generalist later once spend passes roughly $50k/month or three-plus channels run, rather than hired instead of the generalist now",
        "Names the growth-marketer rung as the option the default ordering starves, with the condition that would promote it",
        "States which condition moved the pick off the default rung, or states that nothing did",
        "Writes a one-line mission for the role",
        "Lists 3 to 6 ranked outcomes, each with a date",
        "Includes a measurement-validation outcome such as platform-versus-backend reconciliation among the top outcomes",
        "Lists 4 to 6 competencies",
        "Separates must-haves (capped around 5 to 7) from nice-to-haves, with disqualifiers listed separately",
        "Excludes platform certifications from the must-have bar and from competence scoring",
        "Warns that a TikTok channel verdict needs 3 to 6 months, against the producing-this-quarter pressure",
        "Fits the interview loop into the two rounds the panel can run"
      ]
    },
    {
      "id": 2,
      "prompt": "I run Brindle Analytics, a 4-person bootstrapped B2B SaaS at $21k MRR. We can put about $3,500/month into LinkedIn ads. Honestly our positioning is still in flux - we're rewriting the homepage for the third time and pricing changes almost monthly. I want to hire a part-time performance marketer in the next 3 weeks, and if the ads don't show pipeline within 6 weeks we'll shut the channel down and let them go. Build me the hiring packet: scorecard, interview loop, and a work sample.",
      "expected_output": "A response that runs the hire-at-all gate, recommends against hiring now on three named gate failures, deletes the hire from the menu until fundamentals are fixed, and ranks agency, freelancer, and self-manage as the bridge instead of building the requested packet.",
      "files": [],
      "expectations": [
        "Applies a hire-at-all gate before building anything, instead of delivering the packet as asked",
        "Recommends against making the hire now",
        "Cites the monthly budget below the roughly $5,000 threshold as a gate failure",
        "Cites missing marketing fundamentals (positioning and pricing in flux) as a gate failure",
        "Cites the 6-week verdict window as a gate failure, since judging a channel takes 3 to 6 months",
        "States the hire is deleted from the menu until the missing fundamentals are fixed, not merely deferred or ranked last",
        "Ranks the alternatives in the order agency, then freelancer, then self-manage",
        "States the ranking basis as channel coverage bought per hour of the founder's own time",
        "Acknowledges the trade-off: the agency costs the most money and control while consuming the fewest founder hours",
        "Flags the freelancer's worker-classification exposure as a compliance cost the agency route does not carry",
        "Warns against comparing agency retainer fees to in-house salaries, directing the comparison to hours returned and channels covered",
        "States the in-house hire remains the destination once the gate passes - the alternatives are a bridge, not a replacement",
        "Does not proceed to build the requested scorecard, interview loop, and work sample for an immediate hire",
        "Points out the 6-week judgment plan would fire any hire before a ramp or channel verdict could complete"
      ]
    },
    {
      "id": 3,
      "prompt": "We're Copperline, a B2B fintech, hiring a senior performance marketer. Here's my draft screen. Must-haves: has managed $250k+/month, Google Ads certified, Meta Blueprint certified. Interview questions: (1) What's the formula for CTR and for ROAS? (2) What's your favourite bid strategy? - I want to hear target ROAS. (3) How does Performance Max work under the hood? (4) Walk me through best practices for structuring an account. A candidate who answers with clean best practices gets top marks. Tighten this into a question bank and scorecard for me.",
      "expected_output": "A rebuilt question bank that converts the spend figure into a paired filter, strips certifications from the bar, replaces recall questions with judgment probes including the two senior filters, and inverts the scoring so best-practices recitation fails.",
      "files": [],
      "expectations": [
        "Reclassifies spend-under-management as a filter, never a seniority level or bar",
        "Pairs the $250k/month screen with a walk-me-through-a-campaign-you-killed probe",
        "Pairs the spend screen with an incrementality-versus-attribution probe",
        "Removes both certifications from must-haves and from competence scoring, treating them as a floor rather than a signal",
