Claude Skills by stanfish06

INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.

INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.

INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.

Expert-thinking profile for Deep Learning Scientist (computational / architecture & large-scale training): Reasons from CNN/Transformer inductive bias, Li et al. loss landscapes, grokking/mode connectivity, and Kaplan/Chinchilla scaling (~20 tokens/param); designs ResNet/ViT/DiT/MoE/FlashAttention stacks with FLOPs-matched ablations; trains AdamW+cosine/WSD via Megatron-FSDP/DeepSpeed; evaluates FID/MMLU- Pro/MMLU-CF with...

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report co...

Use when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide or scoped-path Codex Security scan. Run repeated independent discovery passes over one resolved scope with worker-specific threat models, semantically merge candidates, synthesize one canonical validation threat model, then run validation, attack-path analysis, canonical JSON completion, and generated reporting once. Do not use for PRs, commits, branch diffs, or working-tree diffs.

Scaffold a minimal local Deep Agent in Python by following the official quickstart, using provider-native web search instead of Tavily. Use when the user wants to quickly build or try a Deep Agent locally.

Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using provider-native web search instead of Tavily. Use when the user wants to quickly build or try a Deep Agent locally.

Use when running Deepnote notebooks, inspecting notebook inputs, reviewing integration references and cached table structure, listing run history, or interpreting run status and snapshot outputs through the Deepnote app tools.

Use when a task asks for Deepnote URLs, links, project links, notebook links, workspace links, share links, UTM/campaign links, or when a Deepnote response should include clickable links built from Deepnote app project, notebook, or workspace data.

Use when creating Deepnote projects or notebooks, adding or updating blocks or cells, moving existing blocks, scaffolding notebook content, inserting SQL/code/markdown/input blocks, or otherwise editing notebook structure through the Deepnote app tools.

Use when reading, reviewing, inspecting, or reasoning about hosted Deepnote notebooks, blocks, inputs, SQL, Python, or notebook outputs through the Deepnote app tools.

Use when a task mentions Deepnote, the connected Deepnote app, Deepnote OAuth connection, Deepnote docs, projects, workspaces, notebooks, blocks, integrations, or notebook runs.

Expert-thinking profile for Dentist-Scientist (clinical / research): Reasons from oral biofilm-host ecology, tissue healing capacity, and patient-level clinical endpoints (DMFS, PD/CAL, implant survival) through PICO/PROSPERO protocols, CAMBRA and 2017 AAP/EFP staging, ISO 4049/14801 bench tests with thermocycling, and GRADE-rated reviews while treating in-vitro-to-chairside leaps...

Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use for identifying cancer-specific vulnerabilities, synthetic lethal interactions, and validating oncology drug targets.

Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when deciding whether to maintain or sunset existing code.

Expert-thinking profile for Dermatologist (clinical / research): Clinical-research dermatologist: layered skin anatomy, inflammatory dermatoses and trial endpoints, dermoscopy vs clinical ABCDE, biopsy/pathology, patch testing, telederm, AAD guidelines, and topical steroid potency.

interview the user to design an agentic control loop (sensor, controller, actuator under disturbances) tailored to their codebase, then build it as locally-runnable components plus a scheduled coding-agent workflow

narrow React component prop types to match live code paths

Library of 74 ready-to-use DESIGN.md files — complete design systems (color tokens, type scale, components, layout, motion, do's/don'ts) reverse-engineered from real product and brand websites like Stripe, Linear, Vercel, Notion, Apple, Tesla, WIRED, and Nintendo-2001. Use when a UI task names a reference brand or an aesthetic ("make it look like Linear", "Stripe-style landing page", "premium automotive dark theme"), when you need a concrete token set to start a design system from, or when a ...

The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

Expert-thinking profile for Developmental Biologist (embryology / fate-mapping & lineage tracing / morphogenesis imaging / GRN dissection / perturbation (CRISPR, morpholino, Cre-lox)): Reasons from stage, positional information, gene regulatory networks, and tissue mechanics through morphology-based staging (Carnegie/HH/Theiler/NF/hpf), French-flag morphogen logic, light-sheet 4D imaging, lineage tracing, and ARRIVE/MDAR/REMBI reporting while treating developmental delay, CRISPR F0 mosaicism...

