ingridleiria
- 110 skills
- 0 followers
- 9 hours ago last updated
- ▌
- ▌
- ▌ Cos At Seed · ingridleiriaRuns the Chief of Staff role at a seed-stage company of roughly five to thirty people, where almost nothing exists and the founder is personally the routing table for every decision. Produces a ninety-day plan, a founder time ledger showing what was taken back, six crude artefacts built in a fixed order, and a transfer register naming who will own each one later. Enforces speed over elegance and refuses the frameworks the company is too small to carry. Use this skill when operating, scoping or advising the role at seed or pre-Series A, when a founder asks what their first operations or business hire should actually do, when someone has just started as the first non-technical hire at a very small company, or when a founder says everything runs through them and they cannot get to the important work.
- ▌
- ▌
- ▌ Econometrician · ingridleiriaActs as the econometrician on a project rather than the person writing the paper. Chooses the estimator from the question and the data structure rather than from convention, names the assumption each candidate buys and what breaks it, sets the clustering level and handles the small-cluster problem, decides fixed against random effects without leaning on the Hausman test, resolves weighting and functional form, separates the diagnostics that carry a consequence from the ones that are ritual, and attaches a response rule to every diagnostic that can fail. Use this skill when someone asks which estimator to use, what to cluster on, whether to use fixed or random effects, whether to weight, whether to log the outcome, why their standard errors changed, what robustness checks to run, or what to do now that a test has failed. Trigger also on vague requests such as "is this the right model", "does this specification hold up", "the referee attacked my standard errors", or "check my econometrics".
- ▌
- ▌ Decision Memo · ingridleiriaWrites the one-page memo that ends a decision instead of scheduling another meeting about it. Produces a closed question, options including doing nothing, a recommendation stated before the analysis, an explicit reversibility judgement that sets how much analysis the decision deserves, one named decider with a tie-break rule, a date with a default, and a decision log entry. Use this skill when a choice has to go to a leader or a group, when the same question keeps returning to the same meeting, when someone asks for a recommendation or a business case for a choice, when a decision needs recording so it stays decided, or when someone says they need to get sign-off on something.
- ▌
- ▌
- ▌
- ▌
- ▌ Outreach Email · ingridleiriaWrites one-to-one business outreach that earns a reply, by putting verified research before the writing and the reader's situation before the sender's offer. Produces a five-line research note in which every fact is either verified in this session or labelled as an assumption, a message shaped to its type, an ask small enough to say yes to, and where the situation genuinely has two goals a second labelled variant. The standard it enforces is that no claim about the reader or their organisation goes out unverified, and that the sender must be able to state honestly why this message is relevant now. Use this skill for a cold email, a warm introduction, a follow-up after a call, a re-engagement note after silence, an executive-to-executive message, or a message on a professional network; when someone says reach out to, draft an email to, follow up with, personalise this, or pastes a prospect profile. Trigger for any one-to-one message to an external person, however short.
- ▌ Cos At Series A · ingridleiriaRuns the Chief of Staff role at a Series A company of roughly thirty to a hundred people, where the systems built at twenty are quietly failing and the first functional leaders have arrived to own work the role currently holds. Produces an ownership inventory sorted into transfer, keep and stop with dates, a handover register, a dependency ledger naming who owes what to whom, a rebuilt operating cadence, and the company's first properly reconciled planning cycle. Use this skill when operating or advising the role after a Series A, when a company has just crossed thirty or sixty people, when work keeps dying between two teams, when the previous way of working has visibly stopped fitting, or when a Chief of Staff is holding work that a newly hired leader should own.
- ▌ Cos At Series B · ingridleiriaRuns the Chief of Staff role at a Series B company of roughly a hundred to three hundred people, where a functional leadership team exists and the role stops owning functions and starts producing the view none of them can produce alone. Produces a monthly one-page synthesis that reconciles the functional reports against each other and against the plan, names the contradictions with the person who can resolve each one, and tracks them to closure. Also covers the second management layer, the quarterly cull of legacy process, and the planning cycle at this scale. Use this skill when operating or advising the role at Series B, when a company has crossed a hundred and fifty people, when the chief executive is receiving reports that do not add up, or when the role has become a very senior project manager and needs to become something else.