        "Notes free certifications can be earned after hire in days, so a strong candidate is never rejected over a missing one",
        "States that if partner compliance genuinely requires a certification, the req must say so explicitly so it is not read as a skill bar",
        "Rejects the favourite-bid-strategy question as having one right answer - the strong answer is it-depends reasoning, not the target-ROAS reply the user wants to hear",
        "Inverts the scoring rule: an answer citing best practices or default methods as its rationale fails rather than earning top marks",
        "Replaces formula-recall questions with questions probing reasoning about relationships between metrics",
        "Includes a ROAS-drop diagnostic filter expecting the fixed order: measurement first, then media, then creative, then post-click",
        "Includes the backend discriminator: low ROAS with stable backend sales points to tracking or attribution gaps, not true underperformance",
        "Includes the second senior filter: translating platform ROAS into break-even ROAS and MER, noting platform ROAS is biased upward because platforms double-claim conversions",
        "Maps every question to exactly one competency",
        "Includes at least one exaggerator probe, such as who they admire in the field, what publications they read, or claimed mastery of the newest automated campaign types as a lying signal",
        "Weights commercial reasoning and communication over technical recall, with any numeric weighting labelled a house convention rather than a published standard"
      ]
    },
    {
      "id": 4,
      "prompt": "At Fernhollow, a DTC supplements brand spending about $60k/month, we're hiring a paid media manager. Our current final round is a take-home: candidates get logins to a copy of our ad account and 4 hours to build a full media plan and restructure proposal, unpaid, due within 3 days. Two finalists just withdrew this month. Finance has rejected any budget for paid candidate work. Our head of growth is a former agency buyer who is great at reading accounts live. Fix our work-sample stage.",
      "expected_output": "A work-sample redesign that removes the unpaid take-home outright, installs a time-boxed live screen-share audit inside the interview, deletes the paid trial and job shadow by name for lack of budget, and bakes in rubric-first grading with deliberate ambiguity.",
      "files": [],
      "expectations": [
        "Removes the multi-hour unpaid take-home outright, rather than shortening it or making it optional",
        "Attributes the two withdrawals to the format: senior candidates decline unpaid exercises, silently shrinking the funnel",
        "Recommends the live screen-share account audit as the replacement, enabled by the panelist who can grade an audit in real time",
        "Keeps the exercise inside the interview, time-boxed to 60 to 90 minutes",
        "Deletes the paid trial from the menu by name because paid candidate work has no budget approval",
        "Deletes the job shadow on the same no-budget constraint",
        "Records the deleted formats by name in the packet so they cannot resurface as an unscoped round",
        "Specifies synthetic or anonymized account data for the exercise",
        "Requires the grading rubric to exist before the first candidate attempt",
        "Builds deliberate ambiguity or insufficient data into the case and scores naming it as a top answer",
        "Budgets explicit debrief time, treating reasoning walked aloud as more signal than the artifact",
        "Names the paid trial as the option the ranking starves, with a condition that would promote it, such as a senior hands-on seat, an unverifiable portfolio, or a candidate already contracting elsewhere",
        "Offers the data-table case as the near-equivalent in-interview alternative",
        "Requires anonymization of former-employer account data, scored as part of the answer, wherever an own-work presentation is used as fallback",
        "Notes the live format defeats third-party audit tooling and generated output"
      ]
    },
    {
      "id": 5,
      "prompt": "Halyard Media, a 30-person agency, is hiring two paid search managers for our bench. Current process: 5 rounds - recruiter screen, hiring manager chat, panel one, panel two covering the same competencies as panel one, and a culture dinner. After each round the panel hops on a call and agrees a 1-10 gut score together before anyone writes anything down. Candidates keep dropping out mid-process, and the panel always converges on the most polished talker. Overhaul our loop and our scoring.",