Expert-thinking profile for Developmental Psychologist (longitudinal cohorts / age- normed psychometrics / ToM & EF paradigms / looking-time methods / IRB assent (45 CFR 46 subpart D)): Reasons from developmental trajectories, measurement invariance, and familial-environmental context through age-normed instruments (Bayley, WPPSI/WISC, CBCL, MacArthur-Bates CDI), false-belief and violation-of-expectation paradigms, and lme4/lavaan growth models while treating verbal-demand confounding of theo...

generate, refine, validate, and render diagrams from natural language, notes, code snippets, schemas, tables, or existing diagram source. use for flowcharts, swimlanes, sequence diagrams, state diagrams, er diagrams, class diagrams, architecture/c4-style diagrams, dependency graphs, gantt charts, mind maps, user journeys, sankey-style flows, org charts, network graphs, and other visual models. supports mermaid by default, graphviz dot for complex graph layout, plantuml for uml-heavy engineeri...

Run DiffDock molecular docking via NVIDIA NIM to predict small-molecule binding poses against protein targets. Use for DiffDock, molecular docking, ligand docking, blind docking, SMILES or SDF ligands, ranked poses, confidence scores, hosted NVIDIA API, or local Docker deployment.

DiffDock and DiffDock-L molecular docking. Use for protein-small-molecule pose prediction from PDB or sequence plus SMILES/SDF/MOL2, batch docking, virtual screening, and pose-confidence interpretation. Not for binding affinity prediction.

Bulk transcriptomics differential expression with count-aware modeling, design validation, contrast handling, thresholded exports, and publication-ready DE figures.

Expert-thinking profile for Differential Geometer (theoretical / geometric analysis / gauge & index theory): Reasons from connections, curvature, and holonomy; fixes Lee vs Besse/MTW Riemann signs; uses SageManifolds/xAct/Cadabra, Chern–Weil and Atiyah–Singer index theory, and model-space checks (S^n, flat tori) while treating chart artifacts, torsion misuse, and CAS convention drift as first-class failure modes.

Use for authorized digital forensics including memory dumps, disk timelines, PCAP investigation, artifact triage, and IR evidence preservation.

Expert-thinking profile for Digital Pathology Scientist (clinical / research): Reasons from whole-slide pixels, pathologist-ground-truth label levels, and stain/scanner batch effects through QuPath, CLAM/TIAToolbox MIL, Macenko/Vahadane normalization, and MI-CLAIM/TRIPOD+AI standards while treating patch-level leakage, scanner-ID shortcuts, attention-on-necrosis artifacts, and...

Expert-thinking profile for Distributed Systems Researcher (protocol R&D / consensus & replication / consistency semantics / chaos & formal verification (TLA+, Jepsen)): Reasons from failure models, consistency contracts, and tail-latency-and-recovery performance through TLA+ model checking, Jepsen and Porcupine linearizability checking, and YCSB/DeathStarBench benchmarking with iptables and kill -9 fault injection, while treating unbounded leases and split-brain, clock skew under...

DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline development and execution.

You are an advanced Docker containerization expert with comprehensive, practical knowledge of container optimization, security hardening, multi-stage builds, orchestration patterns, and production deployment strategies based on current industry best practices.

Containerizing and shipping applications with Docker — writing efficient Dockerfiles (multi-stage builds, layer caching, small/secure images), docker compose for multi-service local stacks, and the core build/run/debug commands. Use when creating a Dockerfile, debugging image builds, slimming images, or composing services (app + db + cache). For Claude Code dev sandboxes use devcontainer-setup; for serverless GPU runs use modal.

Creates task-oriented technical documentation with progressive disclosure. Use when writing READMEs, API docs, architecture docs, or markdown documentation. Also use this skill at the END of any completed reverse engineering, penetration testing, CTF, or security analysis task to generate a formal report in the user's project directory. Trigger keywords: 写报告, 写文档, 出报告, writeup, 技术文档, report, documentation.

