數據科學

Comprehensive draft and post access, creating, editing and analysis. When Claude needs to work with the Ghost Admin API to access content published on alt-counsel.com as Houfu's partner.

Applies JAX patterns for scientific Python development. Use when working with JAX, distrax, numpyro, blackjax, or scientific computing. Covers vmap, JIT, RNG handling.

Evaluate the quality and strength of evidence supporting claims, useful for fact-checking, research validation, or making well-supported decisions. Use when: (1) asked to verify a claim, fact-check something, assess evidence quality, or determine if something is true, (2) before presenting quantitative claims or research findings, (3) making causal claims that require distinguishing correlation from causation, (4) relying on studies or reports without verified sourcing, (5) when evidence is indirect and requires inferential leaps, (6) when certainty levels may exceed what the evidence supports

Elite marketing strategy combining Brian Balfour's growth loops, Jobs-to-be-Done framework, Blue Ocean Strategy, attribution modeling, product-led growth, and community-driven tactics. Use for comprehensive marketing strategy, channel selection, growth experimentation, attribution analysis, and sustainable competitive advantages.

Clones HEC-HMS components (basins, met models, control specs, runs) using the CLB Engineering LLM Forward approach. Creates non-destructive, traceable, GUI-verifiable copies for QAQC comparison, scenario analysis, and parameter sensitivity testing. Use when creating alternative scenarios, setting up QAQC workflows, comparing baseline vs updated models, or preserving original while testing modifications. All clones appear in HEC-HMS GUI with separate DSS outputs for side-by-side comparison. Trigger keywords: clone, duplicate, copy, QAQC, scenario, alternative, baseline, comparison, side-by-side, non-destructive, traceable.

View situations from multiple vantage points to gain comprehensive understanding, useful for breaking out of fixed viewpoints, understanding stakeholder needs, or seeing problems differently. Triggered when: (1) asked to examine a situation through contrasting viewpoints or consider what different roles perceive, (2) When stuck on a problem with only one approach emerging, when making design decisions affecting multiple stakeholders, when resolving disagreements between stakeholders, when designing experiences bridging technical and user needs, during analysis paralysis with competing priorities, when evaluating stakeholder objections or concerns, when searching for solutions satisfying competing needs, when stakeholder feedback conflicts with technical constraints, before finalizing approaches impacting different user groups, or when tradeoffs between perspectives feel irreconcilable

Identify named logical fallacies (ad hominem, false dichotomy, slippery slope, appeal to authority, etc.) in arguments by pattern-matching against known flawed reasoning structures. Use when: (1) asked to check for logical fallacies or identify specific argumentative errors by name, (2) arguments rely on emotional appeals or rhetorical techniques rather than evidence-based reasoning, (3) encountering either/or framing that may artificially exclude alternatives, (4) arguments attack credibility of sources rather than addressing substantive claims.

Analyzes iron condor credit spreads with OTM put and call spreads for range-bound trading. Requires numpy>=1.24.0, pandas>=2.0.0, matplotlib>=3.7.0, scipy>=1.10.0. Use when expecting sideways price action, want to collect premium in high IV, analyzing range-bound opportunities, or implementing neutral income strategies on stocks with defined trading ranges.

This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, scenario planning, LBO analysis, and real estate investment modeling for investment decisions

Write, run, and analyze component tests using Vitest 4 and React Testing Library with coverage analysis, visual regression, and accessibility validation

Performs comprehensive analysis of Claude Code sessions, examining git history, conversation logs, code changes, and gathering user feedback to generate actionable retrospective reports with insights for continuous improvement.

Phân tích, gom nhóm, và ĐỒNG BỘ THÔNG MINH giữa Tổng Quan listing và actual group headers. v5.1.0: Intelligent Analysis with agent integration - phân tích thực sự cả hai với hỗ trợ từ specialized agents.

Containerizes applications with impact-aware Dockerfiles and docker-compose configurations. This skill should be used when containerizing projects for Docker, creating Dockerfiles, docker-compose files, or preparing applications for Kubernetes deployment. It performs impact analysis first (env vars, network topology, auth/CORS), then generates properly configured container configs. Invokes the impact-analyzer subagent for comprehensive project scanning.

Recognize when thinking is going in circles, useful when stuck, repeating yourself, or not making progress despite continued effort. Use when: (1) explicit request to detect reasoning loops or check for circular thinking, (2) same points or decision points recur in multiple responses without new conclusions, (3) information gathering or analysis steps haven't changed the approach to the problem, (4) revision cycles continue with diminishing returns while central questions remain unresolved.

Test infrastructure configurations and deployments - security scanning with Checkov/tfsec, cost estimation analysis, pre-deployment validation, post- deployment verification, integration testing, generates comprehensive test reports with pass/fail status, identifies vulnerabilities and compliance issues, tracks test history for trend analysis.

Analyzes long call butterfly spreads with 3 strikes and 4 legs for neutral outlook. Requires numpy>=1.24.0, pandas>=2.0.0, matplotlib>=3.7.0, scipy>=1.10.0. Use when expecting minimal price movement, want low-cost defined-risk strategy, analyzing pinning opportunities, or evaluating tight-range neutral positions on stocks near technical levels.

Component skill for systematic result interpretation with intellectual honesty in DataPeeker analysis sessions

AI coaching for Rocket League using local replay analysis. Use when the user asks about their Rocket League performance, replays, improvement, or coaching. Covers analysis, comparison, weakness detection, and practice recommendations.

Parse URLs in CSV files and extract query parameters as new columns. Use when working with CSV files containing URLs that need parameter extraction and analysis.

Analyzes long strangle volatility plays with OTM call and put at different strikes. Requires numpy>=1.24.0, pandas>=2.0.0, matplotlib>=3.7.0, scipy>=1.10.0. Use when expecting very large price movement, want lower-cost alternative to straddle, analyzing high-volatility events, or evaluating wide-range breakout opportunities on stocks with elevated IV.