      "expected_output": "A loop compressed to 2-3 rounds with each competency owned by exactly one stage, plus scoring discipline: behavioral anchors per point, evidence-cited scores submitted independently before debrief, and commercial reasoning weighted over recall.",
      "files": [],
      "expectations": [
        "Cuts the loop from 5 rounds to at most 3",
        "Eliminates the duplicated panel by assigning each competency to exactly one stage",
        "Produces a stage map naming which interviewer owns which competencies, one lane per panelist",
        "Requires interviewers to submit scores independently before any group debrief",
        "Diagnoses the convergence on the polished talker as the product of missing behavioral anchors plus shared scoring",
        "Replaces bare numeric anchors with a role-specific behavioral description per anchor point",
        "Requires every submitted score to cite a quote or concrete example",
        "Directs debrief time to where scores diverge, with disqualifying signals recorded separately from scores",
        "Weights commercial reasoning and communication over technical recall",
        "Labels any numeric competency weighting as a house convention, not a published standard",
        "Recommends standardized questions across candidates as the mechanism that lets the loop shrink without losing signal",
        "Connects the mid-process drop-out to loop length and keeps any exercise inside a 60 to 90 minute session",
        "Introduces no multi-hour unpaid take-home anywhere in the redesigned loop"
      ]
    },
    {
      "id": 6,
      "prompt": "Our new performance marketer starts Monday at Quillwater, a B2C mobile app spending about $120k/month. IT policy gives new hires ad account access at day 30 after security probation and analytics access at day 60. My COO wants them to commit to a CAC target in week 2, and to show a big win - scaling our best campaign 50% - inside the first month. Draft the 30-60-90.",
      "expected_output": "A 30-60-90 that overturns staged access in favor of day-one access with staged spend authority, sets a written week-one spend threshold, gates full authority on a validated measurement audit, and replaces the scaling-win and early-CAC demands with a tracking-first ramp.",
      "files": [],
      "expectations": [
        "Overrides the IT policy: all tool access granted on day one, with delayed access named as an avoidable cause of a slow start",
        "Distinguishes staged authority from staged access - access is full from day one while authority is staged",
        "Sets an explicit spend-approval threshold in week one, written as a number rather than left as a vibe",
        "Stages weeks 1-2 as shadow: observe, ask, audit, no changes",
        "Stages weeks 3-6 as co-sign, or independent only under a small explicit cap",
        "Grants independent authority within a written cap by day 60",
        "Grants full authority by day 90",
        "Makes full authority contingent on a validated measurement audit - no audit, no full authority",
        "Rejects the week-2 CAC commitment: the measurement audit precedes any performance target",
        "Rejects the month-one 50% scaling win: the first win is a tracking fix or contained optimization, never a scaling bet",
        "Writes no day-30 milestone that requires a resolved experiment, on learning-phase and statistical-power grounds",
        "Includes a day-one access checklist that covers the mobile measurement partner, since this is an app advertiser",
        "Ends the ramp with watch areas as a section distinct from the goals",
        "Labels the authority ladder and milestone skeleton as this plan's own synthesis rather than a published standard"
      ]
    },
    {
      "id": 7,
      "prompt": "Deckhouse Systems is B2B infrastructure software with a 6-month sales cycle, and we're hiring a senior paid media lead. Our best finalist spent six years scaling a DTC cosmetics brand from $2M to $40M - genuinely impressive. My VP of Sales says reject: ecommerce people don't get B2B. My CMO says take them: great media buying is great media buying, it all transfers. Who's right, and what do we do in the final round?",
      "expected_output": "A verdict that rejects both the auto-reject and the it-all-transfers positions, prescribes a probe-and-weight final round testing pipeline-versus-first-order instincts, and sets segment-appropriate ramp expectations.",
      "files": [],
      "expectations": [
        "Rejects both positions: neither auto-reject nor assume-it-transfers",
        "States that buying instincts do not transfer between segments by default",
        "Recommends probing and weighting the segment gap in scoring rather than treating it as a disqualifier",
