Claude Skills by stanfish06

Trace bugs and manual fixes back to kits and prompts; fix at the source so the iteration loop can reproduce the fix autonomously. Six-step revision process plus the single-failure backpropagation protocol. Use when a manual hot-fix has been applied, when convergence stalls, or when the same class of bug keeps reappearing.

Validation-first design for Cavekit — every kit requirement must be automatically verifiable. Six-gate validation pipeline, phase gates, merge protocol, completion signals, acceptance criteria patterns. Use when designing acceptance criteria, wiring CI gates, or debugging why an agent is producing output that nobody can verify.

Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.

Quick-reference card for caveman modes, skills and commands. Trigger: /caveman-help or "caveman help".

Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".

Show real token usage and estimated savings for the current session, read from the session log. Trigger: /caveman-stats.

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

Expert-thinking profile for Cell Biologist (wet-lab / mammalian cell culture / fluorescence microscopy / genetic perturbation / rigor (STR, MIQE, REMBI)): Reasons from compartment thermodynamics, membrane electrophysics, and necessity-plus- sufficiency logic through STR authentication, confocal/TIRF imaging, CRISPR and siRNA perturbation with rescue, and Western blot, treating mycoplasma, passage and serum-lot drift, edge effects, antibody cross-reactivity, siRNA seed...

Cell-cell / ligand-receptor communication analysis for single-cell data using LIANA+ (recommended consensus default), CellPhoneDB, CellChat (R), and squidpy's ligrec. Use for inferring cell-cell communication, ligand-receptor pairs, source->target signaling from an annotated .h5ad. Trigger terms - "cell-cell communication", "ligand-receptor", "CellPhoneDB", "CellChat", "LIANA", "cell interaction", "ligrec".

Cell segmentation in fluorescence microscopy images. Supports Cellpose/cpsam (Cellpose 4.0) with additional backends

Expert-thinking profile for Cell Signaling Biologist (wet-lab / phospho-signaling / pathway biology): Reasons from RTK–RAS–MAPK and PI3K–Akt–mTOR phosphorylation networks, pathway crosstalk and feedback; validates with phospho-Western, phospho- flow, and PhosphoSitePlus while treating serum-starvation artifacts, inhibitor off- targets, and RNA footprint vs PTM mismatch as first-class failure modes.

DL cell/nucleus segmentation for fluorescence and brightfield microscopy with Cellpose 4's Cellpose-SAM and CellposeDINO models. Handles grayscale, multichannel, 2D, and 3D images and outputs label masks for morphology and tracking. Use scikit-image watershed for rule-based segmentation; use Cellpose when learned generalization is needed.

Bioimage cell and nucleus segmentation routing with cellpose-cell-segmentation, Cellpose, StarDist, napari-viz, and monai-medical-imaging-ai. Use when choosing or comparing segmentation models for microscopy, nuclei, cells, 2D/3D images, masks, overlays, fine-tuning, and segmentation quality control.

Expert-thinking profile for Cellular Neuroscientist (wet-lab / patch-clamp electrophysiology / live-cell imaging / culture-slice-iPSC preparations / synaptic physiology): Treat the neuron as a cable with active channels, not a point integrator unless you have shown it is one for your question. Separate voltage, calcium, and fluorescence observables. GCaMP reports Ca²⁺-driven fluorescence with indicator kinetics; it is not membrane potential. FRET sensors (ArcLight, ASAP) trade speed...

Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs/downloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.

Expert-thinking profile for Ceramics Engineer (processing / sintering / microstructure / electroceramics / mechanical reliability (Weibull, ASTM C-series)): Reasons from crystal chemistry, defect equilibria, sintering densification, and flaw statistics through XRD/Rietveld, dilatometry, SEM fractography, impedance spectroscopy, and Weibull analysis per ASTM C1161/C1239/C1421 while treating surface grinding flaws, Pb/alkali volatilization, closed-pore traps, and...

Design and run bounded chaos engineering experiments that test whether a system preserves measurable steady-state behavior during realistic faults. Use for resilience hypotheses, game days, fault injection, failover and recovery validation, or LitmusChaos and Chaos Mesh experiments involving pod, node, network, latency, resource, storage, DNS, time, or cloud failures. Require explicit authorization before mutating an environment, especially production; do not use as a substitute for load test...

Inspect a ChatGPT Apps MCP server codebase and generate chatgpt-app-submission.json with app info suggestions, tool hint justifications, test cases, and negative test cases, then report review-check findings and outputSchema warnings for submission review.

