Results for “beweislast”

Enforces running verification commands and confirming output before claiming work is complete, fixed, or passing, ensuring evidence precedes any success claims.

Require fresh evidence before claiming an implementation, fix, build, or test is complete.

Enforces running verification commands and confirming output before claiming work is complete, fixed, or passing, to prevent false success claims.

Enforces a verification gate before any completion claim, requiring fresh command output as evidence.

Define a lightweight, disposable Proof of Life probe to test a risky hypothesis cheaply and surface harsh truths before building real product.

Automated test validation, coverage checking, and quality metrics with aggressive defaults

Simulates a NeurIPS/SC/ICSE-style peer review with five reviewer personas (HPC, ML, Stats, Reproducibility, Devil's Advocate) that verify every claim against actual result data before submission.

Redige e fundamenta pedido de tutela da EVIDENCIA do CPC 311, que dispensa o perigo de dano. Cobre as 4 hipoteses (abuso do direito de defesa/proposito protelatorio; tese em repetitivo ou sumula vinculante + prova documental; contrato de deposito; peticao instruida com prova documental suficiente sem prova capaz de gerar duvida) e indica quando cabe liminar (incisos II e III, par. unico). Use quando o operador disser tutela da evidencia, art 311, prova documental robusta, tese ja pacificada, abuso de defesa, ou quiser adiantar a tutela sem urgencia.

Runs a persistent verification-and-fix loop, executing existing test suites and browser/desktop checks until the requested surface is verified or a real blocker remains.

Stops fantasy approvals, evidence-based certification - Default to "NEEDS WORK", requires overwhelming proof for production readiness

Designs and executes load tests, covering scenario design, baseline capture, execution configuration, results analysis, and reporting for k6, Locust, Gatling, and JMeter.

Validate skill outputs against assertion manifests to detect regressions, enforce quality gates, and bootstrap starter manifests from historical runs.

Enforces an algorithm-first discipline: state Big-O, data structure, and algorithm family before writing loops, queries, or recursion to catch O(n²), N+1, and brute-force defaults.

Review a code change for changed behavior that could regress without reliable verification catching it. Use when checking whether a change is adequately verified.

NLVR2: A Visual Reasoning Benchmark for Natural Language

Screenshot-obsessed, fantasy-allergic QA specialist - Default to finding 3-5 issues, requires visual proof for everything

Debugging is the scientific method under time pressure.

Use this skill to evaluate which DataQ challenges have winning evidence and which don't. Covers documented vs anecdotal evidence and the 8 high-success patterns.

Scaffolds a per-task verification skill for a repo, including a dev-local launcher, a browser driver, and a verification SOP that spawns a sub-agent to drive the app and produce proof.

Load this skill when the user says "tech debt", "tech-debt", or "/tech-debt", or asks to file/track something they've identified as tech debt. Verifies the claimed problem still exists in the current code, drafts a single [Tech Debt]-prefixed issue from `.github/ISSUE_TEMPLATE/tech-debt-issue.md`, and creates it via `gh issue create` only after the user approves the draft.

A/B test design and experiment planning for paid advertising. Structured hypothesis framework, statistical significance calculator, test duration estimator, sample size calculator, and platform-specific experiment setup guides (Meta Experiments, Google Experiments, LinkedIn A/B). Use when user says A/B test, split test, experiment design, test hypothesis, statistical significance, sample size, or test duration.

Most teams run one test — expected peak for ten minutes — and believe they have

基于证据优先的仓库执行工作流，适用于ECC。当用户需要运行命令、检查仓库、调试CI失败或推送带有精确执行和验证证明的窄修复时使用。

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Enforces a mandatory pre-commit/pre-PR testing gate: detects the test stack, runs the full suite, fixes failures, creates minimal tests when none exist, and verifies coverage before allowing commits.