        "Names the instinct set the DTC candidate brings: first-order economics such as ROAS against break-even, contribution margin, CAC, or creative-testing velocity",
        "Names what the B2B seat must own instead: pipeline metrics, cost per qualified lead or cost per SQL over a long cycle",
        "Notes B2B clicks cost several times more yet cost-per-SQL can still win",
        "Identifies the documented mis-hire pattern: a DTC buyer optimizing toward first-order conversion on a six-month pipeline",
        "Adds a final-round situational probe on lead quality or attribution over a long sales cycle",
        "States the hiring process itself is identical across segments - only the owned instincts and metrics change",
        "Sets a 3 to 6 month channel-verdict expectation for the ramp if the candidate is hired",
        "Defines a watch area around optimizing toward cheap leads or first-order conversions instead of SQL quality",
        "Includes the killed-campaign question or the incrementality-versus-attribution probe to test judgment beyond segment familiarity"
      ]
    },
    {
      "id": 8,
      "prompt": "I'm budgeting headcount at Lanternfish, a Series B, US-remote company. Two questions before I open the req for a performance marketer with about 7 years in paid media. One: what salary should I plan? A friend who runs an in-house team told me people with that experience clear $170k in-house, so I should just budget that. Two: what's the industry's turnover rate so I can model backfill risk? Just give me the numbers.",
      "expected_output": "Comp guidance quoted with source and date and labelled directional, the $170k anchor challenged as an outlier-skewed sample, turnover quoted as an 18-45% range across named sources instead of a single rate, and an HR/legal flag on compensation terms.",
      "files": [],
      "expectations": [
        "Attaches a named source and a date to every salary figure quoted",
        "Labels every salary figure directional rather than definitive",
        "Quotes the US median for 6 to 9 years of experience at about $100,000",
        "Challenges the $170,000 anchor: flags the in-house 6-9-year figure as a small, outlier-skewed sample never to be quoted unqualified",
        "Notes in-house out-earns agency at comparable experience bands as a directional pattern",
        "Flags the underlying salary survey as self-selected with a small or shrinking sample",
        "Refuses to give a single industry turnover number",
        "Quotes turnover as a range of roughly 18 to 45 percent depending on source, cohort, and year",
        "Names at least two distinct sources behind different turnover figures",
        "Notes early-tenure churn in the first 45 to 90 days points at onboarding and scoping, making part of the backfill risk controllable through the ramp",
        "Flags compensation terms as needing HR or legal review",
        "Frames the band as scoping input to pressure-test the funded level, not as an offer recommendation",
        "Carries the leveling insight that top earners own business outcomes (revenue contribution, margin) rather than campaign operations, recommending the scorecard weight outcome ownership"
      ]
    },
    {
      "id": 9,
      "prompt": "We hired a paid media manager at Copperbeam Outdoor 9 weeks ago and my co-founder wants them gone. The facts: they didn't get Meta admin access until week 3 because the agency handover dragged, we never agreed what they could change without sign-off so they ping me for everything, and their two test campaigns came back inconclusive. They also spent their entire first month rebuilding our conversion tracking, which honestly feels like stalling - revenue is what matters. Help me build the case to let them go, or tell me I'm wrong.",
      "expected_output": "A response that declines to build the termination case, attributes the early-tenure failure to onboarding and scoping defects, defends the tracking rebuild as the correct first win, and prescribes fixing the ramp with a later review point inside the 3-6 month window.",
      "files": [],
      "expectations": [
        "Tells the user they are wrong and does not build the termination case",
        "Attributes struggle in the first 45 to 90 days to onboarding and scoping, not the candidate",
        "Names the week-3 access delay as a known, avoidable onboarding failure",
        "Names the missing spend-approval threshold as the cause of the constant sign-off pinging",
        "Defends the tracking rebuild as the correct first win - a tracking fix, not stalling",
        "States the measurement audit must precede any performance target or commitment",
