Claude Skills by stanfish06

Audits an existing test file or suite in any language for anti-patterns and quality issues — produces a severity-ranked report (Critical/Warning/Info). INVOKE whenever asked to audit or review tests, find what's wrong with a suite, judge whether tests are any good, or check for: tests that pass but verify nothing, missing assertions, swallowed exceptions, self-comparing / tautological assertions, coverage-touching tests, broad exceptions, flaky or order-dependent tests (Thread.Sleep, DateTime...

Performs pseudo-mutation analysis on production code in any language to find gaps in existing tests. Use when the user asks to find weak or shallow tests, discover untested edge cases, or check whether tests would catch a bug — e.g. \"would my tests catch it if someone changed the code\", \"would a subtle logic or boundary change slip past the current tests\", \"are my tests strong enough to catch a subtle bug\". Evaluates test effectiveness through mutation-style reasoning: analyzes mutation...

Deep-dive audit using the full testsmells.org 19-smell academic catalog for tests in any language. Every finding maps to a named, citable smell from the research literature (Assertion Roulette, Duplicate Assert, Mystery Guest, Eager Test, Sensitive Equality, Conditional Test Logic, Sleepy Test, Magic Number Test, etc.) with research-backed severity. Polyglot: .NET (MSTest/xUnit/NUnit/TUnit), Python (pytest/unittest), TS/JS (Jest/Vitest/Mocha/node:test), Java (JUnit/TestNG), Go, Ruby (RSpec/Mi...

Analyzes test suites in any language and tags each test with standardized traits (positive, negative, critical-path, boundary, smoke, regression, integration, performance, security). Use when the user wants to categorize, audit, or label tests with traits. Works across .NET (MSTest/xUnit/NUnit/TUnit), Python (pytest), TS/JS (Jest/Vitest), Java, Go, Ruby, Rust, Swift, Kotlin, PowerShell, and C++ — auto-editing when the framework has canonical tag syntax, otherwise report-only. Do not use for w...

Triage macOS tests across Xcode and SwiftPM. Use when narrowing failures, explaining assertions or crashes, or separating setup from regressions.

Test data visualizations and dashboards. Use when the user needs chart or diagram test strategy, screenshot or image diff testing, visual regression, mocked or synthetic chart data, component or unit tests, E2E dashboard QA, interactive UML-like diagram verification, scroll-driven story verification, export verification, or guidance on avoiding brittle over-testing.

Expert-thinking profile for Theoretical Chemist (dynamics theory / PES construction / TST & master-equation kinetics / quantum scattering): Reasons from Hamiltonians, partition functions, and flux through dividing surfaces using validated potential energy surfaces, variational transition state theory with Eckart and small-curvature tunneling (Polyrate), and master-equation falloff solvers (MESMER, MultiWell), while treating spurious saddle imaginary...

Expert-thinking profile for Theoretical Computer Scientist (theoretical / complexity, algorithms, and formal proof): Reasons from explicit models (TM, circuit, communication, query) and resource measures; audits Karp/parsimonious/gap/fine-grained reductions against ETH/SETH/#ETH and PCP/UGC/APX barriers; uses Complexity Zoo, ECCC/arXiv cs.CC, Coq/Lean/DRAT, Williams algorithms-for-lower-bounds, and Yao/IC lower bounds while treating...

Expert-thinking profile for Theoretical Physicist (analytic theory / QFT & EFT / lattice & many-body numerics / RG & critical phenomena / GR & gravitation): Reasons from symmetries, conservation laws, effective field theory, and limiting cases through Feynman-diagram and on-shell amplitude tools, renormalization-group flow, lattice and tensor-network numerics, and the conformal bootstrap, while treating gauge-dependent artifacts, unitarity and Ward-identity violations...

Expert-thinking profile for Thermodynamics Engineer (energy-system analysis / cycle modeling / exergy & pinch / heat exchangers / acceptance testing (ASME PTC, AHRI)): Reasons from energy conservation, entropy generation, state properties, and exergy quality through cycle modeling on T-s/h-s diagrams, IAPWS-IF97/REFPROP/CoolProp property models, LMTD/ε-NTU and pinch analysis, and ASME PTC/AHRI acceptance protocols, while treating efficiency-above-Carnot claims, pinch violations...

Use for authorized security testing of desktop thick clients including local storage, update channels, IPC, traffic, and client-side trust boundaries.

Expert-thinking profile for Thin-Film Scientist (deposition (PVD/CVD/ALD) / thin-film metrology / stress & adhesion / optical coatings / semiconductor fab): Reasons from nucleation and growth modes, film stress, interfacial adhesion, and conformality across topography through spectroscopic ellipsometry, XRR, Stoney wafer-curvature, XPS/RBS, and standards like ASTM E2244 and ISO 9211 while treating columnar porosity, barrier pinholes, reactive-sputter hysteresis drift, and...

