#SkillRepo stars
- 865Bio Methylation Methylkithackernoon/cuttlefish-agent-skillsImports Bismark coverage or cytosine-report files into the methylKit object model, then runs the import-to-results spine - filterByCoverage, normalizeCoverage, unite/destrand, calculateDiffMeth, getMethylDiff - for both per-CpG (DMC) and fixed-tile (DMR) differential methylation, plus tileMethylCounts, PCA/correlation/clustering QC, and assocComp/removeComp batch handling. Covers the silent default traps that shape the false-positive rate: overdispersion='none' does no correction while 'MN' forces the F-test (ignoring test='Chisq'), adjust defaults to SLIM not BH, getMethylDiff defaults differ9
- 866Bio Microbiome Differential Abundancehackernoon/cuttlefish-agent-skillsTests which individual taxa differ between groups on an amplicon ASV/feature table (phyloseq) using compositionally-aware methods - ALDEx2 (Dirichlet-MC CLR, conservative), ANCOM-BC2/ANCOMBC (sampling-fraction bias correction, structural zeros, passed_ss, default p_adj_method=holm), MaAsLin2/MaAsLin3 (multivariable GLM, random effects, prevalence/abundance split), LinDA (CLR mixed-model regression), ZicoSeq (permutation FDR), LEfSe, and q2-composition ancombc. Covers why the hit list depends more on the DA tool than the biology (Nearing benchmark) so the deliverable is a CONSENSUS of >=2 tools9
- 867Bio Pathway Gseahackernoon/cuttlefish-agent-skillsTests a ranked gene vector for coordinated expression shifts in GO, KEGG, Reactome, or MSigDB gene sets with clusterProfiler's gseGO, gseKEGG, gsePathway, and GSEA (fgseaMultilevel engine), and scores per-sample pathway activity with ssGSEA and GSVA. Covers why a GSEA result is a deterministic function of three implicit choices (the ranking STATISTIC, the weight exponent p, and which LABELS are permuted), why the input must be a NAMED vector sorted DECREASING by a signed variance-calibrated metric (DESeq2 stat, limma t) not a raw p-value that erases direction, why preranked gene-permutation is9
- 868Bio Pathway Wikipathwayshackernoon/cuttlefish-agent-skillsTests a gene list (ORA, enrichWP) or a ranked gene vector (GSEA, gseWP) against the WikiPathways community-curated pathway collection with clusterProfiler and rWikiPathways. Covers why a WikiPathways result is a snapshot of a live, monthly-updated database (enrichWP/gseWP/gson_WP silently pull data.wikipathways.org/current/), why reproducibility requires pinning a dated GMT via downloadPathwayArchive(date=, format='gmt'), why the WP GMT is Entrez-keyed so symbols and Ensembl silently overlap nothing, why universe=NULL gives a biased all-WP-genes background, how to split the name%version%wpid%o9
- 869Bio Population Genetics Association Testinghackernoon/cuttlefish-agent-skillsSingle-variant common-variant GWAS with plink2 --glm (linear/logistic, Firth) and the linear mixed models GEMMA, BOLT-LMM, SAIGE, regenie (SPA). A GWAS statistic is valid only when genotype is independent of unmodeled phenotype drivers after the chosen covariates and random effects, so the engine follows sample structure and case:control imbalance, not taste: PC covariates absorb continuous ancestry but cannot remove relatedness (a covariance structure needing an LMM), genomic inflation above 1 is mostly true polygenic signal not confounding (the LDSC intercept is the diagnostic), LOCO prevent9
- 870Bio Population Genetics Rare Variant Associationhackernoon/cuttlefish-agent-skillsGene and region-based rare-variant aggregation - burden/collapsing, SKAT, SKAT-O, ACAT-V/ACAT-O, annotation-weighted STAAR - with regenie (--vc-tests), SAIGE-GENE+, and the SKAT R package. Single-variant tests are powerless at low minor allele count, so rare variants are aggregated across a gene or region under an explicit mask (functional class plus a MAF cutoff). A burden test collapses variants into one score assuming a single effect direction (powerful when true, near-zero power when risk and protective variants cancel); SKAT is a variance-component test robust to mixed directions; SKAT-O 9
- 871Bio Pose Validationhackernoon/cuttlefish-agent-skillsValidates docked / generated protein-ligand poses using PoseBusters physical-validity tests, strain energy quantification, geometric checks (planarity, vdW overlap, bond/angle distortion), and pose-energy reasonableness. Use when QC-ing docking results, comparing classical vs ML docking outputs, or filtering pose lists before SAR analysis.9
- 872Bio Proteomics Differential Abundancehackernoon/cuttlefish-agent-skillsTests for differentially abundant proteins between conditions with limma/DEqMS empirical-Bayes moderation, proDA/msqrob2/MSstats missingness modeling, and Python Welch+BH alternatives. Frames missing values as left-censored MNAR (model, do not impute), makes variance moderation the load-bearing step at n=3-5, and prefers feature/peptide-level testing. Use when identifying proteins with significant abundance changes between experimental groups. Summarization and normalization mechanics are proteomics/quantification; volcano and MA plots are data-visualization/volcano-and-ma-plots; pathway enric9
- 873Bio Proteomics Quantificationhackernoon/cuttlefish-agent-skillsQuantifies protein abundance from mass spectrometry using label-free (LFQ/MaxLFQ, DIA fragment-level), isobaric (TMT/iTRAQ reporter ions, MS2 vs SPS-MS3), and metabolic (SILAC) approaches, including peptide-to-protein summarization (Tukey median polish, MaxLFQ, msqrob), sample-loading and IRS cross-plex normalization, and isotopic impurity correction. Use when turning peptide/PSM/reporter signal into a protein-by-sample abundance matrix for downstream analysis. Statistical testing of that matrix is differential-abundance; DIA quant mechanics and DIA-NN runs are dia-analysis; reading search-eng9
- 874Bio Read Alignment Bowtie2 Alignmenthackernoon/cuttlefish-agent-skillsAligns DNA short reads to a reference with Bowtie2, choosing end-to-end (whole read must align) vs local (soft-clip read ends) mode and a sensitivity preset; the de-facto aligner for ChIP-seq, ATAC-seq, and CUT&RUN, where fragment-geometry flags (--no-mixed, --no-discordant, --dovetail, -X) and a tool-appropriate MAPQ filter feed the peak caller. Use when aligning ChIP/ATAC/CUT&RUN reads, when read ends are adapter-contaminated and need soft-clipping, or when a tunable sensitivity/speed preset is wanted. DNA variant calling prefers bwa-alignment; RNA spliced alignment is star-alignment/hisat2-9
- 875Auditing Repositoriestomada1114/tomada-claude-pluginsAudit the repository you are in, often a template or an app cut from one, for technical debt and room to improve in four areas: architecture and design patterns; tests; file structure and code quality; and tooling, CI, dependencies and the agent harness. Design a safe, test-first fix for every evidenced finding, and file the findings as GitHub issues that follow the repository's own issue conventions (triaging-issues, issue forms, past issues). A finding inherited from the template is also filed in the template repository. Cheap read-only sub-agents collect the evidence and high-effort analyst5
- 876Bun Dates and Timesjarle/bun-skillsLearn how to manipulate time and dates in your Bun tests using setSystemTime and Jest compatibility functions9
- 877Bun DOM Testingjarle/bun-skillsLearn how to test DOM elements and components using Bun with happy-dom and React Testing Library9
- 878Bun Finding Testsjarle/bun-skillsLearn how Bun's test runner discovers and filters test files in your project9
- 879Bun Generate Code Coverage Reports with the Bun Test Runnerjarle/bun-skillsGenerate code coverage reports with the Bun test runner9
- 880Bun Import, Require, and Test Svelte Components with Bun Testjarle/bun-skillsimport, require, and test Svelte components with bun test9
- 881Bun Lifecycle Hooksjarle/bun-skillsLearn how to use beforeAll, beforeEach, afterEach, and afterAll lifecycle hooks in Bun tests9
- 882Bun Mocksjarle/bun-skillsLearn how to create and use mock functions, spies, and module mocks in Bun tests9
- 883Bun Re Run Tests Multiple Times with the Bun Test Runnerjarle/bun-skillsRe-run tests multiple times with the Bun test runner9
- 884Bun Runtime Behaviorjarle/bun-skillsLearn about Bun test's runtime integration, environment variables, timeouts, and error handling9
- 885Bun Selectively Run Tests Concurrently with Glob Patternsjarle/bun-skillsSet a glob pattern to decide which tests from which files run in parallel9
- 886Bun Set a Code Coverage Threshold with the Bun Test Runnerjarle/bun-skillsSet a code coverage threshold with the Bun test runner9
- 887Bun Snapshotsjarle/bun-skillsLearn how to use snapshot testing in Bun to save and compare output between test runs9
- 888Bun Test Configurationjarle/bun-skillsLearn how to configure Bun test behavior using bunfig.toml and command-line options9
- 889Bun Test Runnerjarle/bun-skillsBun's fast, built-in, Jest-compatible test runner with TypeScript support, lifecycle hooks, mocking, and watch mode9
- 890Bun Writing Testsjarle/bun-skillsLearn how to write tests using Bun's Jest-compatible API with support for async tests, timeouts, and various test modifiers9
- 891DebateMagnus-Gille/claude-skillsRun an adversarial debate with a cross-model reviewer (Codex or Antigravity/agy) to stress-test a draft, plan, research claim, or design decision. Use this whenever you need structured critique before finalizing decisions.5
- 892User Test MemoryMagnus-Gille/claude-skillsSpawn independent AI agents across one or more ecosystems (Claude, Codex, Antigravity) to user-test the Munin memory system. Each explores with minimal pre-knowledge and returns structured feedback on what works, what's broken, and what's missing.5
- 893DogfoodLord1Egypt/RA-SkillsExploratory QA of web apps: find bugs, evidence, reports.9
- 894Replay DemoLord1Egypt/RA-SkillsSynthetic localhost skill for testing Browserbase session replay playback.9
- 895Art of Unit Testingvnovakovits/claude-skillsApply Roy Osherove's "The Art of Unit Testing" (Manning — 2nd ed. 2013 in C#/.NET, 3rd ed. 2024 in JavaScript) — the practitioner's guide to writing trustworthy, maintainable, readable unit tests. Centers on Osherove's broad unit-of-work definition (entry point → observable exit point), his three-part test-naming convention (UnitOfWork_StateUnderTest_ExpectedBehavior), the stub-vs-mock distinction by whether you assert against the double, the one-mock-per-test rule, designing for testability via seams (dependency injection, Extract-and-Override), and getting legacy code under test. Use when wr5
- 896Condition Based WaitingFreddy-CHEN-ux/00_claude_skillsUse when tests fail intermittently. Replace arbitrary timeouts with condition polling. Eliminates flaky tests caused by timing assumptions.8
- 897Gameplay BrowserFreddy-CHEN-ux/00_claude_skillsTest game via browser with Chrome DevTools. Navigate UI, play through game flow, observe behavior and report issues.8
- 898Grill Mebolasblack/claude-skillsStress-test a plan, design, decision, or idea through a focused interview. Use when the user asks to be grilled, challenge their thinking, or resolve design choices before proceeding.5
- 899Peer Reviewvnovakovits/claude-skillsReview a change the way a respected colleague would — design and craft lenses applied to the diff, every finding verified in the code, and the result written as kind, specific comments anchored to lines. Loads clean-code, fractal-architecture, responsibility-driven-design and domain-driven-design for the production code; unit-testing-principles (Khorikov's four pillars, managed vs unmanaged dependencies), art-of-unit-testing, xunit-test-patterns and test-data-patterns for the tests, including a map of every promised scenario to the test that pins it and a check that no guard can be removed wit5
- 900Playwrightbolasblack/claude-skillsComplete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.5
- 901Playwright Frontend TestingFreddy-CHEN-ux/00_claude_skillsUse when testing frontend applications. AI-assisted browser testing with Playwright MCP. Fast, deterministic, no vision models needed.8
- 902Playwright TesterFreddy-CHEN-ux/00_claude_skillsCapture screenshots and run E2E tests with Playwright. Use for frontend debugging, visual inspection, or user flow validation. (project)8
- 903Pm AnalystFreddy-CHEN-ux/00_claude_skillsEnd-to-end PM workflow - from data analysis to pragmatic Linear tickets. Analyzes user behavior, identifies opportunities, creates specs, and audits for simplicity.8
- 904QA Agent TestingFreddy-CHEN-ux/00_claude_skillsQA harness for agentic systems: scenario suites, determinism controls, tool sandboxing, scoring rubrics, and regression protocols covering success, safety, latency, and cost.8
- 905QA API Testing ContractsFreddy-CHEN-ux/00_claude_skillsAPI testing and contract validation. Design and execute schema validation, contract tests, negative testing, and change safety for REST, GraphQL, and gRPC APIs. Use when you need API test plans, contract testing, or CI quality gates.8
- 906QA Handoffvnovakovits/claude-skillsUpdate a ticket with what shipped and tell QA what to test, in lean, empathetic, user-journey language. Verifies what is actually merged, released and deployed, maps each change to the ticket it fixes, writes a short status (in production / open / left, by owner) and a numbered list of user journeys to test with expected outcomes and what to report. Use when a change is merged or deployed and someone asks "what should QA test", "update the ticket", "post what we merged", "is this live", or wants a tester note, release note or status comment for any tracker (Linear, Jira, GitHub Issues).5
- 907QA ObservabilityFreddy-CHEN-ux/00_claude_skillsObservability for quality engineering: using logs, metrics, and traces as test signals; SLI/SLO quality gates; trace-based debugging of failures; and cost-aware instrumentation with OpenTelemetry.8
- 908QA RefactoringFreddy-CHEN-ux/00_claude_skillsSafe refactoring for quality engineering: characterization tests, seam creation, incremental steps, contracts, and CI quality gates to preserve behavior while changing structure.8
- 909QA ResilienceFreddy-CHEN-ux/00_claude_skillsResilience engineering for QA: failure mode testing (timeouts/retries/dependency failures), chaos experiments with blast-radius controls, degraded-mode UX expectations, and reliability gates.8
- 910QA Testing IOSFreddy-CHEN-ux/00_claude_skillsiOS testing with XCTest/XCUITest on simulators and devices: layered strategy, determinism/flake control, device matrix selection, CI ergonomics, and repeatable simulator automation.8
- 911QA Testing MobileFreddy-CHEN-ux/00_claude_skillsMobile app testing strategy and execution for iOS and Android. Cover device matrix, automation frameworks, performance, reliability, and release gates. Use when you need cross platform mobile QA plans or mobile testing automation guidance.8
- 912QA Testing PlaywrightFreddy-CHEN-ux/00_claude_skillsEnd-to-end web application testing with Playwright: scope control, stable selectors, parallelization/sharding, flake control, network mocking vs real services, visual testing tradeoffs, and CI/CD integration.8