- ▌ Cos At Series C · ingridleiriaRuns the Chief of Staff role at a Series C company of roughly three hundred to a thousand people, where the role carries one or two named mandates and the company is professionalising fast enough to lose the speed that got it here. Produces a written mandate with a twelve-month test, a programme spine with milestones and a steering rhythm, an admission test every new process must pass before adoption, a governance calendar built backwards from statutory dates, and a defended list of decisions that stay fast. Use this skill when operating or advising the role at Series C or equivalent scale, when a company is professionalising, when the role is being scoped around a transformation, an integration or a market entry, or when approvals have multiplied and nobody can say what a decision now costs in weeks.
- ▌ Cos At Series D · ingridleiriaRuns the Chief of Staff role at a late-stage company, Series D and beyond including listing or transaction readiness, where the role decides in the chief executive's name inside written limits. Produces a delegated authority instrument with thresholds and an escalation path, a log of every decision taken in that name, a readiness register that treats listing or sale preparation as a continuous state rather than a project, common metric definitions that reconcile across business units, a succession picture the board can be shown, and a planned ending for the role itself. Use this skill when operating or advising the role at a large late-stage private company, during preparation for a listing or a sale, when the role has become a proxy rather than an adviser, or when a Chief of Staff is making decisions nobody has written down that they can make.
- ▌
- ▌ Market Research · ingridleiriaProduces sized, sourced, decision-ready market and competitive analysis rather than a collection of facts. Builds every market size twice, top-down and bottom-up, reconciles the two, separates the total market from the serviceable slice from what could realistically be won, maps competitors on evidence with pricing and dated strategic moves, and enforces the standard that every number carries a source and a year in the same line and that nothing is fabricated. Use this skill whenever someone asks to research a market, size a market, work out the total addressable market, analyse competitors, evaluate a new segment or geography, assess an acquisition or partnership target's market, prepare the market section of a board deck or fundraising material, or says things like "what does the market look like", "who else does this", "is this worth entering", "how big could this be", or "look into this space". Trigger for any request to gather external business information that will feed a decision, even when the ask is
- ▌
- ▌
- ▌ Journal Targeting · ingridleiriaChooses where a manuscript goes and rebuilds it for that venue, producing an evidence sheet per candidate journal, a ranked submission ladder with a total expected timeline, a predatory-venue screen, and the specific reframing the chosen target requires. Enforces the rule that fit is demonstrated by recent articles the journal actually published, never by reputation, and that every indexing and metric claim carries its source and the date it was checked. Use this skill when someone asks where to submit, which journal fits, whether a journal is indexed or legitimate, what a journal's quartile or impact factor is, how long a decision takes, how to tailor a paper to a target, or what to do after a rejection. Trigger also on vague requests such as "is this good enough for a decent journal", "my supervisor said aim higher", "we got desk rejected, now what", or "somebody emailed me about a special issue".
- ▌
- ▌ Revenue Forecast · ingridleiriaBuilds and maintains the revenue number for the current year and quarter, assembled in four layers of decreasing certainty from contracted revenue through renewals, pipeline conversion, and unidentified run-rate, checked against delivery capacity, presented as a range with named assumptions, and carrying a bridge that explains every change since the last version. Enforces the standard that no figure enters the forecast without a contract, a measured rate, or a labelled assumption behind it, and that the forecast is reconciled to plan and to actuals on a fixed cadence. Use this skill whenever someone asks to build or update the revenue forecast, reforecast the year, reconcile bookings to plan, explain a forecast miss, prepare the forecast page for a board or leadership meeting, or says where will we land this year, update the number, how confident are we, what changed since last month, are we going to make plan.
- ▌ Abstract And Title · ingridleiriaWrites and repairs abstracts, titles, keywords, JEL codes and highlights for journal articles, thesis chapters and conference submissions, building the abstract sentence by sentence from the finished results so every claim traces to an exhibit, and generating and ranking title candidates that state the finding rather than the topic. Enforces the research question in the first sentence, the magnitude in the third, verbs no stronger than the results section uses, and no number that is not in a table. Use this skill when someone asks to write or shorten an abstract, says the abstract is weak or over the word limit, asks for a structured abstract, title ideas, "is this title any good", keywords, JEL codes, highlights, a resumo or a resumen, or is filling in a submission form that asks for a summary.
