lyndonkl-claude

Plugin lyndonkl-claude from marketplace cascade-ai-ml-agents-misc-1 in joshuarweaver/cascade-ai-ml-agents-misc-1. Commands read from the repo's manifest — 1 month ago.

Skills (200)

• abstraction-concrete-examples
• academic-letter-architect
• adr-architecture
• adverse-selection-prior
• advisory-edit
• alignment-values-north-star
• analogy-weight-check
• anomaly-fraud-scanner
• answer-uncomfortable-question
• attribute-performance
• auction-first-price-shading
• auction-winners-curse-haircut
• audit-drift
• bayesian-reasoning-calibration
• brainstorm-diverge-converge
• business-narrative-builder
• career-document-architect
• cash-flow-forecaster
• category-allocation-best-response
• category-trend-analyzer
• causal-inference-root-cause
• chain-estimation-decision-storytelling
• chain-roleplay-debate-synthesis
• chain-spec-risk-metrics
• check-analogy-novelty
• check-corpus-readiness
• chef-assistant
• citation-form-check
• claim-extractor
• classify-claim
• classify-post-to-section
• closer-critique
• cluster-corpus-by-theme
• code-data-analysis-scaffolds
• cognitive-design
• cognitive-fallacies-guard
• communication-storytelling
• company-classification-routing
• component-extraction
• compute-baseline
• concept-rediscovery-walk
• conf-abstract-enrichment
• conf-pipeline-orchestration
• conf-preference-elicitation
• conf-program-extraction
• conf-schedule-optimization
• conf-theme-clustering
• constraint-based-creativity
• corporate-governance-analysis
• cost-of-capital-toolkit
• cross-poster-blurb
• cross-ref-topic-ledger
• cross-reference-claim
• d3-visualization
• data-schema-knowledge-modeling
• dcf-valuation-engine
• debt-design
• decision-matrix
• decomposition-reconstruction
• dedupe-against-corpus
• deliberation-debate-red-teaming
• derive-section-voice-overlay
• design-evaluation-audit
• design-of-experiments
• dialectical-mapping-steelmanning
• discovery-interviews-surveys
• domain-research-health-science
• embedding-fusion-strategy
• environmental-scanning-foresight
• equivariant-architecture-designer
• estimation-fermi
• ethics-safety-impact
• evaluation-rubrics
• expected-value
• experiential-kolb-teaching
• extract-thread-spine
• facilitation-patterns
• fetch-arxiv-recent
• fetch-preprint-recent
• fetch-public-page-stats
• fetch-pubmed-recent
• fetch-substack-stats
• fetch-watchlist-sources
• financial-data-sourcing
• financial-statement-normalization
• financial-unit-economics
• flag-boundary-break
• focus-timeboxing-8020
• forecast-premortem
• generate-analogy-set
• genomics-viz
• geometric-algebraic-bridge
• glossary-alignment-check
• goal-reset-proposal
• grant-proposal-assistant
• graphrag-evaluation
• graphrag-system-design
• hedge-detector
• heuristics-and-checklists
• high-dim-intuition-rebuild
• hook-generator
• household-finance-dashboard-builder
• hsa-receipt-vault
• hypotheticals-counterfactuals
• identify-kill-list
• information-architecture
• ingest-inbox-item
• ingest-substack-csv
• inspectional-reading
• kill-criteria-exit-ramps
• knowledge-graph-construction
• ladder-of-abstraction
• layered-reasoning
• learning-in-public-voice
• linkedin-post-rewrite
• map-analogy-to-concept
• mapping-visualization-scaffolds
• markdown-to-pdf
• market-mechanics-betting
• mastery-assessment
• matchup-win-probability-sim
• mcphee-structure-derivation
• memory-retrieval-learning
• meta-prompt-engineering
• metrics-tree
• ml-primitive-decoder
• mlb-beginner-translator
• mlb-category-state-analyzer
• mlb-closer-tracker
• mlb-decision-logger
• mlb-faab-sizer
• mlb-league-state-reader
• mlb-matchup-analyzer
• mlb-opponent-profiler
• mlb-player-analyzer
• mlb-playoff-scheduler
• mlb-regression-flagger
• mlb-signal-emitter
• mlb-trade-evaluator
• mlb-two-start-scout
• model-equivariance-auditor
• monte-carlo-valuation
• morphological-analysis-triz
• narrative-arc-mapping
• narrative-evidence-ledger
• narrative-fallacy-guard
• narrative-fidelity-audit
• narrative-form-triage
• narrative-handoff-contract
• narrative-opposition-web
• narrative-to-numbers
• negative-contrastive-framing
• negotiation-alignment-governance
• normalize-format
• numbers-in-narrative
• one-pager-prd
• opener-critique
• opponent-archetype-classifier
• option-valuation-toolkit
• paid-tier-readiness-check
• paper-cluster-by-theme
• paper-relevance-filter
• paper-three-pass-extraction
• paragraph-rhythm-check
• payout-policy-analysis
• pdf-statement-parser
• per-section-tracking
• platform-voice-check
• portfolio-drift-rebalancer
• portfolio-roadmapping-bets
• postmortem
• prioritization-effort-impact
• product-hiding-scan
• project-investment-analysis
• project-risk-register
• propose-counterfactual
• propose-section
• prose-force-and-rhythm
• prototyping-pretotyping
• quarterly-zoomout
• rank-by-user-fit
• readability-check
• reader-first-prose
• recommend-prune
• recurring-charge-detector
• reference-class-forecasting
• relative-valuation-toolkit
• research-claim-map
• retrieval-search-orchestration
• reviews-retros-reflection
• roadmap-backcast
• role-switch
• scene-construction-scam
• scientific-clarity-checker
• scientific-email-polishing
• scientific-manuscript-review
• score-intuition-density
• scout-mindset-bias-check
• search-corpus
• section-break-check