Submit compact ChEBI 2.0 API requests for chemical search, compound lookup, ontology traversal, and structure metadata. Use when a user wants concise ChEBI summaries

Detects MSBuild projects with conflicting OutputPath or IntermediateOutputPath. USE FOR: builds failing with 'Cannot create a file when that file already exists', 'The process cannot access the file because it is being used by another process', intermittent build failures that succeed on retry, or missing/overwritten outputs in multi-project or multi-targeting builds where bin/obj (or project.assets.json) collide. Common causes: shared OutputPath, missing AppendTargetFrameworkToOutputPath, ex...

Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions. Waits for pending checks to complete, categorizes issues as actionable or informational, and optionally fixes and resolves them. Use when the user wants to check a PR/MR/CL, address review feedback, or prepare a change for submission.

Expert-thinking profile for Chemical Biologist (wet-lab / chemoproteomics / probe discovery & target validation): Reasons from chemical genetics, ABPP/TPP/CETSA chemoproteomics, and SGC/Portal probe criteria; deconvolves phenotypic hits with PAINS/aggregator triage, inactive analogs, and genetic epistasis while treating colloidal aggregation, probe promiscuity, and degrader DC50/Dmax tag artifacts as first-class failure modes.

Expert-thinking profile for Chemical Engineer (process design / unit operations / separations & reaction engineering / HAZOP safety (API 520, IEC 61511) / Aspen flowsheeting): Reasons from closing mass, energy, and momentum balances and competing equilibrium/kinetics/transport regimes through Aspen Plus/HYSYS flowsheeting, McCabe- Thiele and Damkohler-based sizing, pinch analysis, and HAZOP/LOPA with API 520/521 relief, while treating azeotrope-pinched columns, reactor runaway, recycle...

Expert-thinking profile for Chemical Oceanographer (seawater carbonate chemistry / nutrient & trace-metal biogeochemistry / isotope tracers / shipboard & autonomous sampling...): Reasons from seawater thermodynamics, carbonate-system coupling (DIC, TA, pH, pCO2), redox hierarchies, and tracer conservation on density surfaces through CO2SYS/seacarb with Dickson CRMs, Winkler oxygen, IRMS isotopes, GO-FLO clean trace- metal sampling, and GLODAP/SOCAT/GEOTRACES synthesis while treating organic...

Expert-thinking profile for Cheminformatician (computational / medicinal-chemistry informatics / (Q)SAR): Reasons from Standard InChI identity and RDKit sanitization through ChEMBL pChEMBL harmonization, Morgan/ECFP fingerprints, scaffold splits and applicability domains, while treating tautomer collapse, KNIME-vs-Python canonicalization drift, and random-split QSAR leakage as first-class failure modes.

Use when choosing architecture.

Expert-thinking profile for Chromatin Biologist (wet-lab / chromatin biochemistry / epigenomics): Reasons from nucleosome arrays, histone PTM crosstalk, remodelers, and 3D genome organization; validates ChIP/CUT&Tag/ATAC with spike-ins and IgG controls while separating composition from mechanism.

Expert-thinking profile for Chronobiologist (wet-lab / computational / human circadian physiology): Reasons from TTFL molecular clocks, SCN–peripheral coupling, and zeitgeber entrainment (PRC); analyzes actigraphy, DLMO, and PER2::LUC with ClockLab/LumiCycle, MetaCycle/eJTK/LimoRhyde, and CircaDB/CGDB/ChronobioticsDB while separating masking from endogenous τ under constant routine/FD.

Forecast private capital cashflows for existing portfolios using Chronograph MCP data and a Takahashi-Alexander style model. Use when Codex needs to analyze or forecast LP-level contributions, distributions, NAV, unfunded exposure, net cashflows, or Excel-style cashflow forecast outputs from existing Chronograph funds, commitments, groups, or portfolios.

Prepare an LP to meet with their fund manager (GP): review the fund's latest reporting, surface what changed since last period, and draft the questions worth raising. Use when someone is getting ready for a manager call, quarterly check-in, annual meeting, LPAC meeting, or a re-up decision — for example "I have my quarterly call with this manager next week, help me prep," "what changed in this fund this quarter," "what should I ask them about these marks," or "what are the red flags in this r...

GP platform one-pager and investor report generator for private equity portfolio companies. Use this skill whenever a user asks to generate a company tearsheet, one-pager, investor report, portfolio overview, or company deep-dive — especially when they name a company or ask to "build a report", "create a one-pager", or "show me a tearsheet". Also trigger when the user asks to include commentary, quarterly updates, investment narratives, or any Investment Overview in the report output. This sk...

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

Diagnose and fix failing CircleCI builds quickly and safely. Use when users ask to investigate failed CircleCI jobs, triage flaky pipelines, identify root causes from logs, and implement minimal fixes in configuration, test setup, or build-related code paths.

Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. Use when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

Canonical rules and HTML/CSS contract for inline `[n]` citation references, end-of-document Citations blocks, and optional per-section citation recaps used across Moody's Agentic Solutions HTML report skills (earnings-brief, peer-analysis, issuer-brief, sector-brief, etc.). Parent skills must read BOTH this `SKILL.md` (rules, numbering, hyperlink behavior, source data shape) AND `assets/template.html` (canonical CSS block + literal HTML markup snippets) before emitting citations. The asset fi...

Cite-checks a brief, motion, or memo (PDF/Word): verifies each cited case is real, supports the proposition, is good law, and quoted accurately. Returns one marked-up .docx with comments and redlines.

Expert-thinking profile for Civil Engineer (structural / geotechnical / water resources / LRFD design-review / codes (ASCE 7, ACI 318, AASHTO LRFD)): Reasons from load paths, factored load combinations, soil-structure interaction, and governing limit states through ASCE 7, ACI 318, AISC 360, and tools like SAP2000/ETABS, PLAXIS, and HEC-RAS while treating missing load paths, connection and foundation failures, differential settlement, and unvalidated FEA as...

Hand the current conversation off to a fresh background agent that picks up the work immediately.

Ancestry decomposition PCA against the Simons Genome Diversity Project

Shotgun metagenomics profiling — taxonomy, resistome, and functional pathways

Eval-driven skill tuning. Given a task and an LLM-judge rubric, iteratively rewrites a SKILL.md until a downstream executor agent performs well against the judge. Low-code: all evaluation is LLM-as-judge, not deterministic Python.

Expert-thinking profile for Climate Risk Analyst (financial / insurance / disclosure & portfolio climate risk): Reasons from TCFD/IFRS S2 four-pillar disclosure, NGFS Phase V orderly/disorderly/hot-house scenarios, hazard–exposure–vulnerability and RMS/AIR/CLIMADA cat economics, transition carbon-price and stranded-asset pathways, and PCAF financed emissions while treating exposure geocoding quality, Kotz damage- function...

Expert-thinking profile for Climate Scientist (computational / observational / paleoclimate physical climate science): Reasons from ERF/EEI energy-budget closure, AR6 forcing (WMGHG vs ERFaci), optimal fingerprinting and FAR event attribution, CMIP6/ScenarioMIP SSP workflows (ESGF, ESMValTool), and paleo proxy physics (PAGES2k, ice-core δD/CO₂, foraminifera Mg/Ca, coral Sr/Ca) while treating aerosol uncertainty, tree-ring divergence...

Expert-thinking profile for Climatologist (computational / observational climatology & paleoclimate reconstruction): Characterizes climate via WMO CLINO baselines (1991–2020 vs 1961–1990), ETCCDI indices, and teleconnection modes; bridges ERA5 climatology to CMIP6/ScenarioMIP SSP deltas (xsdba/QDM), optimal-fingerprint attribution, AR6 ERF/ECS/TCR, and proxy reconstructions (CPS/EIV, PAGES2k, MXD divergence)—distinct from weather...

Expert-thinking profile for Clinical Data Manager (clinical / research): Reasons from ALCOA+ data integrity, traceability, and analysis-ready datasets through CDASH/SDTM/ADaM pipelines, edit-check specs, Pinnacle 21 validation, MedDRA/WHO Drug coding, and define.xml under 21 CFR Part 11, treating blinding breaches, SAE-safety reconciliation gaps, mid-study IG/dictionary version drift, and...

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug dev...

Expert-thinking profile for Clinical Embryologist (clinical / research): Reasons from gamete and embryo biology, manufacturing-quality lab control, and prespecified cycle/oocyte/embryo denominators through Vienna consensus KPIs, Gardner/ASEBIR grading, time-lapse morphokinetics, WHO 6th-edition andrology, and vitrification SOPs while treating media-lot and incubator-gas drift, witness...

Expert-thinking profile for Clinical Epidemiologist (clinical / dry-computational (observational & evidence synthesis)): Clinical epidemiology expert for causal study design, observational bias control, GRADE/EBM synthesis, and principled reporting (CONSORT/STROBE/PRISMA).

Expert-thinking profile for Clinical Laboratory Scientist (clinical / core laboratory (chemistry, hematology, microbiology, blood bank, molecular)): Reasons from pre- analytical–analytical–post-analytical total testing process; EP15/EP09/EP28 validation, Westgard/Sigma IQC, HIL indices (C56), EP23/IQCP, critical-value read- back, type-and-screen/crossmatch, CLSI M100 direct AST, LC-MS/MS C62, and AUTO10 autoverification.