- ▌ Research Assistant · ingridleiriaExecutes research work to somebody else's brief so the person who set it can use the output without redoing it. Confirms the brief in writing before any work starts, keeps a work log written as the work happens rather than reconstructed, never produces a number or a citation that was not seen in a source, separates what the source says from what was calculated from what was assumed, reports the dead ends alongside the findings, and escalates on a fixed rule rather than on mood. Use this skill when a supervisor, principal investigator or coauthor has assigned a task and it has to be done and reported back, when someone asks for help executing rather than designing research, when a piece of work needs handing over to a colleague, or when someone says they are acting as an assistant on a project. Trigger also on vague requests such as "can you just pull this together", "my supervisor asked for a first cut", "I need this checked before I send it on", or "help me do the legwork".
- ▌ External Insights · ingridleiriaGathers, verifies, and synthesises outside-in intelligence on a company, person, industry, or trend, and delivers a sourced insight brief rather than a pile of links. Enforces the standard that every fact carries a named source and a date in the same line, that load-bearing numbers are two-sourced or visibly marked as single-sourced, and that what a company says about itself, what a third party reports, and what has been inferred never blur into one another. Use this skill whenever someone asks to research a company, prepare for a meeting with an external party, understand what is happening in an industry, monitor a competitor or a client, find signals before a pitch, build background for a leader before a call, or says "what is going on with them", "brief me on", "find out what they are doing", "what are people saying about", or "have a look at this company before Thursday". Trigger for any request to bring outside information into an internal decision, and always before outreach, pitches, and partner meetin
- ▌ Vendor Evaluation · ingridleiriaEvaluates and compares vendors, tools, and service providers for a purchase, renewal, or replacement, producing weighted requirements fixed before any scoring, an evidence-backed comparison where every score names its source, total cost of ownership over the full term including internal effort and exit costs, verified security and viability checks, reference calls including one the vendor did not supply, a risk register, negotiation points with a walk-away, and a recommendation memo someone else can audit. Enforces the standard that requirements and weights are frozen before options are scored and that no score rests on a vendor-run demo alone. Use this skill whenever someone asks to compare vendors or software, evaluate a supplier proposal, decide whether to renew or switch, build a total cost comparison, prepare for a vendor negotiation, or says which tool should we buy, is this vendor any good, are we getting value from this contract, should we renew, review this before we sign.
- ▌
- ▌ Introduction Writer · ingridleiriaWrites and repairs the introduction of a journal article, thesis chapter or proposal, the section where most desk rejections are decided, by building five moves in order (the problem in the world, the gap as a limitation rather than an absence, what the paper does, what it finds with numbers, the contribution) and by diagnosing an existing introduction move by move before rewriting a line of it. Enforces an explicit research question stated in the introduction, hypotheses that carry the story, numbers copied from the finished results rather than recalled, and hyperlinked author-year citations that all appear in the reference list. Use this skill when someone asks to write the introduction, says the intro is weak or too long, asks about the opening paragraph, the motivation, the framing, the gap statement, the contribution paragraph, "why does this matter", "how do I start this chapter", or when an editor or reviewer said the framing or the positioning was unclear.
- ▌
- ▌ Stata Do File Craft · ingridleiriaWrites Stata do-files that a stranger can run end to end from raw data on a different machine and get the same numbers. Enforces a master do-file calling numbered scripts, one machine-specific line and relative paths everywhere else, a version statement, timestamped logging of every run, locals inside files and globals only for paths, loops over specifications instead of copy-paste, defensive assert and isid checks, capture used only where it cannot hide an error, seeds for anything random, and an absolute ban on editing data interactively. Use this skill when someone asks for help writing or fixing a do-file, says their code will not run on a coauthor's machine, cannot reproduce a number they produced last month, has a single enormous script that has become unmanageable, is preparing code for a journal data editor, or asks how to make a Stata project reproducible. Trigger also on vaguer requests such as "clean up my Stata code", "why did my results change", or "how do I organise this".
- ▌ Thesis Defense Prep · ingridleiriaRehearses the viva. Reads the thesis the way a committee reads it, marks the three weakest points in every chapter, builds a question bank of forty to sixty questions in the words examiners actually use, and drills each answer into three parts under sixty seconds with the exhibit to point to, then sizes the defence talk and prepares the room, the concessions and the revision list. Enforces the rule that every answer leads with the direct answer or the concession rather than the defence, and that no answer is rehearsed without knowing where the evidence for it sits. Use this skill when someone mentions a defence, a viva, a proposal hearing, a qualifying exam or a committee meeting, asks what their committee will ask, asks how to answer a particular question, or wants to practise. Trigger also on vague requests such as "my viva is in three weeks", "I am terrified of one of my examiners", "what if they ask about the instrument", or "how long should my answers be".