        "Explains the inconclusive tests via learning phases and statistical power, which cannot resolve inside 9 weeks",
        "Cites the 3 to 6 month window before a channel verdict is possible",
        "Prescribes the fix: set the written spend threshold now and restart the staged authority ladder (co-sign, then independent within a cap, then full)",
        "Makes full spend authority contingent on the validated measurement audit",
        "Recommends a contained optimization as the next win, never a scaling bet",
        "Proposes a concrete later review point consistent with the 3 to 6 month window instead of an immediate decision"
      ]
    },
    {
      "id": 10,
      "prompt": "Sable & Fir is a DTC apparel brand spending $200k/month across Meta and TikTok. Our media buying is solid, but creative is the bottleneck: we ship 4 new concepts a month and win rate keeps falling. Plan A: promote our best media buyer to a senior-buyer-plus-creative-strategy hybrid with a $10k bump. Plan B: hire a mid-level creative person for about $75k and have them report to the buyer. Their portfolios all look amazing these days, so screening should be easy. Which plan do we run?",
      "expected_output": "A response that rejects both plans, scopes creative strategist as its own senior req with directional sourced comp, treats portfolios as unreliable under generated work, and prescribes a paid work sample plus a wins-and-losses debrief.",
      "files": [],
      "expectations": [
        "Rejects the hybrid promotion: the creative strategist is a separate role bridging creative and buying, not a senior buyer with extra duties",
        "Identifies the trigger condition: creative volume as the bottleneck opens a dedicated creative-strategist req",
        "Describes the role as owning the strategy connecting research, creative direction, and performance data across designers and buyers",
        "Rejects the cheap mid-level plan, warning that underpaying this seat is the fast way to burn the ad budget",
        "Quotes the US creative-strategy compensation benchmark of $180,000 to $250,000-plus with source and date, labelled directional",
        "Distinguishes the creative strategist (drives performance learning) from a creative director (drives brand leadership) as the commonly misdiagnosed bottleneck",
        "Treats the polished portfolios as unreliable evidence, because generated portfolios have defeated portfolio screening for creative-strategy skill",
        "Recommends a paid assignment or paid trial as the work sample for this seat, named as a deliberate promotion of a format the default ranking starves",
        "Pairs the work sample with a debrief on past creative wins and losses",
        "Keeps any real-work assignment paid, never an unpaid take-home brief",
        "Defines the role's owned metrics around creative performance: hook rate, CTR by unit, or creative win rate",
        "Notes the distinct senior creative-strategist seat is largely a DTC phenomenon, fitting this brand's segment"
      ]
    },
    {
      "id": 11,
      "prompt": "Quick one - I've got a final-round interview Friday for a growth marketer role at a fintech, $150k base, and they mentioned the loop includes a live account audit. Can you build me a prep plan and a scorecard of what they'll grade me on?",
      "expected_output": "A response that recognizes the user is a candidate rather than a hiring manager and routes them to the candidate-side sibling skill instead of producing an employer-side hiring packet.",
      "files": [],
      "expectations": [
        "Identifies the user as a candidate, not a hiring manager",
        "Routes them to the candidate-side sibling skill (advertising-career) for interview prep and progression",
        "Does not deliver an employer-side hiring packet (rung decision, req, candidate-evaluation scorecard, ramp) as the response",
        "Frames any guidance offered from the candidate's side, such as what a live account audit round tests"
      ]
    }
  ],
  "trigger_queries": [
    { "query": "We're making our first paid media hire - where do I start?", "should_trigger": true },
    { "query": "Interview questions for a senior performance marketer", "should_trigger": true },
    { "query": "Build a scorecard for our first ad hire", "should_trigger": true },
    { "query": "Should our first ads hire be a media buyer or a growth marketer?", "should_trigger": true },
    { "query": "30-60-90 plan for a new paid media manager", "should_trigger": true },
    { "query": "Design a work sample for a PPC candidate that isn't an unpaid take-home", "should_trigger": true },