Subagents (85)

• biostat-assessor

  Closed-book assessor for the learnbiostats studio. Probes mastery of a module's claims through Socratic, no-notes questioning across Bloom levels, detects misconceptions, bands the result on the Dreyfus-flavored mastery scale, and schedules the next spaced-repetition surfacing. Grounded in the maste

• biostat-coach

  Curriculum coach for the learnbiostats studio. Holds the whole-program view — tracks the learner's position across phases and modules (`curriculum/`, `progress/`), decides what to study next given prerequisites and mastery, paces the plan against a daily cadence, and surfaces the spaced-repetition q

• biostat-editor

  Advisory-only editor for spoken-out, dictated essays in the learnbiostats studio. Directs STRUCTURE, flags grammar, and suggests strategic language — but never modifies the writer's text unless the writer explicitly says "apply"/"rewrite this." Deliberately has no Write/Edit/Bash tools, so it physic

• biostat-emergence

  Bottom-up cluster-finder for the learnbiostats vault. Reads the evergreen/ knowledge graph and proposes structure notes when a real cluster has formed — a minimum of 4 related evergreen notes before a cluster is "ready," and flags over-large clusters (>12 notes) for splitting. Mirrors the reference

• biostat-health

  Auditor of vault + curriculum health for the learnbiostats studio. Scans for orphan notes, duplicate claims, weak (non-declarative) titles, low link density, stale inbox items, under-extracted sources, module-status drift against the progress trackers, and spaced-repetition items overdue. Writes a d

• biostat-lab

  Lab and project mentor for the learnbiostats studio. Designs and reviews the experiential projects and capstones (`projects/`, `projects/capstone/`), scaffolds and runs analysis code against real genomics/phenotype data, and enforces the two disciplines that keep an ML genetics result honest — cross

• biostat-scribe

  Generative note/post writer for the learnbiostats studio. Assembles publish-ready, Obsidian-vault-style notes and Substack-ready posts FROM the writer's own evergreen claims — composition from existing material, never invention of claims the writer has not made. Writes in the writer's voice (learnin

• biostat-tutor

  Socratic, experiential tutor for the learnbiostats studio. Runs a single learning module as a live session through the full Kolb cycle (Concrete Experience → Reflective Observation → Abstract Conceptualization → Active Experimentation), grounded in the experiential-kolb-teaching skill. NEVER summari