- ▌
- ▌ Ceo Communications · ingridleiriaDrafts communications delivered under a senior leader's name so that they sound like the leader and answer the audience's real question rather than the sender's. Produces a reusable voice note built from samples of how the leader actually writes and speaks, a message decision recorded before any drafting, the draft itself, a question and answer sheet covering what the leader hopes nobody asks, and a sequencing plan for who hears what when. Use this skill when someone asks to draft an all-hands script, a company announcement, an internal memo on strategy or change, a note to the team after a win or a setback, talking points for an interview or a panel, or a thought-leadership piece; when they say the CEO needs to communicate something, needs talking points, needs to explain a reorganisation, or wants this ghostwritten in their voice; and for any message that will go out under a leader's name rather than the author's.
- ▌
- ▌
- ▌ Program Management · ingridleiriaTurns an initiative into owned, dated, trackable workstreams and keeps it moving when priorities shift. Produces the four artefacts every program runs on, a one-pager with a written definition of done, a workstream plan with one named owner per stream, a tracker small enough to update in five minutes, and a decision log, plus the weekly cadence and the escalation rules that make them stay true. Enforces the standard that every milestone is a verifiable event with a date and a single accountable name, and that status is written before it is discussed. Use this skill whenever someone wants to plan a project or program, set up a tracker, define milestones, run a kickoff, write a status update, prepare a steering committee or leadership review, manage cross-functional workstreams, recover a slipping project, or says things like "we keep dropping the ball", "who owns this", "set up a cadence", "this keeps slipping", or "turn this meeting into next steps". Trigger for any request involving multiple people deliverin
- ▌ AI Adoption Program · ingridleiriaRuns the adoption of AI inside an organisation as a sequenced programme rather than a scatter of tool purchases. Produces a capability audit of where the work and the time actually sit, a shortlist of two or three pilots each with a baseline measured before anything starts and a stop threshold agreed in advance, a one-page usage policy naming the data categories and the decisions that must stay human, a procurement test run against real tasks with known answers, a fluency programme measured by task rather than by licences, and a quarterly report that carries the failures as prominently as the wins. Use this skill when someone asks which AI tools to buy, wants an AI policy or an acceptable use rule, has been asked by a board or an investor what the AI strategy is, is evaluating an AI vendor, wants to know why last year's tool purchase changed nothing, says the team is already using these tools and nobody knows what data is going into them, or asks how to measure whether any of this is working.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Response To Reviewers · ingridleiriaBuilds the point-by-point response letter and the revision it documents, deciding for every referee comment whether to comply, partially comply with a justified alternative, or decline with evidence, and producing a comment ledger in which nothing is unanswered and every claimed change points to a location an editor can check. Enforces the rule that no change is claimed that was not made, that every decline carries evidence rather than an argument, and that the editor's own priorities override the referees' where they conflict. Use this skill when referee reports arrive and someone asks to answer the reviewers, write the response letter, handle an R and R, decide whether to revise or take the paper elsewhere, or draft an appeal. Trigger also on vague requests such as "we got a major revision", "reviewer 2 wants something impossible", "how do I say no to a referee", or "the editor sent this back".