Use for blue-team threat hunting, detection engineering with Sigma/YARA, SIEM query design, and incident detection validation.

Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model, or the user explicitly asks to create, update, or persist a repository threat model. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.

Implement browser-game runtimes with plain Three.js. Use when the user wants imperative scene control in TypeScript or Vite with GLB assets, loaders, physics, and low-level WebGL debugging.

Render WebGL-accelerated data visualizations with Three.js, raw WebGL, deck.gl, luma.gl, PixiJS, Sigma.js, Plotly WebGL traces, ECharts GL, CesiumJS, Babylon.js, or related GPU libraries. Use when the visualization needs true spatial structure, dense 2D or 3D GPU rendering, particle or flow animation, volumetric views, or interactive exploration that adds real analytical value.

Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.

Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.

Expert-thinking profile for Tissue Engineer (wet-lab / regenerative medicine): Reasons from the TE triad, Krogh transport limits, and Engler mechanobiology through perfusion bioreactors, dECM constructive remodeling, ASTM F2150/F1635 characterization, and ARRIVE/ISO 10993/21560 translation—treating hypoxic cores, acellular controls, and biological-vs-technical replicate inflation as first-class...

Expert-thinking profile for Topologist (proof-based / algebraic topology / low- dimensional & knot theory / TDA (persistent homology)): Reasons from continuity, compactness, connectedness, homotopy, and manifold structure through invariants and tools like π₁ via Seifert-van Kampen, cellular/simplicial homology with ∂²=0 and Smith-normal-form torsion, Mayer-Vietoris, and SnapPy/GUDHI computation, while treating lost-Hausdorffness in quotients, torsion...

PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch_geometric, not for general NetworkX analytics or non-graph PyTorch models.

PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc.

Expert-thinking profile for Toxicologist (regulatory / pharmaceutical / industrial chemical safety): Reasons from dose–response, ADME/TK, MOA/AOP, and exposure context; separates hazard from risk; derives BMDL/DNEL/RfD PODs and interprets OECD/ICH batteries with vehicle, strain, S9, and histopath artifacts as first-class failure modes.

Track validated Codex Security findings in Linear, Jira, GitHub issues, or draft GitHub security advisories. Use it for one finding or an explicitly selected batch of up to 25 findings tracked as Linear, Jira, or GitHub issues. Includes duplicate checks, exact previews, approval-gated writes, and readback. Do not use it for scans or fixes.

Expert-thinking profile for Traffic Engineer (operations / safety / signal & corridor analysis): Reasons from LWR/CTM flow, HCM delay/v/c/LOS, K-D-PHF-DDHV volumes, ITE TGM 12th/MTIASD TIAs, Synchro/HCS/SIDRA/VISSIM workflows, and HSM SPF+CMF+EB safety — treating unc calibrated models, naive before–after crashes, and LOS-without-v/c as first-class failure modes.

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in Node.js and browsers (with WebGPU/WASM) using pre-trained models from Hugging Face Hub.

Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Use when working with AutoModel, pipelines, tokenizers, or TrainingArguments—not for general ML outside the Transformers library.

Expert-thinking profile for Translational Researcher (preclinical / IND-IDE-enabling / early clinical PoC & biomarker translation): Reasons from T0–T4 stage gates, murine vs NHP translatability, PK/PD allometric bridging, MRSD/MABEL FIH dose selection, BEST/CLIA/CAP biomarker tiers, and CONSORT/SPIRIT/STROBE reporting while treating target-wrong, model-wrong, non-predictive biomarker, and preclinical irreproducibility as first-class failure modes.

Expert-thinking profile for Transportation Engineer (planning / demand modeling / geometric design / corridor evaluation): Reasons from four-step and activity-based travel demand (CUBE/Visum/EMME), AASHTO Green Book geometry, HCM capacity, MPO LRTP and NEPA 23 CFR 771 project development, and multimodal corridor MOEs while treating unvalidated TDM forecasts and capacity-without-demand balance as first-class failure modes.

Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.

Use when the user supplies or imports existing security findings, vulnerability reports, or security/vulnerability Jira/Linear tickets from scanners, advisories, GitHub, Atlassian Rovo, Linear, or similar backlog sources and wants static repo-impact triage. Do not use for discovery, duplicate-bug triage, validation, or fixes.

Expert-thinking profile for Tribologist (tribometry / contact mechanics & EHL / lubricant & coating selection / wear failure analysis / condition monitoring (ASTM G99, ISO 281/4406)): Reasons from contact mechanics, lubricant rheology, Stribeck- regime and λ ratio through Hamrock-Dowson EHL film estimates, pin-on-disk/four- ball/SRV/FZG bench tests and SEM-EDS/ferrography scar analysis while treating scuffing, rolling-contact pitting, three-body abrasion and DLC adhesive transfer as first-cla...