Document Quality Check skill for Datasite deal rooms. Use this skill whenever a deal team wants to audit document quality before going live to buyers. Triggers include: "check document quality", "flag bad documents", "find password protected files", "check for blank documents", "PII check", "redaction review", "find corrupted files", "document audit", "quality check the data room", "are there any blank or broken files", "check for unredacted personal data", or any request to verify that docum...

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

Project-wide code coverage and CRAP (Change Risk Anti-Patterns) score analysis for .NET projects. Calculates CRAP scores per method and surfaces risk hotspots — complex code with low coverage that is dangerous to modify. Use to diagnose why coverage is stuck or plateaued, identify what methods block improvement, or get project-wide coverage analysis with risk ranking. USE FOR: coverage stuck, coverage plateau, can't increase coverage, what's blocking coverage, coverage gap, CRAP scores, risk ...

.NET / C# 二进制逆向。当目标是 .NET assembly（PE 头含 CLR、.exe/.dll 托管程序）、C# 编译产物（含 NativeAOT）、红队 Sharp* 工具（Rubeus / SharpHound / SharpHound 等）、.NET 混淆程序（ConfuserEx / SmartAssembly / Babel / Eazfuscator）、.NET loader / info-stealer / 套壳 malware 时使用。优先用 dnSpyEx + de4dot，需要 AI 直接操作时联动 dnSpy MCP。不用于纯 native 二进制（走 reverse-engineering / ida-reverse）。

Find the Prometheus metrics that drive your Grafana Cloud bill. `dpm-finder` is a Grafana Professional Services CLI that ranks metrics by Data Points per Minute (DPM) with per-label-set breakdown, optional `--cost-per-1000-series` pricing, and a Prometheus-exporter mode. Use when investigating high Grafana Cloud spend, hunting noisy / high-cardinality metrics, comparing pre/post recording-rule cardinality, or feeding cost data into dashboards — even when the user says "why is my Mimir bill so...

Drafts court filings — motions, memoranda of law, appellate briefs — as court-ready .docx, with Midpage research behind every citation. Use to \"draft a motion to dismiss,\" \"write the brief.\"

Writes a formal objective legal research memo (Questions Presented, Brief Answers, Facts, IRAC Discussion, Conclusion) as a .docx. Use to \"draft a research memo on whether…\" Predicts, never advocates.

NOTE: molecule and target inputs and your NGC_API_KEY are transmitted to external NVIDIA-hosted API endpoints on every call. Use local NIM containers for confidential or proprietary data. Run a complete computational drug discovery pipeline using NVIDIA BioNeMo NIMs: generate drug-like molecules with GenMol, dock them to a protein target with DiffDock, then predict binding affinity with Boltz2. Use this skill whenever the user wants to generate and screen small molecule drug candidates, perfo...

Medication photo to personalised PGx dosage card via Claude vision — snap a pill, get genotype-informed guidance

DSPy declarative framework for automatic prompt optimization treating prompts as code with systematic evaluation and compilers

Search DuckDB and DuckLake documentation and blog posts. Returns relevant doc chunks for a question or keyword using full-text search against a locally cached index.

Data Version Control (DVC) for tracking large datasets/models with Git-like semantics, defining reproducible data/ML pipelines (dvc.yaml stages that only re-run when their inputs change), and lightweight experiment tracking without a server. Use when large files (VCF/BAM/FASTQ, reference genomes, model weights) can't go in Git, when you need Make/Snakemake-style selective re-execution driven by data, or when comparing many training runs locally before promoting one. Pairs with Git (code), clo...

Expert-thinking profile for Dynamical Systems Theorist (analysis + numerics / bifurcation theory / normal forms / continuation (AUTO, MatCont) / chaos diagnostics): Reasons from state spaces, invariant sets, bifurcations, and multiple time scales through normal-form classification, center-manifold reduction, Floquet/Poincaré maps, and continuation tools like AUTO, MatCont, and DynamicalSystems.jl while treating spurious chaos from finite-time Lyapunov bias, false limit cycles...

Guide for creating and managing E2B sandboxes using ComputeSDK. Use when building applications that need E2B provider for ComputeSDK - cloud sandboxes with full Linux environments, filesystem access, and microVM isolation.