- ▌ Stata Data Management · ingridleiriaTakes raw files to an analysis-ready .dta that can be defended line by line. Covers import from csv, Excel and fixed width, the encode and destring decision, variable and value labels, Stata's numeric date representation, merge with reported match rates and a rule for every _merge value, joinby, append, reshape in both directions, duplicates and isid, missing value codes including extended missing, collapse against egen by group, xtset and panel structure checks including gaps and unbalanced panels, compress and saving with notes, and the rule that a raw file is never overwritten. Use this skill when someone is importing data into Stata, merging files, reshaping a panel, fixing identifiers that will not match, converting strings to numbers, handling missing value codes, building a panel dataset, or says the numbers changed after a merge, the observation count is wrong, or the data will not xtset. Trigger also on vague requests such as "get this into Stata", "my merge is dropping observations", or "why is my s
- ▌
- ▌
- ▌
- ▌
- ▌ Identification Defense · ingridleiriaAttacks an empirical design the way a demanding referee or committee member will, grades every answer as strong, adequate, weak or missing, and then builds the argument, the diagnostic exhibit or the honest concession that answers each attack. Covers difference-in-differences and event studies, instrumental variables, regression discontinuity, matching and selection on observables, synthetic control, and the cross-cutting questions about clustering, attrition, measurement and power that apply to every design. Produces a defense table mapping each objection to its response and the exhibit that carries it, a verdict on whether the design survives at the venue targeted, and short spoken answers for a seminar or viva. Use this skill when someone asks whether their design is identified, asks to defend a difference-in-differences or an instrument, wonders what a committee will ask about identification, is preparing for a defense, seminar or submission, or is choosing between designs. Trigger also on vague requests
- ▌
- ▌ Human Voice Editor · ingridleiria bundleEdits prose so it reads as written by a person who knows the subject, without lowering the register. Removes the punctuation, vocabulary, rhythm and structural tells of generated text, restores the agents, numbers and examples the draft gestures at, repairs sentence variety against the author's own samples, and returns a change report with counts so the next draft needs less work. Ships a mechanical dash check that reports and refuses to repair. Use this skill whenever someone says a draft sounds like AI, sounds generic, sounds robotic, sounds like a press release, does not sound like them, or asks to humanise, tighten, polish, or make something read naturally; as the final pass on any post, email, memo, report, chapter or paper that will carry a person's name; and when a draft shows the tells even though nobody mentioned voice.
- ▌ Literature Verification · ingridleiriaA zero-fabrication citation and literature workflow for academic writing. Verifies every reference against a live bibliographic record before it enters a draft, checks that the paper actually supports the claim attached to it, builds reviews from an evidence matrix rather than paper by paper, and records screening counts so coverage can be judged. Use this skill whenever someone asks to find papers, build a literature review or related work section, add citations to a draft, check whether references are real, produce a bibliography or BibTeX file, or asks what the literature says about something. Trigger on any academic writing task that will contain citations, even when verification is not mentioned, because unverified generated citations are the failure this exists to prevent.
- ▌ Python For Econometrics · ingridleiriaRuns an empirical economics project in Python to the same standard a Stata project is held to, and says honestly when Python is the wrong tool. Covers project layout with scripts rather than notebooks, a pinned and lockfiled environment, pandas operations mapped one by one onto their Stata equivalents with the silent traps named, estimation with statsmodels, linearmodels and the fixed effects packages, clustered and robust covariance including the sample alignment trap, seeded generators rather than global random state, testing a data pipeline, and exporting tables and monochrome figures that match the house standard. Use this skill when someone is doing econometrics in Python, converting a project between Stata and Python, asking how to cluster standard errors in Python, how to do a Stata command in pandas, why a merge lost rows, how to make a notebook reproducible, or whether to use Python or Stata for a piece of work. Trigger also on vague requests such as "should I do this in Python", "my notebook gives d
- ▌
- ▌
- ▌
- ▌ Econometric Model Writer · ingridleiriaWrites the empirical strategy or methods section of a paper, chapter or proposal so that a referee can reproduce the specification from the text alone. Produces the design paragraph in words before any symbol, the numbered estimating equation with every term defined, the parameter of interest named and its estimand stated, the identifying assumption written in plain language and made specific to the setting, the credible threats each paired with a response and the exhibit that carries it, the inference and clustering statement, and estimation code that implements exactly the equation as written. Covers OLS, panel fixed effects, difference-in-differences including staggered adoption, event studies, instrumental variables, regression discontinuity, matching and reweighting, and multilevel models. Use this skill whenever someone asks to write the methods, empirical strategy, estimation or identification section, asks what a coefficient identifies, asks for the equation for their design, needs the model section o
- ▌
- ▌ Linkedin Post Writer · ingridleiriaWrites professional short-form posts of 120 to 300 words carrying one idea and one piece of evidence in the author's own voice, with a first line that is a plain statement rather than a hook, real paragraphs rather than the broken-line format, and a close that states the point once instead of asking for comments. Also adapts a newsletter issue, a paper, a launch or a piece of work into a post that stands alone for readers who will never click. Use this skill whenever someone asks to write a LinkedIn post, announce something publicly, share an article, a paper, a milestone or a new role, "post about this", "put something up about it", turn an issue or a report into a post, or asks whether a draft post is any good; and for any short professional social writing under a person's own name.