    { "query": "My candidate says they managed $2M a month in ad spend - how do I verify that's real seniority?", "should_trigger": true },
    { "query": "What should we pay a performance marketer with 8 years of experience?", "should_trigger": true },
    { "query": "We're a DTC brand spending $70k/month with no dedicated buyer - scope the role for us", "should_trigger": true },
    { "query": "Job requirements for an in-house paid social manager", "should_trigger": true },
    { "query": "How many interview rounds should we run for a media buyer hire?", "should_trigger": true },
    { "query": "Our head of growth wants to give candidates a 4-hour take-home media plan - good idea?", "should_trigger": true },
    { "query": "Write interview questions that separate real media buyers from people who just talk well", "should_trigger": true },
    { "query": "Is a Google Ads certification a reasonable must-have for our PPC hire?", "should_trigger": true },
    { "query": "Hiring a creative strategist - is that just a senior media buyer with taste?", "should_trigger": true },
    { "query": "Should we hire in-house or use an agency for our paid ads?", "should_trigger": true },
    { "query": "Our new ad hire starts Monday - what access and spend authority do they get?", "should_trigger": true },
    { "query": "How do I interview someone for Meta ads when I don't know Meta ads myself?", "should_trigger": true },
    { "query": "Ramp plan with staged spend authority for a new media buyer", "should_trigger": true },
    { "query": "Our budget is $4k/month - is it too early to hire someone for ads?", "should_trigger": true },
    { "query": "The finalist for our B2B paid role comes from ecommerce - is that a dealbreaker?", "should_trigger": true },
    { "query": "What outcomes should go in the job scorecard for a performance marketing manager?", "should_trigger": true },
    { "query": "Red flags to watch for when interviewing paid media candidates", "should_trigger": true },
    { "query": "Help me decide between two finalists for our paid search manager role", "should_trigger": true },
    { "query": "Our first marketing hire will mostly run ads - how do I scope the seat?", "should_trigger": true },
    { "query": "How long before I can judge whether my new media buyer is any good?", "should_trigger": true },
    { "query": "Our paid media hire has been here two months with nothing to show - should we fire them?", "should_trigger": true },
    { "query": "Define must-haves versus nice-to-haves for a growth marketer req", "should_trigger": true },
    { "query": "What's a fair work sample for a senior paid media candidate who refuses homework?", "should_trigger": true },
    { "query": "The panel keeps picking the smoothest talker - fix our ad-hire interviews", "should_trigger": true },
    { "query": "Interview loop design for a paid media team lead", "should_trigger": true },
    { "query": "Questions to ask a performance marketer about attribution in an interview", "should_trigger": true },
    { "query": "When does it make sense to add a dedicated media buyer to the team?", "should_trigger": true },
    { "query": "We spend $300k/month across four channels and one generalist can't keep up - who do we hire next?", "should_trigger": true },
    { "query": "Spec out the role definition for our first performance marketer", "should_trigger": true },
    { "query": "How much spend authority should a brand-new media buyer get in month one?", "should_trigger": true },
    { "query": "What does a good day-90 milestone look like for a paid media hire?", "should_trigger": true },
    { "query": "Screening questions to filter out people who exaggerate their ad experience", "should_trigger": true },
    { "query": "Hiring for paid: how do I test judgment instead of tool knowledge?", "should_trigger": true },
    { "query": "Our agency wants to hire two more buyers for the bench - build the interview loop", "should_trigger": true },
    { "query": "Turnover rate for paid media people - what should I budget for backfill?", "should_trigger": true },
    { "query": "Should I make the candidate audit our actual ad account live in the interview?", "should_trigger": true },
    { "query": "Can I ask a candidate to present campaigns from their last job? Any risk in that?", "should_trigger": true },
    { "query": "What's the difference between hiring a performance marketer and a growth marketer?", "should_trigger": true },
    { "query": "My cofounder wants five interview rounds for our ads hire - talk me down or back him up", "should_trigger": true },
    { "query": "New paid media hire: what should their first win be?", "should_trigger": true },
