327 skills · sorted by relevance
Turn a bug report, improvement request, or experiment into a structured GitHub issue. Check for duplicates, write reproduction steps or testable completion criteria, apply suitable labels, and verify the published title and body.
Investigate code failures, startup problems, and performance regressions involving JAX, Iris, Zephyr, or TPU hardware. It guides failure reproduction, focused hypothesis testing, and infrastructure diagnosis using the relevant operational procedures.
Coordinate specialist agents to investigate suspicious activity in public GitHub repositories. Collect evidence from multiple sources, develop and test hypotheses, verify original records, and produce a report covering timelines, actors, and impact.
Review code that has not yet been checked by forming security hypotheses and testing them with analysis tools. The skill records evidence, checks whether affected code is reachable, searches for related patterns, and preserves review progress across sessions.
Investigate crashes, hangs, incorrect responses, and other failures by testing hypotheses against observed runtime behavior. Confirm the cause, verify the fix with a reproducing test, check the real workflow, and remove temporary debugging artifacts.
Analyze research data with suitable statistical tests, regression, correlation, or Bayesian methods. Check assumptions, estimate effect sizes and uncertainty, plan sample sizes, and prepare figures, tables, and reports following APA academic reporting conventions.
Guide repeated NeMo-RL or NeMo-gym experiments to test hypotheses and improve training settings. Establish a baseline, compare relevant metrics, and preserve reproducible records in git and TSV logs while keeping users involved in launch decisions.
[omh] Native program crashes or corrupts memory: prepare hypothesis-driven debugging of native binaries and instruct the executor to drive a DAP debugger instead of printf. Use when the user says: native-debugging, native debugging, native binary, segfault, segmentation fault, core dump, stack corruption, memory corruption.
The English summary is being prepared. Showing the original description.
[omh] Unvalidated early product idea: test whether a customer problem, segment, and business hypothesis deserve product investment, ending in kill, pivot, persevere, or inconclusive before any PRD. Use when the user says: product-discovery-validation, product discovery validation, product discovery, customer discovery, customer discovery plan, zero to one validation, validate the problem before building, problem solution interview.
The English summary is being prepared. Showing the original description.
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions. Use for /figure-it-out or 'figure it out'.
The English summary is being prepared. Showing the original description.
Design an A/B experiment — hypothesis, variants, primary metric, and sample size. Use when a change can be measured quantitatively at scale. For observing behaviour qualitatively, use `test-scenario`.
The English summary is being prepared. Showing the original description.
Use when the user asks to "test our messaging before we scale it", "design a message-market-fit panel", or "run a 5-second comprehension test on our new tagline"; produces a message-test design spec — hypothesis, panel and recruit criteria, comprehension / 5-second / message-market-fit (Wynter-style) protocols, stimulus set drawn from the canon, success thresholds, and a stop/revise decision rule — for the TALE Evaluate phase so the message is validated before any paid scale. It designs the test; it never runs the experiment or adjudicates a claim. Not for running the panel or A/B experiment — use send-experiment-designer or ad-test-designer; not for analyzing the results — use performance-analyzer; not for authoring the message itself — use message-system-architect. 消息测试/理解度测试/面板设计/五秒测试/消息市场契合
The English summary is being prepared. Showing the original description.
Use when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"; produces a hypothesis, variant matrix, sample-size/duration/power plan, and a documented effect/uncertainty read from own exported results. It applies only a precommitted owner-approved action rule; the statistical helper never chooses a business action. Not for producing variants — use ad-creative-builder; not for reading back one shipped change — use paid-measurement-loop. 广告AB测试设计/实验设计/显著性判定/增效测试
The English summary is being prepared. Showing the original description.
Use when the user asks to "design an email A/B test", "set up a multivariate subject/CTA test", "run a send-time test", "build a hold-out group", or "is this email result statistically and practically material?"; produces a falsifiable hypothesis, one-variable-per-cell matrix, sample-size/MDE/duration/power plan, and an effect/uncertainty read from own ESP data. Applies only a precommitted owner-approved action rule; the helper never chooses a business action. Not for EQS/vetoes or writing the email. 邮件AB测试设计/多变量测试/发送时间测试/留出组/显著性判定
The English summary is being prepared. Showing the original description.
Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Use when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts.
The English summary is being prepared. Showing the original description.
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions. Use for /figure-it-out or 'figure it out'.
The English summary is being prepared. Showing the original description.
Designs, runs, and reads A/B tests and growth experiments — hypothesis, sample size, duration, and honest interpretation. Use this to plan a test, judge whether a result is real, build an experimentation program, decide what to test next, or diagnose why tests keep producing inconclusive or non-replicating results.
The English summary is being prepared. Showing the original description.
Perform statistical tests, hypothesis testing, correlation analysis, and multiple testing corrections using scipy and statsmodels. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).
The English summary is being prepared. Showing the original description.
Generate a complete NSFC (National Natural Science Foundation of China) General Program grant application in Chinese, following the 2026 official template. Use when the user provides a scientific hypothesis and wants to generate a full grant application document, including abs...
The English summary is being prepared. Showing the original description.
Generates complete programmed-cell-death (PCD) / regulated-cell-death (RCD) bulk-transcriptome oncology research designs from a user-provided disease and mechanism theme. Always use this skill whenever a user wants to design, plan, or structure a cancer bioinformatics study built around cell-death patterns, tumor microenvironment, prognostic modeling, immune landscape analysis, mutation profiling, and computational drug sensitivity. Covers five study patterns (mechanism-gene-set, subtype-discovery, prognostic-signature, immune-response stratification, translational drug-hypothesis) and always outputs four workload configs (Lite / Standard / Advanced / Publication+) with recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, publication upgrade path, and a strictly verified reference literature retrieval layer with real references only.
The English summary is being prepared. Showing the original description.
Refines broad, vague, or aspirational biomedical research objectives into clear, bounded, measurable, executable, and downstream-ready study objective statements. Always use this skill when a user has a general aim such as “explore a mechanism,” “study prognosis,” “investigate biomarkers,” or “look at treatment response,” but the objective is still too broad, non-operational, or too ambiguous to support protocol framing, design selection, analysis planning, or hypothesis design. Never assume that polished wording alone means the objective is actionable. Focus first on objective type, missing operational elements, scope discipline, and downstream-ready formulation.
The English summary is being prepared. Showing the original description.
Use whenever you run statistical analysis for the social sciences (regression, hypothesis tests, econometrics) or read Stata (.dta) / SPSS (.sav) data in this workspace. Enforces an execute-don't-interpret boundary (surface estimates, don't volunteer causal claims), checks the analysis against a preregistration plan for HARKing, verifies reproducible seeds, and reproduces .dta/.sav estimates via R. Flags integrity risks; never certifies the analysis is sound.
The English summary is being prepared. Showing the original description.
Autonomous research engineering — web search orchestration, source synthesis, hypothesis formation, and structured research report generation.
The English summary is being prepared. Showing the original description.
Structured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and resolve defects.
The English summary is being prepared. Showing the original description.