7.1K skills · sorted by relevance
Design studies that combine quantitative data, such as surveys, with qualitative evidence, such as interviews. It recommends a suitable design and outlines study phases, participant selection, timing, and ways to combine findings into an integrated interpretation.
Find datasets for a research question and compare whether they support the planned study. Receive ranked candidates with feasibility grades, coverage, access requirements, methodological limitations, and recommended next steps for obtaining the most suitable data.
Audit references in a LaTeX manuscript by checking whether papers exist, bibliographic details are accurate, and cited findings support each claim. Produce a structured report with suggested corrections, then review and apply edits with a change log.
Get a simulated peer review of a paper, abstract, or selected sections. Receive assessments of originality, methods, results, and writing, with specific revision suggestions, severity ratings, and a prioritized checklist for improving the manuscript.
Review whether a proposal, specification, or design decision addresses the right problem and follows from its goals and constraints. Receive prioritized findings with supporting evidence, confidence, and concrete alternatives or questions that would resolve each concern.
Review scientific manuscripts and grant proposals using structured checklists. Assess methods, statistics, reproducibility, ethics, and reporting completeness, then organize findings into a balanced report with major concerns, minor comments, and specific suggestions for revision.
Assess candidate CVEs, identifiers for known vulnerabilities, against observed software, versions, and patch evidence. The skill helps determine whether to continue verification, gather more information, or change testing direction within the authorized scope.
Write structured reviews of scientific manuscripts and grant proposals. Assess methods, statistics, reproducibility, ethics, and reporting completeness, then organize strengths, major concerns, minor issues, and specific suggestions into constructive feedback.
Captures what an AI agent is supposed to do — its purpose, boundaries, and success criteria — as a durable snapshot for anyone building, evaluating, reviewing, or changing it. Explores the user's codebase and docs first, then asks one intent question at a time for what source cannot supply. Hands its answers to ethos-write, which writes ethos.md. Use over generic brainstorming when the goal is an agent's ethos.md.
The English summary is being prepared. Showing the original description.
Use this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq / doca_gpu_eth_txq, standing up the per-CUDA-device doca_gpu context, designing the persistent CUDA kernel that drains the GPU-visible queue, running the dual capability check (DOCA cap-query plus cudaGetDeviceProperties), registering cudaMalloc pools via doca_buf_arr_create_*, or debugging DOCA_ERROR_* returns from the GPUNetIO API. Trigger even when the user does not explicitly mention "DOCA GPUNetIO" or "persistent kernel" — typical implicit phrasings include "CUDA kernel reading packets directly from the NIC", "GPU-initiated networking on BlueField", "DOCA_ERROR_DRIVER on doca_gpu_create", "nvidia_peermem not loaded", "kernel-per-packet is too slow", or "which GPU supports GPU-side packet I/O". Refuse and route elsewhere for general CUDA programming, DOCA Ethernet queue bring-up, DOCA DPA, or DOCA install — those belong to other skills.
The English summary is being prepared. Showing the original description.
Extract methylation calls from Bismark BAM files using bismark_methylation_extractor. Generates per-cytosine reports for CpG, CHG, and CHH contexts. Use when extracting methylation levels from aligned bisulfite sequencing data for downstream analysis.
The English summary is being prepared. Showing the original description.
Differentially methylated region (DMR) detection using methylKit tiles, bsseq BSmooth, and DMRcate. Use when identifying contiguous genomic regions with methylation differences between experimental conditions or cell types.
The English summary is being prepared. Showing the original description.
A step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first). Use when the user says "/fable-method", "use the fable method", or "approach this like Fable", or proactively when starting any multi-step task that no task-specific skill covers. Subcommands - plan (stop after the plan), audit (grade finished work against the loop), report (rewrite an answer outcome-first).
The English summary is being prepared. Showing the original description.
Detects methodological gaps across study design, analysis, validation, bias control, reproducibility, and implementation readiness within a biomedical research area. Use this skill when a user wants to identify what current studies are still methodologically missing, which weaknesses are most consequential, and what upgrade path would produce a stronger next-step study. Always separate design gaps, analysis gaps, validation gaps, and reproducibility gaps. Never treat technical complexity as methodological rigor.
The English summary is being prepared. Showing the original description.