• biostat-viz

  Builder of interactive D3 visualizations for the learnbiostats docs/ GitHub Pages site. Turns an evergreen genetics/genomics claim into a teaching figure — a takeaway-stating title, an annotation layer, a guided reading order, and the one interaction that teaches — by applying the genomics-viz skill

• business-narrative-analyst

  Builds the business story behind a valuation and converts it into the drivers the model consumes. Surveys the landscape, writes the narrative in prose, grades every claim as possible, plausible or probable, maps each claim to exactly one dcf-valuation-engine payload field with a range and a reason,

• capital-structure-analyst

  Answers how much debt a firm should carry and what kind it should be. Runs the full cost-of-capital schedule across debt ratios, locates the optimum, prices the move there, stress-tests it at recessionary operating income, applies and prices any rating constraint, then designs the debt itself — matu

• claim-verifier

  Adversarially attacks an assigned batch of calibrated claims — re-derives numbers from independently located primary sources, audits citations, challenges confidence intervals and source grades — and returns a verdict (confirmed, adjusted, rejected, or unverified) with evidence for every claim. Rece

• cognitive-design-architect

  An orchestrating agent that collaboratively helps designers apply cognitive science principles to create effective visual interfaces, data visualizations, educational content, and presentations. Guides users through cognitive foundations, information architecture, D3 visualization implementation, st

• company-diagnostician

  Classifies a company and routes it to the analytical treatment its type allows, then compiles the constraints that bind every later stage. Computes the S1 signals from the filings, applies the sector, ownership, life-cycle and survival gates in precedence order, assigns overlays, and writes classifi

• conf-director

  Master orchestrator for the conference-scheduling pipeline. Runs the four-stage state machine (ingest -> cluster -> elicit -> schedule) across a team of specialist agents, talking to them only through schema-shaped artifacts, verifying each stage's confidence at a gate before advancing, holding and

• conf-enrichment-researcher

  Isolated web-research worker for the conference-scheduling pipeline. Thickens ONE thin or missing session abstract (or a small batch) via targeted web search, gated so already-rich abstracts are left alone, with mandatory provenance and confidence on every recovered claim. Spawned by conf-program-in

• conf-preference-elicitor

  Stage 3 collaborative preference agent for the conference-scheduling pipeline — the one a person actually talks to. Reads the theme map and representative talks first so it is grounded, then asks a SMALL number of sharp, choice-based questions contrasting real sessions, holds the person's interests

• conf-program-ingestor

  Stage 1 ingestion worker for the conference-scheduling pipeline. Parses a conference program (any format) into normalized event records with per-field confidence and independent axes, flags thin abstracts, fans out the high-volume web enrichment to conf-enrichment-researcher sub-workers, merges the

• conf-schedule-optimizer

  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/blac

• conf-theme-cartographer

  Stage 2 clustering worker for the conference-scheduling pipeline. Turns event records into a navigable theme map — 6-8 coarse themes with sub-clusters, an explicit outlier bucket, and soft top-k affinities for every event — using the embed-then-label pipeline (resources/cluster.py) when the librarie

• cost-of-capital-analyst

  Estimates the discount rate and defends every input behind it — the riskfree rate in the mandate currency, an equity risk premium weighted by where the company actually operates, a bottom-up beta from a named comparable set, the cost of debt from the right rating table, market-value weights, and the

• curator

  Shape-watcher for the substacker publication. Every 4-6 weeks reads the accumulating corpus, proposes emerging sections (when active-launch is not pre-planned), audits drift on existing sections, maintains section-map.md and per-section profiles. Also handles active mode — classifies drafts into sec

• distribution-translator

  Turns each published substacker essay into platform-native rewrites. Primary platforms — LinkedIn post + Substack Note + cross-poster blurb (writer's preferred distribution surface). Optional — X thread (generated only if the essay translates well to X; otherwise skipped cleanly). Platform-native re