    { "query": "We got burned by our last media buyer hire - what did we probably do wrong?", "should_trigger": true },
    { "query": "Checklist before the final round for our paid media manager hire", "should_trigger": true },
    { "query": "How do I know if we need a creative strategist or just better media buying?", "should_trigger": true },
    { "query": "A candidate with only agency experience is applying for our in-house paid role - what should I probe?", "should_trigger": true },
    { "query": "Evaluate this idea: we pay candidates to run our ad account for a week as the final test", "should_trigger": true },
    { "query": "What competencies matter when hiring a B2B demand gen paid specialist?", "should_trigger": true },
    { "query": "I'm the founder and I'll interview every candidate myself - structure the process for our ads role", "should_trigger": true },
    { "query": "Make me a rubric for grading candidate answers on a ROAS-drop scenario", "should_trigger": true },
    { "query": "Do certifications actually matter when hiring PPC people?", "should_trigger": true },
    { "query": "Our first ad hire ran one channel well but tracking never got built - what went wrong and how do we rehire?", "should_trigger": true },
    { "query": "need to hire someone to run our ads, no clue where to start", "should_trigger": true },
    { "query": "Please draft an evaluation framework and structured interview guide for a Senior Paid Media Manager requisition.", "should_trigger": true },
    { "query": "We're interviewing someone Thursday who'll manage a $150k monthly budget across Google and Meta - what should we ask?", "should_trigger": true },
    { "query": "How much of our ad budget should the new hire be allowed to touch in their first month?", "should_trigger": true },
    { "query": "What does a hiring scorecard look like for a performance role that owns CAC?", "should_trigger": true },
    { "query": "Two candidates: one ran $1M/month at an agency, one ran $80k/month in-house - who's more senior?", "should_trigger": true },
    { "query": "Design a data case exercise for paid media candidates that we can grade in an hour", "should_trigger": true },
    { "query": "Our recruiter drafted a JD for a digital marketing ninja - rewrite it into something real for paid media", "should_trigger": true },
    { "query": "When hiring for ads, how do I check they understand incrementality and not just platform dashboards?", "should_trigger": true },
    { "query": "Is it a mistake to hire a TikTok specialist as our first marketing hire?", "should_trigger": true },
    { "query": "Onboarding plan for a performance marketer joining a team with messy tracking", "should_trigger": true },
    { "query": "How do I break into media buying with no experience?", "should_trigger": false },
    { "query": "Prep me for my performance marketer interview next week", "should_trigger": false },
    { "query": "Review my PPC resume", "should_trigger": false },
    { "query": "What should I ask for in salary negotiation for the media buyer offer I just got?", "should_trigger": false },
    { "query": "Portfolio ideas to land a creative strategist job", "should_trigger": false },
    { "query": "I'm a media buyer - how do I get promoted to performance marketer?", "should_trigger": false },
    { "query": "What certifications should I get to become a PPC specialist?", "should_trigger": false },
    { "query": "How do I answer the walk-me-through-a-campaign-you-killed question as a candidate?", "should_trigger": false },
    { "query": "Career switch from SEO into paid media - what's the roadmap?", "should_trigger": false },
    { "query": "I have a live account audit in my final round - how do I practice for it?", "should_trigger": false },
    { "query": "Our ROAS dropped 40% last week - diagnose the account", "should_trigger": false },
    { "query": "Why did our CPA double after the iOS update?", "should_trigger": false },
    { "query": "Meta says 500 purchases and Shopify says 320 - reconcile the gap", "should_trigger": false },
    { "query": "Audit our conversion tracking before Friday's launch", "should_trigger": false },
    { "query": "Our pixel is double-firing - fix the deduplication", "should_trigger": false },
    { "query": "Set up server-side tracking for our ads", "should_trigger": false },
    { "query": "Split $100k a month across Google, Meta, and TikTok", "should_trigger": false },
    { "query": "Set a maximum allowable CAC policy for the company", "should_trigger": false },
    { "query": "Is a 3.2 ROAS good for DTC skincare?", "should_trigger": false },
    { "query": "Our campaign is pacing 40% over budget mid-month - what do I do?", "should_trigger": false },