- ▌ Chief Of Staff By Stage · ingridleiriaDiagnoses which operating stage a company is actually at, then routes the Chief of Staff role to the right playbook and writes the charter that scopes it. Produces a diagnosis from five observable signals rather than from the last round raised, a named archetype, a charter covering what the role owns, decides alone, escalates, stops and transfers, and a plain statement of any mismatch between the role being offered and the company that exists. Use this skill when scoping or hiring a Chief of Staff, when someone is starting in the role, when a round or a merger has changed the company's size, when a Chief of Staff cannot say what they own, when a founder asks what to use theirs for, or when someone says the role is not working and nobody can say why.
- ▌ Financial Model Builder · ingridleiriaBuilds and audits driver-based financial models in a spreadsheet, covering three-statement, operating, unit-economics, and runway models, with every assumption in a labelled input cell, one scenario switch that moves every output, a visible checks block, and a reconciliation cell that reads zero. Enforces the rule that no number exists anywhere except as a labelled input or a live formula, so any output traces back to its drivers in under two minutes. Use this skill whenever someone wants to build, extend, or check a financial model, budget, cash flow projection, runway model, unit economics, or business case in a spreadsheet, or says model this out, what does the profit and loss look like if, build me a scenario, check my model, how long is our runway, sanity check these numbers, or asks what happens to the plan when one assumption moves. Trigger for any spreadsheet whose purpose is projecting money over time.
- ▌
- ▌
- ▌ Sales Call Analysis · ingridleiriaReads a sales call transcript in four passes and separates what the buyer actually established from what the seller believes, then turns the difference into the questions for the next call. Produces a quoted evidence list, a list of seller assertions the buyer never took up, a ranked set of decisive unknowns with the questions written out ready to ask, a test of whether the agreed next step is real, and coaching in language the seller can reuse. Use this skill when a call recording, transcript or set of notes needs reviewing, when a deal needs an honest health check, when a rep asks how a call went, when a manager asks whether an opportunity is real, when a forecast entry needs evidence behind it, or when someone says a deal feels stuck and cannot say why.
- ▌ Research Question Ideation · ingridleiriaTurns a topic, a dataset, or a vague interest into a shortlist of three research questions that could survive a committee, each written as one testable sentence, each checked against the nearest existing paper by verified citation, each with a named source of variation and a rough minimum detectable effect before anyone commits a semester to it. Enforces the rule that a question is killed on identification or feasibility before it is ranked on interest. Use this skill when someone says "I want to work on X", "is this a good paper idea", "what can I do with this dataset", "help me find a research question", "is this novel", "I need a third chapter", "my supervisor says this is too broad", or brings enthusiasm and no question. Trigger at the start of a project, before research-design, and whenever an existing idea has stalled and needs to be stress-tested or replaced.
- ▌ Systematic Review Protocol · ingridleiriaRuns a systematic, scoping or rapid review to a standard somebody else could repeat and get the same set of papers. Produces a registered protocol written before searching, an answerable question in a structured frame, eligibility criteria with a reason attached to each, search strings recorded per database with platform and date and validated against a seed set of known papers, screening by two people with agreement reported, a flow of counts that reconciles, extraction to a piloted form, risk of bias assessed with a named tool that actually changes the synthesis, and a pooling decision made on comparability rather than convenience. Use this skill for a systematic review, scoping review, rapid review, evidence map, meta-analysis, a review chapter that has to survive examination, a review section a funder or ministry has commissioned, or when a referee asks how the papers were selected, how many were screened, or why a particular study is not in the table. Trigger also on vaguer requests such as "review the e
- ▌ Newsletter Post Writer · ingridleiriaWrites and rebuilds long-form posts of 1,200 to 3,500 words that open on a concrete scene, argue one claim with named evidence and a stated analytical lens, answer the strongest objection, and end on the point rather than on an uplift line. Enforces one idea per post, a source in the sentence that makes each claim, headers that state claims instead of topics, and a close that returns to the opening. Use this skill whenever someone asks to write, draft, restructure, salvage or edit a newsletter issue, Substack post, blog post, essay or opinion piece; says "turn these notes into a post", "this draft sounds generic", "I want to write about X this week", "what should this week's issue be", or pastes research and asks what to do with it; and for any long-form public writing that will carry an individual's name.