• editor

  Two-pass review (structural + voice) on substacker drafts. Produces marked-up critique, never a replacement draft. Flags voice-don'ts (delve, unpack, paradigm shift, generic opener), catches hedges that weaken rather than specify, blocks AI-explainer slop, verifies opener/closer/analogy-weight/rhyth

• financial-data-collector

  Gathers every external input a company analysis needs — filings, footnotes, market data, macro series and the Damodaran reference tables — and reports honestly what it could not find. Accepts user-supplied statements and files, prefers them over anything it fetches, and searches only for what the us

• financial-statement-analyst

  Converts reported accounting statements into valuation-ready numbers by running the S3 statement-repair sequence — trailing-twelve-month update, operating lease capitalization, R&D capitalization, one-time and personal expense removal, cycle normalization where the routing demands it, and a rebuilt

• geometric-deep-learning-architect

  An orchestrating agent that collaboratively helps ML engineers apply group theory and symmetry principles to neural network design. Guides users through symmetry discovery, validation, group identification, equivariant architecture design, and model verification. Use when user mentions symmetry, inv

• graphrag-specialist

  An orchestrating agent that collaboratively helps engineers build graph-based retrieval-augmented generation systems. Guides users through knowledge graph construction, embedding strategy design, retrieval orchestration, system integration, and evaluation. Use when user mentions knowledge graph, Gra

• growth-analyst

  Weekly Substack performance analyzer for substacker. Pulls stats directly from the Substack dashboard via Claude-in-Chrome browser automation (primary) or ingests a manual CSV export (fallback). Computes rolling 4-week baseline, attributes over/under-performance in plain English with calibrated conf

• growth-strategist

  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 go

• household-bills-vigilance

  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 sev

• household-bookkeeper

  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 t

• household-cfo

  Master orchestrator and synthesizer for the household finance team. Runs the per-drop pipeline (intake → bookkeeper → spending/vigilance/savings/investments/tax in parallel → CFO synthesis), the monthly briefing pipeline, the weekly dashboard generation, and the on-demand chat mode where the user as

• household-dashboard-designer

  Generates the weekly static HTML dashboard for the household finance JSON store. Reads the canonical data files, applies cognitive-design principles for visual hierarchy and visual-storytelling-design for narrative annotations, runs cognitive-fallacies-guard to prevent visual misleads, and produces

• household-intake-classifier

  Document intake specialist for household finance pipelines. Classifies every PDF in a drop folder by document type (checking, savings, credit card, brokerage, 401k, HSA, mortgage, tax form, insurance), matches each against existing accounts by institution + mask, proposes new account records when no

• household-investment-retirement

  Tracks and advises on the long-horizon portfolio — taxable brokerage, 401k, and HSA invested portion — by aggregating asset allocation across all three, computing drift versus target, optimizing contributions (employer match, annual limits, HSA investment threshold), scanning for tax-loss-harvest ca

• household-savings-debt

  Manages the household short-to-medium-horizon balance sheet — emergency fund, sinking funds, mortgage, any consumer debt, and credit-card rewards optimization. Tracks goal progress and pacing, sizes the emergency fund against essential expenses, ranks debts by APR for avalanche payoff, models mortga

• household-spending-analyst

  Household spending analyst that answers, every month, where the money went, what changed versus prior months and same-month-last-year, what is recurring, what is an outlier, and what is coming up. Produces the Spending section of the monthly briefing, runs a quarterly subscription audit, projects 60

• household-tax-compliance

  Tracks tax-relevant events year-round so April is a non-event. Maintains the expected-document checklist (W-2, 1099-DIV/INT/B, 1098, 5498-SA, 1095), accumulates deduction candidates from transactions, manages the HSA receipt vault for deferred reimbursement, surfaces tax-aware moves throughout the y

• intrinsic-valuation-analyst

  Turns value drivers into an intrinsic value per share and states what the market price already assumes. Chooses the DCF model variant, sets the forecast drivers from the narrative and the cleaned financials, runs the valuation engine, closes with a disciplined terminal value, walks the equity bridge