Design Thinking method coaching knowledge across all nine methods including per-method techniques, deep expertise, and industry context (energy, financial services, healthcare, manufacturing, nonprofit and social impact, pharmaceuticals and life sciences, professional services, public sector, retail and CPG)
The English summary is being prepared. Showing the original description.
Cross-method decision tree for calling hits in pooled CRISPR screens. Catalogs statistical models (MAGeCK RRA, MAGeCK MLE, BAGEL2, drugZ, JACKS, Chronos, CERES), experimental designs each is built for, failure modes outside design domain, reconciliation when methods disagree, multiple-testing and effect-size thresholds, the order of operations (count -> QC -> CN-correct -> hit-call -> validate), the second-best-sgRNA conservative rule, and consensus-hit strategy. Use when choosing among MAGeCK / BAGEL2 / drugZ / JACKS / Chronos for a given design, reconciling disagreement across two or three methods on the same screen, deciding whether to require consensus, gating downstream validation by hit-confidence tier, or interpreting unstable hit lists across reruns.
The English summary is being prepared. Showing the original description.
Think and work like an expert Ethologist. Use when a task calls for Ethologist judgment. Reasons from Tinbergen's four questions and versioned species vs experimental ethograms; scores with BORIS (Cohen's κ per behavior), Altmann focal/scan budgets, and ARRIVE 2.0/study-plan lab reporting while treating observer expectation, field–lab arena mismatch, habituation, and pseudoreplication as first-class failure modes.
The English summary is being prepared. Showing the original description.
Differentially methylated region (DMR) detection using methylKit tiles, bsseq BSmooth, and DMRcate. Use when identifying contiguous genomic regions with methylation differences between experimental conditions or cell types.
The English summary is being prepared. Showing the original description.
Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".
The English summary is being prepared. Showing the original description.
Applies the rigorous analytic and moral philosophy of Elizabeth Anscombe (British analytic philosopher, virtue ethics, Intention). Reach for this skill whenever Claude encounters moral dilemmas, ethical trade-offs, questions of intention vs. foresight, or consequentialist/utilitarian reasoning. Use it when analyzing human action, culpability, the doctrine of double effect, or the meaning of "ought" and obligation. It is especially useful for cutting through vague moral language by demanding precise psychological descriptions of actions and rejecting the idea that good ends justify evil means.
The English summary is being prepared. Showing the original description.
Field observation, data collection, and research methods for geographic inquiry. Covers site selection and sampling strategies, field observation techniques (landscape reading, transects, quadrats), survey and interview methods for human geography, GPS and field mapping, environmental monitoring and instrumentation, data recording and field notebooks, ethical considerations in fieldwork, and the integration of field data with GIS analysis. Use when planning geographic field research, designing data collection protocols, evaluating field evidence, or connecting field observations to broader geographic analysis.
The English summary is being prepared. Showing the original description.
Audits a methods section against a 45-item reporting checklist synthesized from the APSA Experimental Section rubric, JARS-Quant, CONSORT, and DA-RT, covering pre-registration, recruitment, randomization and treatments, sample flow and attrition, sample-size justification, three-tier results labeling, conjoint reporting, validity, and open-science infrastructure. Use when checking whether a methods section reports enough, preparing a submission or replication archive, asking what CONSORT, JARS, or DA-RT require, or documenting a deviation from a pre-analysis plan. Writing that plan before data collection goes to pre-registration-writing.
The English summary is being prepared. Showing the original description.
Conduct structured insect behavior observations using sampling protocols, ethogram categories, event recording, interaction logging, environmental context, and summary analysis. Covers focal animal sampling, scan sampling, all-occurrences sampling, and instantaneous sampling methods. Defines a standard insect ethogram with locomotion, feeding, grooming, mating, defense, communication, and rest categories. Includes timestamped event recording, intraspecific and interspecific interaction logging, environmental covariate documentation, and time budget analysis. Use when studying insect behavior for ecological research, documenting behavioral repertoires for a species, observing pollinator activity or predator-prey dynamics, or supporting conservation assessments with behavioral data.
The English summary is being prepared. Showing the original description.
Develop a high-performance liquid chromatography method: define separation goals, select column chemistry and mobile phase, optimize gradient and flow conditions, choose the appropriate detector, and evaluate initial method performance for target analytes in solution or complex matrices.
The English summary is being prepared. Showing the original description.