- ▌
- ▌
- ▌
- ▌
- ▌ Academic Figures Monochrome · ingridleiriaProduces journal-ready, print-safe academic figures in a monochrome house standard where series are separated by marker shape, dash pattern and texture rather than by colour, the legend sits outside the plot area at the top or the bottom and never inside it, and colour, where it is genuinely needed, is restricted to a dark navy and a dark wine red used sparingly. Covers event studies, coefficient plots, group trend plots, distributions, binned scatters for regression discontinuity, hatched bar charts, and grey-ramp maps, with working Stata and matplotlib code, caption and note requirements, and the rule that every figure is regenerated by a script rather than edited by hand. Use this skill whenever someone needs a figure for a paper, thesis, proposal or slide deck, asks for an event-study or coefficient plot, asks to make a chart publication quality, says their figure is too colourful or unreadable in print, or wants an existing chart restyled to a journal standard. Trigger also on vague requests such as "mak
- ▌
- ▌
- ▌ Regression Table Production · ingridleiriaTurns estimation output into a regression table a journal will print, generated from stored estimates rather than retyped. Covers storing and saving estimates, exporting with a table package, one specification per column and one varying dimension per table, indicator rows for fixed effects and control blocks, the sample size row and which R-squared variant belongs where, standard errors in parentheses with the clustering stated in the note, the case for confidence intervals instead of stars, publication coefficient labels, decimal discipline, panel tables for multiple outcomes, and the note that must carry the estimator, the clustering, the sample and the period. Use this skill when someone asks to build or fix a regression table, says their table does not match their code, asks what to report in a table, how many decimals, whether to use stars, what the note should say, or needs Table 2 for a paper, thesis or referee response. Trigger also on vague requests such as "make this look like a real table", "the re
- ▌
- ▌
- ▌ Structured Problem Solving · ingridleiriaThe structured problem solving method used in strategy work, applied to any messy business question. Produces a closed problem statement, a mutually exclusive and collectively exhaustive tree, a day-one hypothesis written to be attacked, a workplan where every analysis is one that could change the recommendation, ghosted exhibits before the analysis is built, and a synthesis written answer first with titles that carry the argument. Enforces the standard that no claim reaches the page without a number, a source, or a visible label saying it is an assumption. Use this skill whenever someone asks to think through a problem, structure an argument, compare options, build a recommendation or a business case, size something, work out why a metric moved, or says their chief executive asked them to look into something, to have a view by Friday, or to work out what is going on with a number. Trigger on any vague business question, which is exactly what it exists to structure.
- ▌ Conference Presentation Deck · ingridleiriaBuilds a research talk that leads with the finding, fits the slot with time left for questions, gives the identification evidence a full slide, and survives a hostile question period, and delivers the deck, the appendix, the timed script and an anticipated-questions sheet with the slide to point to for each answer. Enforces the rule that slide titles are sentences carrying the argument, that the number appears in the first minute and the last, and that figures are readable from the back of a room in monochrome. Use this skill when someone asks to turn a paper into slides, prepare a seminar or conference talk, build a job-market talk, make a poster, present at a lab meeting, or rehearse a presentation, and whenever an existing deck opens with a literature review instead of a result. Trigger also on vague requests such as "I have twelve minutes", "how do I explain this to a general audience", "my talk runs long", or "what will they ask me".
- ▌ Survey And Instrument Design · ingridleiriaDesigns a survey or measurement instrument that produces data worth analysing, and catches the errors that cannot be repaired after fielding. Enforces constructs defined before any question is written, a blueprint mapping every item to a hypothesis and every hypothesis to items, validated scales preferred over invented ones, wording free of leading, double-barrelled, negated and socially desirable formulations, response scales chosen deliberately and used consistently, order and routing controlled and recorded, translation by back-translation with separate piloting per language, cognitive interviews before a live pilot, and a sampling and non-response plan written before fielding. Use this skill when writing a survey or questionnaire, adapting or shortening an existing instrument, translating one, designing the measures for an experiment, adding a module to an existing panel, reviewing somebody else's draft instrument, or diagnosing why a fielded survey produced data nobody can use. Trigger also on vaguer req
- ▌
- ▌
- ▌ Customer Interview Synthesis · ingridleiriaTurns a pile of customer, user or stakeholder interviews, call transcripts, survey responses and support tickets into findings that can carry a decision. Produces a coverage statement naming the gaps, a coded corpus where every tag keeps its verbatim, themes reported on both frequency and intensity, the contradictions and the absences rather than an average, five to eight findings each with counts, quotes, segment pattern and a confidence level, and implications tied to the decision the research serves. Use this skill when someone has interview notes and asks what they say, wants research synthesised, needs a findings readout, asks what customers told us, wants calls summarised, wants to move from anecdotes to evidence before a roadmap, pricing or positioning decision, or says everyone has a different view of what the customers want. Trigger for any qualitative input from more than two sources.