• intuition-builder

  Generates 5 distinct intuitive framings for a technical topic the writer wants to explain — everyday analogy, physical metaphor, contrarian, historical, counterfactual. Each framing includes explicit component-by-component mapping, where the analogy breaks, novelty check against the analogy catalog,

• investment-analyst

  Evaluates a discrete investment, project or acquisition on incremental after-tax cash flows. It discounts them at a hurdle rate matched to the investment's own risk and currency. In project mode it builds the incremental stream, strips sunk costs and allocated fixed overhead, charges side costs, and

• investment-reconciler

  Reconciles every strand of a finished analysis into one verdict and writes the report a decision-maker reads. Sets intrinsic value against the pricing estimates and against the market price, states the margin of safety, and issues the recommendation with its catalysts, its risks and what would chang

• librarian

  Ingests and indexes the writer's Substack corpus. Watches the substacker inbox/ for new material (markdown notes, transcripts, Claude conversation exports, Readwise highlights), normalizes format, tags by topic and intuition density, dedupes against existing corpus, maintains the topic-ledger, and s

• literature-scan-coach

  Search worker for one keyword query across bioRxiv, medRxiv, PubMed, and arXiv. Spawned by an orchestrator that's running a fan-out (one coach per expanded query). Receives a date window, a single query, and an arXiv category list; fetches all four sources in parallel via the fetch-* skills; dedupes

• macroeconomic-analyst

  Researches a single assigned trend category in depth via web search and produces a structured trend report covering sub-trends, value chains, beneficiary archetypes, pricing-in assessment, risks, and watch-indicators. Receives the trend category, anchor questions, and an output path as inputs, and w

• market-era-historian

  Researches the structure of an assigned market during an assigned time period and fills a provided field schema with sourced, calibrated claims. Receives the market, period, mechanism summary, schema spec, rigor spec, factual constraints, seed material, and output paths as inputs. Use when a researc

• math-intuition-coach

  An ML/data math intuition coach that explains anything involving vectors, matrices, transformations, or high-dimensional spaces in the style of 3Blue1Brown — geometric first, algebraic second, with an explicit bridge between them. Covers linear algebra, calculus, probability, and the ML primitives b

• mechanism-analyst

  Produces a worked-number analysis of an assigned market mechanism or economic arrangement — how it works, why it beats or loses to named rival designs or a stated counterfactual, where it breaks — and emits a simulation-ready parameterization. Receives the mechanism spec, rival designs, claims to te

• mlb-category-strategist

  Plans a weekly H2H Categories matchup strategy — which of the 10 cats (R/HR/RBI/SB/OBP, K/ERA/WHIP/QS/SV) to push, which to maintain, which to punt. Fires advocate (Balancer) + critic (Puncher) variants per matchup. Drives waiver/streaming/lineup priorities for the week. Use on Monday mornings or wh

• mlb-fantasy-coach

  Orchestrates a multi-agent team for Yahoo Fantasy Baseball management. Spawns specialists (lineup, waiver, streaming, trade, category, playoff) each in advocate + critic variants, runs dialectical-mapping-steelmanning synthesis, deliberation-debate-red-teaming stress tests, and produces plain-Englis

• mlb-lineup-optimizer

  Picks today's Yahoo Fantasy Baseball lineup for a 26-roster H2H Categories league with OBP/QS scoring. Fires in two variants — advocate (steelmans each start) and critic (red-teams each start) — then synthesizes per slot. Emits daily_quality signals and writes a START/SIT decision per active roster

• mlb-playoff-planner

  Plans Yahoo Fantasy Baseball playoff pushes for weeks 21-23 (ending Sep 6). From July onward, identifies players with most games and best matchups in playoff weeks, suggests trade-deadline (Aug 6) targets, evaluates IL stashes. Fires advocate (Aggressor) + critic (Stabilizer) variants. Use after Jul

• mlb-streaming-strategist

  Plans weekly pitching moves for a Yahoo Fantasy Baseball H2H Categories league with QS/K/ERA/WHIP/SV scoring (no wins). Identifies two-start SPs, favorable spot starts, and rostered SPs to bench on bad matchups. Fires advocate (Stream) + critic (Hold) variants per candidate. Use for weekly pitching