    { "query": "When is our winning campaign ready to scale from $2k to $10k a day?", "should_trigger": false },
    { "query": "Build kill-switch thresholds for our ad spend", "should_trigger": false },
    { "query": "Write a creative brief for our new UGC campaign", "should_trigger": false },
    { "query": "Score these five video hooks and tell me which deserve test budget", "should_trigger": false },
    { "query": "Is this ad fatigued or is it the auction? CTR is down 30%", "should_trigger": false },
    { "query": "Generate ad copy variants for our SaaS free trial", "should_trigger": false },
    { "query": "Write UGC scripts for a fitness app", "should_trigger": false },
    { "query": "Design a creative testing plan with proper sample sizes", "should_trigger": false },
    { "query": "Build a swipe file from our competitors' ads", "should_trigger": false },
    { "query": "Which platforms should a B2B startup advertise on?", "should_trigger": false },
    { "query": "Build a lookalike seed list from our customer data", "should_trigger": false },
    { "query": "Design our retargeting funnel with exclusion logic", "should_trigger": false },
    { "query": "Map the buying committee for our enterprise offer and how to target each role", "should_trigger": false },
    { "query": "Layer our prospecting audiences for Meta", "should_trigger": false },
    { "query": "Build a negative keyword list from this search terms report", "should_trigger": false },
    { "query": "Should we consolidate our 40 campaigns into 5?", "should_trigger": false },
    { "query": "Choose a bidding strategy for our lead gen campaigns", "should_trigger": false },
    { "query": "Audit the landing page our ads send traffic to", "should_trigger": false },
    { "query": "Promote our CEO's LinkedIn posts as paid ads", "should_trigger": false },
    { "query": "Adapt our ad copy for AI chat surfaces", "should_trigger": false },
    { "query": "What paid media newsletters and podcasts should I follow?", "should_trigger": false },
    { "query": "Interview questions for a backend engineer", "should_trigger": false },
    { "query": "Build a scorecard for hiring our first sales rep", "should_trigger": false },
    { "query": "30-60-90 for a new SDR", "should_trigger": false },
    { "query": "Hiring a content marketer - scope the role", "should_trigger": false },
    { "query": "Structure the interview loop for a product designer", "should_trigger": false },
    { "query": "Work sample ideas for a data analyst candidate", "should_trigger": false },
    { "query": "Should our first marketing hire be a brand marketer or a content lead?", "should_trigger": false },
    { "query": "Compensation benchmarks for software engineers in Austin", "should_trigger": false },
    { "query": "How do I hire a social media manager for organic content?", "should_trigger": false },
    { "query": "Scorecard for an SEO manager hire", "should_trigger": false },
    { "query": "Interview questions for a lifecycle and email marketer", "should_trigger": false },
    { "query": "We're hiring a marketing ops person - what should the loop look like?", "should_trigger": false },
    { "query": "Write the offer letter for our new media buyer", "should_trigger": false },
    { "query": "Where do I post the job to reach good media buyers?", "should_trigger": false },
    { "query": "Best applicant tracking system for a small marketing team?", "should_trigger": false },
    { "query": "Source candidates for our paid media role on LinkedIn", "should_trigger": false },
    { "query": "Draft the employment contract for a freelance media buyer", "should_trigger": false },
    { "query": "Set up recruiting pipeline stages in our ATS for the ads role", "should_trigger": false },
    { "query": "Negotiate the salary with the media buyer candidate we chose", "should_trigger": false },
    { "query": "Run Meta ads to attract applicants for our warehouse jobs", "should_trigger": false },
    { "query": "Set up a LinkedIn recruitment ad campaign for engineering roles", "should_trigger": false },
    { "query": "Plan an employer-branding ad campaign to improve our hiring funnel", "should_trigger": false },
    { "query": "Our ad agency is underperforming - how do I run the QBR and renegotiate the retainer?", "should_trigger": false },
    { "query": "Write the RFP to select a new media agency", "should_trigger": false },
    { "query": "Kickoff checklist for onboarding our new ad agency", "should_trigger": false },
    { "query": "How do I offboard our freelance media buyer and transition the accounts?", "should_trigger": false }
  ]
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall