2,377 件 ・ 関連度順
概要と使いどころ
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks
日本語の概要は準備中です。原文の説明を表示しています。
Assess release readiness from applicable criteria, all current defects, risks, limitations, and recorded human decisions without approving release.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a user asks for QA planning, execution, review, release assessment, reporting, status, or test-tool recommendations and the correct PWDEV QA workflow must be selected safely.
日本語の概要は準備中です。原文の説明を表示しています。
Assess requirement clarity, testability, completeness, consistency, and traceability without inventing missing acceptance criteria.
日本語の概要は準備中です。原文の説明を表示しています。
Review a code diff or explicit file set through independent correctness and QA lenses. Use when the user asks for a code review, test-coverage assessment, pre-merge audit, or review gate in a PWDEV Flow workflow.
日本語の概要は準備中です。原文の説明を表示しています。
Diagnose repository and PWDEV Flow health without changing the project. Use when the user asks for a health check, workspace consistency check, dependency assessment, readiness report, or evidence-based scorecard.
日本語の概要は準備中です。原文の説明を表示しています。
Systematically review pull requests, feature implementations, and code changes to ensure quality, maintainability, security, and adherence to best practices. Use when reviewing code before merging, conducting peer reviews, performing self-reviews, auditing code quality, checking for security vulnerabilities, ensuring consistent coding standards, verifying test coverage, assessing performance implications, evaluating architectural decisions, or providing constructive feedback to improve team code quality.
日本語の概要は準備中です。原文の説明を表示しています。
Extract actionable patterns, architecture decisions, code conventions, and skill-relevant insights from GitHub/GitLab repositories. Assess repo credibility, run the full security scan pipeline, and apply findings to existing skills, new skills, or the current project. Load when the user asks to learn from a repo, extract patterns from a codebase, study a repository, or analyze a repo for reusable techniques. Also triggers on "learn from this repo", "learn from this repository", "what can we learn from this codebase", "extract patterns from this repo", "study this repo".
日本語の概要は準備中です。原文の説明を表示しています。
Extract actionable skill knowledge from academic papers and research articles, assess credibility, run security checks, and either improve existing skills or create new ones. Load when the user asks to learn from a paper, extract insights from a research paper, turn a paper into a skill, apply paper findings to skills, read this paper and improve my skills, or process a research article. Also triggers on "skill from paper", "learn from this paper", "paper to skill", "extract from this research", "apply this paper", or when the user uploads or links to an academic PDF or paper URL.
日本語の概要は準備中です。原文の説明を表示しています。
Extract actionable insights from blog posts, web articles, and practitioner content - assess credibility, run security checks, and either improve existing skills or apply to the current project. Load when the user asks to learn from an article, extract insights from a blog post, apply a practitioner's findings, or process engineering blog content. Also triggers on "learn from this article", "learn from this blog post", "extract insights from this post", "what can we learn from this article", "apply this article", or when the user links to a blog, Medium, Substack, dev.to, or engineering blog post.
日本語の概要は準備中です。原文の説明を表示しています。
Surface every assumption embedded in a plan, strategy, or document, assess how critical and how validated each one is, and identify which ones to test first. Load when the user asks to map assumptions, surface hidden beliefs, find what must be true for this to work, run an assumption audit, or when deep-thinking diagnoses an assumption frame. Also triggers on "what are we assuming", "what must be true for this to work", or "find the untested beliefs". Based on David Bland and Alex Osterwalder's assumption mapping method from Testing Business Ideas.
日本語の概要は準備中です。原文の説明を表示しています。
Orchestrator for the eval-output skill suite — evaluate LLM and agent outputs for quality, accuracy, helpfulness, and safety using structured rubrics and LLM-as-judge techniques. Load when the user says "evaluate this output", "score this response", "run an eval", "LLM as judge", "evaluate agent output", "how good is this response", "rate this answer", "eval this", or provides an LLM output that should be assessed for quality. Single entry point for all output evaluation workflows.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation. Trigger on queries involving paper URLs, uploaded PDFs, arXiv links, or requests like "review this paper", "analyze this research", "summarize this study", or "write a peer review".
日本語の概要は準備中です。原文の説明を表示しています。
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
日本語の概要は準備中です。原文の説明を表示しています。
Computes and interprets sequencing read depth and coverage over a genome, windows, or target regions with mosdepth (windowed depth, cumulative distribution, --quantize callable BEDs), bedtools genomecov/coverage (bedGraph tracks, per-target stats), samtools depth/coverage (per-base depth, per-contig depth+breadth). Covers the breadth-vs-mean distinction, the cumulative-coverage curve, evenness (CV/Fano/fold-80/Gini), what each tool silently counts (duplicates, secondary/supplementary, MAPQ, read span vs fragment, mate-overlap), the samtools-depth 8000-cap version trap, and the bedtools coverage -a/-b orientation flip. Use when assessing sequencing adequacy, building coverage tracks, computing breadth at a depth threshold, defining callable regions, or QCing target-capture uniformity.
日本語の概要は準備中です。原文の説明を表示しています。
Evaluates genome assembly quality across the three orthogonal axes - contiguity (QUAST auN/NG50/NGx, not bare N50), completeness (BUSCO/compleasm gene-space plus Merqury k-mer completeness), and correctness (reference-free Merqury QV, Inspector/CRAQ structural errors, asmgene false-duplication/collapse). Covers why N50 is the most-gamed metric, why QV measured on the polishing reads is circular, distinguishing uncollapsed haplotigs from real WGD, and the EBP/VGP 6.C.Q40 standard. Use when judging whether an assembly is good enough to annotate or publish, comparing assemblers, diagnosing a fragmented or duplicated assembly, or assessing a phased diploid assembly.
日本語の概要は準備中です。原文の説明を表示しています。
Quality control for flow, spectral, and mass cytometry - time-based anomaly cleaning (flowAI, flowCut, PeacoQC, flowClean), margin/boundary event removal, signal-drift detection, dead-cell exclusion, CyTOF Gaussian/DNA/event-length checks, instrument calibration/standardization (MESF, CS&T, peak-2), and batch-level outlier flagging. Use when assessing acquisition quality, choosing a cleaning tool, ordering QC relative to compensation, deciding margin removal before density-based steps, or flagging problematic samples before clustering or differential analysis.
日本語の概要は準備中です。原文の説明を表示しています。
Assesses the quality and completeness of a genome annotation with BUSCO (conserved single-copy ortholog recovery), OMArk (proteome completeness, consistency, and contamination), CheckM2 (prokaryotic completeness/contamination), and a gene-set sanity panel (gene count, mono-exonic fraction, protein-length distribution, mRNA:gene ratio, coding density). Covers the assembly-BUSCO-vs-proteome-BUSCO diagnostic, what BUSCO-Duplicated really means, why gene count is a vanity metric, and the QC of transferred annotations. Use when judging whether an annotation is good enough to publish or submit, diagnosing a suspect annotation, or comparing annotation completeness across pipelines.
日本語の概要は準備中です。原文の説明を表示しています。
Assesses genetic health of populations for conservation with Ne estimation across time horizons (LDNe NeEstimator V2 option-file API + SNeP physical-linkage correction; recent trajectory via GONE/GONE2; deep history via Stairway Plot 2 / dadi / fastsimcoal2 / PSMC), F-statistics, runs of homozygosity binned by length class to date inbreeding, genetic-load decomposition (Bertorelle 2022 realized vs masked), the modern 100/1000 Ne rule (Frankham 2014), Ne/Nc 2-6 orders of magnitude in marine fish (Hauser & Carvalho 2008), tree-sequence forward simulations (SLiM 4 + pyslim + tskit), and the Sukumaran-Knowles caveat against MSC methods for management-unit definition. Use when estimating Ne by time horizon, detecting inbreeding via F_ROH, decomposing genetic load, justifying conservation thresholds, distinguishing ESU/MU/DPS, configuring NeEstimator V2, or correcting LDNe physical linkage.
日本語の概要は準備中です。原文の説明を表示しています。
Quality control for pooled CRISPR screens covering library representation, Gini index, log-skew, replicate Pearson and Spearman concordance, essentialome precision-recall AUC against CEGv2 (Hart 2017), Cas9 cut-toxicity diagnostics, copy-number amplicon detection (Aguirre 2016 / Munoz 2016), bottleneck propagation through plasmid pool, infection, selection, and endpoint stages, MOI verification, and DepMap-style screen-quality scoring. Use when assessing screen quality before hit calling, deciding whether to repeat or rescue a screen, diagnosing low-confidence hits, choosing between MAGeCK / BAGEL2 / Chronos based on quality grade, picking a normalization strategy from QC signatures, or evaluating whether an in-vivo screen retained adequate library complexity.
日本語の概要は準備中です。原文の説明を表示しています。
Calculates tumor mutational burden from WES/WGS/panel data with Friends of Cancer Research harmonization equations, per-assay calibration (FDA 10/Mb = 7.8 TSO500 = 8.4 OncomineTML), synonymous/indel/germline filtering, hypermutator tiering, blood TMB, and integration with HLA-LOH and neoantigen quality (Luksza 2017 fitness). Use when assessing ICI eligibility under tumor-specific cutoffs (McGrail 2021), comparing tissue vs bTMB, or auditing TMB-H reporting against ESMO 2024 and FDA pembrolizumab pan-tumor 2020.
日本語の概要は準備中です。原文の説明を表示しています。
Comprehensive quality control for CLIP-seq libraries (eCLIP, iCLIP, iCLIP2, PAR-CLIP) covering library complexity (preseq), FRiP, IDR replicate reproducibility, read-distribution metagene, SMInput vs IgG control rationale, rRNA / snoRNA contamination, fragment-length distribution, and ENCODE-compliance thresholds. Use when assessing whether a CLIP library passed, deciding lenient vs stringent peak thresholds, comparing replicates with IDR rescue and self-consistency ratios, or distinguishing failed IP from over-amplified library.
日本語の概要は準備中です。原文の説明を表示しています。
Constructs and validates polygenic risk scores using LDpred2-auto, SBayesRC, MegaPRS, PRS-CS, PROSPER, MUSSEL, BridgePRS, JointPRS, PRSmix, or PGS Catalog Calculator with ancestry-aware reference panels (HapMap3, UKB-LD), Pejaver-style calibration, and PRS-RS reporting standards. Use when computing PRS for cohorts, applying Whiffin-style absolute-risk transformation, assessing cross-ancestry portability (Martin 2017 / Ding 2023 continuous ancestry), or auditing PRS manuscripts against the 22-item PRS-RS reviewer checklist.
日本語の概要は準備中です。原文の説明を表示しています。
Assesses ChIP-seq quality across antibody specificity, fragmentation, enrichment, replicate concordance, and library complexity. Computes FRiP, NSC/RSC (phantompeakqualtools), library complexity (NRF/PBC1/PBC2), deepTools plotFingerprint (JS distance, AUC, synthetic JS), ChIPQC, IDR with ENCODE Nself/Nt rules, and detects hyper-ChIPable artifacts. Use when validating an antibody, diagnosing failed peak calls, deciding whether to proceed with downstream analysis, grading against ENCODE thresholds, or auditing replicate concordance.
日本語の概要は準備中です。原文の説明を表示しています。