• mlb-trade-analyzer

  Evaluates Yahoo Fantasy Baseball trade offers. Runs advocate (Acceptor) + critic (Rejecter) variants, computes per-category deltas for both sides across all 10 categories (R/HR/RBI/SB/OBP, K/ERA/WHIP/QS/SV), factors in regression, positional scarcity, and playoff schedule. Verdict is ACCEPT, COUNTER

• mlb-waiver-analyst

  Scans Yahoo Fantasy Baseball free agents for weekly waiver claims (FAAB league, $100 season budget). Fires in advocate (Buy) and critic (Pass) variants, synthesizes, and produces ranked ADD + BID $X recommendations with drop candidates. Use for weekly waiver priority review, FAAB bid sizing, prospec

• narrative-architect

  Turns a researched corpus into a validated narrative architecture — evidence ledger, form triage, designing principle, opposition web, beat map — before any prose is written. Selects the structure (Truby arc, explanatory spine, pyramid/SCQA, braided mosaic, or none) rather than assuming one, and can

• paper-extractor

  Per-paper structured-extraction worker for ONE paper at ONE pass depth. Spawned by an orchestrator that's running per-paper fan-out (one extractor invocation per paper). Receives a single paper record, an output directory, a week tag, and the pass to run (1, 2, or 3). Reads the paper at the requeste

• paper-synthesizer

  Two-mode synthesis worker for paper digests. **Mode A** reads one paper's extraction notes and writes a reader-facing per-paper summary (headline + summary + specifics, with all hedging preserved) to a markdown file. **Mode B** reads a folder of per-paper summaries, clusters them by theme, writes th

• payout-policy-analyst

  Judges whether a company returns the right amount of cash to its owners. Computes FCFE over a 5-year history in three debt variants, compares it against dividends plus buybacks, scores management trust from ROE against cost of equity and Jensen's alpha, places the firm in the dividend matrix, and te

• product-strategist

  Reverse-engineers a real product's strategy from the outside using public material, and writes it up so a reader with no background can follow it. Works through vision, competitive strategy, tactical moves, and the product surfaces users touch, grading every strategic claim by how much evidence stan

• real-options-analyst

  Values genuine embedded optionality and rejects the candidates that only look like options. Runs the three-part gate — option test, exclusivity test, pricing test — over every candidate the routing flagged, rejects the ones that fail, and prices the survivors with Black-Scholes or a binomial tree, s

• relative-valuation-analyst

  Prices a company against its peers and against the market using multiples, and says when the evidence will not support a verdict. Runs the four-step discipline — define the multiple, describe its distribution, derive its companion variable, apply it with controls for the differences that remain. Bui

• scenewright

  Executes a narrative architecture into prose at scene and sentence level — SCAM scene qualification, point of view and narrative distance, ladder of abstraction, telling-detail selection, number handling, and Hart's nine Wordcraft passes run in strict order. Source-bound — every concrete detail, quo

• scientific-writing-editor

  An orchestrating agent for scientific writing that routes requests to specialized skills for manuscripts, grants, letters, emails, career documents, and cross-cutting clarity review. Provides multi-pass editing following structured workflows with document-type-specific frameworks. Use when user need

• series-archaeologist

  Locates, assesses, and stitches long-run data series for an assigned metric into one dataset with per-point provenance. Documents every source series (compiler, method, coverage, definitions), maps the breaks between them, and builds a concordance plus bridged estimates instead of splicing silently.