Headless topological data analysis and visualization with the Topology ToolKit (TTK) on top of ParaView. Use this skill when Claude needs to: (1) Compute and visualize persistence diagrams, contour trees, merge trees, and Morse-Smale segmentations, (2) Extract and render critical points of scalar/vector fields, (3) Apply persistence-based topological simplification to denoise scalar fields, (4) Run TTK filters headlessly via pvpython (loading TTK plugins and using the Scalars_ naming conventi...

Expert-thinking profile for Tunnel & Underground Engineer (geotechnical / NATM-SEM & TBM tunneling / rock-mass classification (Q/RMR/GSI) / ground-support convergence / fire-life safety (NFPA...): Reasons from ground-structure-water-air interaction, convergence-support interaction, and face-stability limit states through Q/RMR/GSI classification, Hoek-Brown numerical models (PLAXIS, FLAC), Peck settlement troughs, and DAUB-ITA/NFPA 502 standards while treating face blowout, squeezing, invert ...

Expert-thinking profile for Turbomachinery Engineer (rotating-equipment design / meanline-to-CFD / rotordynamics / performance test (ASME PTC 10, API 617)): Reasons from Euler work transfer, velocity triangles, decomposed loss correlations, and map- based off-design margin through meanline-to-throughflow-to-RANS/URANS analysis, Campbell and unbalance rotordynamics, and ASME PTC 10/PTC 6 and API 617 testing while treating surge and rotating stall, clearance rubs and tip...

Turborepo expert guidance. Use when setting up or optimizing monorepo builds, configuring task caching, remote caching, parallel execution, or the --affected flag for incremental CI.

Build, query, and analyse biomedical knowledge graphs in TuringDB, a columnar graph database with git-like versioning.

Rules for Twilio messaging and voice traffic. Covers TCPA (consent tiers, quiet hours, DNC), GDPR (EU consent, right to deletion), PCI DSS (payment recording, Pay verb), HIPAA (BAA, PHI), FDCPA (debt collection limits), CAN-SPAM, WhatsApp policies, SHAKEN/STIR, and consent management patterns. Use when developers have working traffic to ensure they follow the rules.

Use when building Twilio Enterprise Knowledge workflows for AI or human agents, including provisioning a knowledge base, adding website, PDF, or text sources, semantic search, or grounding responses in approved organization content. Use this for enterprise business knowledge; use `twilio-customer-memory` for person-specific customer context.

Build typed data visualizations in TypeScript. Use when the user wants TypeScript visualization code, typed data models, browser visualization components, UML-like diagram models, interactive graph or architecture diagram contracts, scroll-driven scene contracts, library selection guidance, or a maintainable visualization architecture beyond React- or Next-specific concerns.

Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".

Use when the user wants to use the UCP CLI to find, compare, buy, or track products from online merchants, or to set up and troubleshoot the local UCP profile required for merchant-scoped operations. Covers global catalog search (\"find me X under $Y\"), named-merchant transactions (\"buy this from Z.com\"), order tracking, `ucp profile init`, `ucp doctor`, carts, checkout, orders, and UCP setup/help. Falls back to merchant-hosted handoff when direct in-protocol checkout isn't available.

Specifies CSS-level implementation primitives for UI work — OKLCH palette construction, motion duration and easing tokens, interactive and input state coverage, text-on-fill contrast pairing, and framework-agnostic responsive-correctness bugs. Use when writing or reviewing CSS tokens, building a colour palette, implementing interactive or input states, debugging a UI that looks "almost right", or fixing layout that breaks at narrow viewports.

Use when using Zoom UI Toolkit.

Design, critique, read, write, render, and implement UML and UML-like software diagrams. Use when the user mentions UML, sequence diagrams, class diagrams, activity diagrams, state machines, use case diagrams, component diagrams, deployment diagrams, object diagrams, package diagrams, profile diagrams, timing diagrams, communication diagrams, interaction overview diagrams, composite structure diagrams, ERDs, database schema diagrams, C4, BPMN, swimlanes, flowcharts, network diagrams, applicat...

Bottoms-up unit economics decomposition for any public company

Guide for upgrading Stripe API versions and SDKs

Expert-thinking profile for Urban & Infrastructure Planner (policy / capital programming / asset management): Reasons from comp plan–FLUM–zoning consistency through Euclidean/form-based overlays, CIP/TIP–STIP and ISO 55001/IIMM asset portfolios, ArcGIS Urban parcel workflows, and CEJST/AFFH/Justice40 equity screening while treating FLUM–zoning mismatch, CRS topology errors, and unfunded backlog as first-class failure modes.

Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.

Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.