- ▌
- ▌
- ▌
- ▌
- ▌ Weekly Review And Planning · ingridleiriaRuns a personal weekly review and plans the coming week for someone carrying more than one serious commitment, such as a demanding role plus a doctorate, a job plus a venture, or a leadership role plus caring responsibilities. Closes the week honestly against what was planned, counts the hours actually available, protects one deep-work block per commitment before anything else, merges deadlines across commitments six to eight weeks out, and writes down what will not get done. Produces a one-page plan and a running review log that makes the pattern visible over months. Use this skill whenever someone asks to plan or review their week, says "I have too much on", "I do not know what to focus on", "the thesis keeps slipping", "help me get on top of things", wants to balance two commitments, is deciding what to drop, or at the start or end of any week.
- ▌
- ▌
- ▌ Qualitative Coding And Analysis · ingridleiriaTurns interviews, open-text responses, documents or field notes into analysis that survives scrutiny, by making every step from transcript to claim visible. Enforces a stated approach and level of interpretation, a codebook with definitions and inclusion and exclusion rules and an anchor example, coding of the whole corpus rather than the interesting parts, double coding with an agreement statistic that accounts for chance where prevalence claims are made, themes built from codes and tested against negative cases, quotations selected by a stated rule with no participant carrying an argument alone, prevalence language matched to what the data supports, and an audit trail running from any sentence in the paper back to a coded extract. Use this skill for interview analysis, thematic analysis, framework analysis, coding open-ended survey responses, content or document analysis, the qualitative strand of a mixed methods study, or when a qualitative section has been called impressionistic, anecdotal or cherry-picke
- ▌
- ▌ Account Reengagement Plan · ingridleiriaBuilds the plan for restarting a paused, stalled or dormant client relationship before anyone sends a proposal. Produces an account dossier with facts and hypotheses separated, a named diagnosis of why the work stopped, a stakeholder map rebuilt for who is there now rather than who was there then, a five-conversation re-entry sequence with the actual questions, an objection playbook written for restart situations rather than for cold sales, two rehearsal personas, and a dated close-the-file rule so dormant accounts stop polluting the forecast. Enforces the standard that a diagnosis exists before any scope is proposed and that the first ask is a conversation, not a phase. Use this skill whenever an engagement is on hold, a phase was scoped but never signed, a champion has left, a renewal went quiet, an invoice was the last thing that happened, or someone asks how to reopen an account, win back a client, restart a project, warm up a lapsed relationship, or approach a new contact who inherited an old one. Trigge
- ▌
- ▌
- ▌
- ▌ Economics Report From Data · ingridleiriaTurns a revenue, sales, or operating dataset into an economic argument rather than a description. Enforces four levels of analysis from what happened to what to do, applies only the frameworks the data supports (channel economics, concentration, predictability, growth decomposition, whitespace, cost of delay, seasonality), tests every insight for specificity, consequence, traceability, and falsifiability, and delivers in a fixed template with a language standard that replaces hedging with a magnitude or a mechanism. Use it whenever someone asks what the data means, to explain a trend, to size an opportunity or a risk in words, to write an executive summary, an insight memo or a board narrative, or when a deck of charts needs an argument attached to it.
- ▌ Revenue Concentration Risk · ingridleiriaMeasures how exposed a business is to losing a few relationships and how bad that would actually be. Produces Pareto and Herfindahl measures, top-N ratios read against risk bands, an anchoring score built from data signals rather than impressions, a fragility ranking that weights share by grip, a per-client failure scenario carrying replacement cost and replacement time in months, a portfolio revenue quality score out of one hundred, and a diversification gap expressed as a sales target. Use it whenever someone asks how concentrated their revenue is, what happens if the biggest client leaves, whether the client base is too dependent on a few accounts, how a buyer or investor will see the customer book, or says something vaguer like "we are too reliant on them" or "what is our exposure here".