• skill-creator

  Orchestrates the end-to-end transformation of a methodology document (PDF, markdown, book chapter, research paper, framework guide) into a properly structured Claude Code skill - SKILL.md plus optional resource files plus an evaluation rubric. Runs Adler's six-step reading-and-construction methodolo

• special-situations-analyst

  Runs the valuation branches a standard discounted cash flow cannot handle — financial service firms on excess return or dividends, young and pre-revenue firms driven from revenue with a failure probability, distressed firms blended against a distress-sale value or valued as a call option, private co

• stage-auditor

  Verifies that a pipeline stage satisfied its contract before work advances. Receives a machine-readable stage contract (preconditions, required artifacts, invariants with their checks) plus a report path; runs the deterministic checks, judges the non-deterministic invariants against the artifacts, a

• superforecaster

  An elite forecasting agent that orchestrates reference class forecasting, Fermi decomposition, Bayesian updating, premortems, and bias checking. Adheres to the "Outside View First" principle and generates granular, calibrated probabilities with comprehensive analysis. Use when user asks for forecast

• technical-reviewer

  Pre-publish ML/systems claim check for substacker drafts. Extracts atomic technical claims from prose, classifies each as simplified-correct / simplified-boundary / wrong / contested / overclaim, cross-references primary sources (arXiv, RFC, textbooks — never blog posts), flags boundary-breaks as te

• trend-scout

  Weekly ML/systems signal radar for substacker. Scans ~30-50 curated intuition-first sources (Olah, Weng, Karpathy, Jay Alammar, Raschka, Willison, Transformer Circuits, Interconnects, arXiv cs.LG, Hugging Face papers, etc.) for signal-not-noise items, cross-references against topic-ledger, produces

• valuation-critic

  Attacks a finished analysis and reports what breaks. Runs the consistency validator first, then works the red-team sequence — route conformance, bias, single charge per risk, growth paid for, terminal value plausibility, the equity bridge, implied expectations, comparable-set bias, and the seven sin

• valuation-orchestrator

  Runs a complete company analysis end to end — valuing a company, assessing its corporate finance decisions, pricing an acquisition target, evaluating a project, planning an IPO, or testing a restructuring. Classifies the company first, routes it to the right specialists, enforces the gates between s

• wc-chip-strategist

  Times the five single-use chips (Wildcard, 12th Man, Maximum Captain, Clean Sheet Shield, Qualification Booster) across the whole FIFA World Cup Fantasy tournament horizon. Maintains a living deployment plan — which chip is earmarked for which upcoming round, the trigger condition that fires it, and

• wc-director

  User-facing orchestrator for FIFA World Cup Fantasy. Runs the evolutionary generation loop — spawns archetype strategist teams in parallel, drives fitness/selection/recombination via wc-evolution-engine, has specialists adversarially verify the offspring, then presents a DECISION BOARD of 2-4 weight

• wc-evolution-engine

  The recombination core of the FIFA World Cup Fantasy system. Takes the population of candidate squads/plans produced by the parallel archetype strategists and runs the genetic operators from the Evolution document — scores risk-adjusted, rank-relative fitness; selects an elite set spanning the varia

• wc-fixture-analyst

  The tournament-theory pillar of the FIFA World Cup Fantasy backroom. Rates per-team fixture difficulty for the round (and across the horizon), estimates progression probabilities (group qualification + each knockout round) via reference-class base rates updated Bayesianly on form, flags weak-group m

• wc-matchday-tactician

  Optimises the in-round levers for FIFA World Cup Fantasy — the strongest formation-valid XI from the 15, the CAPTAIN LADDER (ordered armband choices across the round's staggered kickoffs with bank-or-switch thresholds), bench order by kickoff time, and manual-sub triggers. This is the single biggest

• wc-ownership-analyst

  Estimates the field for FIFA World Cup Fantasy — public ownership and EFFECTIVE ownership (EO = field_own% × (1 + captaincy_share)), the template set vs the differential list, where the field is OVER-CONCENTRATED (a fade opportunity) and where it is UNDER-REACTING to fixture/rotation news (a get-the

• wc-scout
• wc-squad-architect
• wc-strategist
• wc-synthesis
• writing-assistant

Hooks (2)

• Stop

  python3 "${CLAUDE_PLUGIN_ROOT}"/skills/readability-check/hooks/readability_hook.py

• PostToolUse

  python3 "${CLAUDE_PLUGIN_ROOT}"/skills/readability-check/hooks/readability_hook.py

Similar plugins