thinking-frameworks-skills

End-to-end company analysis pipeline for standard, profitable companies. Orchestrates business narrative, financial statement cleanup, cost of capital estimation, intrinsic (DCF) and relative (multiples) valuation, capital structure optimization, dividend/buyback policy assessment, and final valuation reconciliation into an investment recommendation. Use when user asks for a complete company analysis, equity valuation, fair value estimate, or investment recommendation for a publicly traded, profitable company.

Quarterly strategic advisor for substacker. Synthesizes the corpus, Curator's section map, Growth Analyst's rolled-up weekly data, and writer's stated goals into a 1500-3000 word review. Surfaces three uncomfortable questions (evidence + reasoning + downside), assesses section portfolio, proposes goal diffs, names one bet for the next quarter, identifies kill list. Rolling 13-week windows, NOT calendar quarters. Use quarterly or on-demand when a specific strategic decision is pending (e.g., "should I launch paid?"). Trigger keywords: quarterly, strategic review, zoomout, uncomfortable questions, paid tier, product hiding, kill list, goals reset.

Continuous vigilance specialist for a household finance pipeline. Watches for missed bills, late recurring payments, duplicate charges within 48 hours, statistical anomalies (>3σ above merchant historical average), first-time large merchants, unexpected fees, and identity-theft signals. Produces severity-tagged alert files with transaction ids, evidence, and recommended actions (call bank, freeze card, dispute, monitor, negotiate fee). Use after every drop, when checking for anomalies post-statement, or when the user reports a suspicious charge.

Stage 4 scheduling worker for the conference-scheduling pipeline. Turns the event records, theme affinities, and preference profile into a feasible day-by-day schedule by solving a constraint-optimization problem — hard constraints (no overlap, travel time, capacity, the attendee's must-attends/blackouts) plus the user-owned weighted objective (interest, breadth, pacing/contiguous-free-time, serendipity). Surfaces unbreakable conflicts as decisions instead of silently picking, and names what the chosen weighting traded away. Reusable across conferences; hardcodes no conference specifics. Writes schedule.json + schedule.md + conflicts.md + rationale.md and returns the schedule.json path. Use as the final stage of a conference-schedule build. Trigger keywords - build schedule, optimize conference plan, resolve overlaps, stage 4 scheduling, packed vs paced.

Meticulous bookkeeper for a household finance pipeline. Takes a manifest produced by the intake classifier and the underlying PDFs, extracts every transaction or holding, normalizes amounts to integer cents and dates to ISO 8601, deduplicates against the existing transaction store, categorizes via taxonomy rules + LLM fallback, reconciles statement math, and writes append-only updates to transactions.json, balances.json, investments.json, retirement.json, hsa.json, and mortgage.json. Halts and flags rather than committing dirty data when reconciliation fails. Use after intake completes, when reprocessing a single statement, or when correcting a categorization batch.

Designs neural network architectures that respect validated symmetry groups, recommending architecture families (G-CNN, steerable CNN, e3nn), layer patterns, and implementation libraries. Use when you have validated symmetry groups and need equivariant architecture design, or when user mentions equivariant layers, G-CNN, e3nn, steerable networks, or building symmetry into a model.

Decomposes complex unknowns into estimable components to produce rapid order-of-magnitude answers with bounded uncertainty. Use when making quick estimates (market sizing, resource planning, feasibility checks), bounding unknowns with upper/lower limits, sanity-checking strategic assumptions, or when user mentions Fermi estimation, back-of-envelope calculation, order of magnitude, ballpark estimate, or triangulation.

Fetches preprints posted to bioRxiv or medRxiv within a given date window, then keyword-filters the results client-side. Wraps the public `api.biorxiv.org/details/{server}/{from}/{to}/{cursor}` endpoint, handles cursor pagination, normalizes records to a stable shape (doi, title, authors, abstract, date, server, version, url), and applies a keyword-OR match against title + abstract. Domain-neutral — usable for any biology / clinical preprint scan, not just one project. Use when user mentions bioRxiv, medRxiv, weekly preprint scan, fetch preprints, last-N-days preprints, or when a literature-scan agent needs structured preprint records.

Uses WebFetch to pull publicly visible subscriber count and per-post public view count from substacker's Substack archive page and individual post URLs. Supplements the CSV when subscriber-count field is stale (>24h old) or when a post has public shares not yet reflected. Rate-limited to ≤10 fetches per invocation. Use when CSV subscribers-end field may have drifted or when external-share attribution needs a public signal. Trigger keywords: public stats, Substack public page, subscriber count check, post views supplement, WebFetch.

Generates exactly 5 distinct intuitive framings for a given technical topic — one everyday analogy, one physical metaphor, one contrarian take, one historical angle, one counterfactual. Each framing is a short scaffold (not prose), paired with its archetype and a one-line framing statement. Use when the writer invokes the Intuition Builder agent, as the core generation step before mapping, stress-testing, novelty checking, and voice fitness. Trigger keywords: generate framings, analogies for, give me 5, intuitive angles, framing set.