「regressions」の検索結果

Detects time and space complexity hotspots via AST scan. Use when code feels slow, before performance-sensitive merges, or to find O(n²) regressions.

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。

Analyze and improve the improvement process. Use for detecting regressions and meta-optimization.

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 to test whether an AI agent, prompt, or skill actually works before or after it ships — build a small eval set, score runs, and catch regressions when the prompt or model changes. Trigger when the user asks whether a prompt is good, wants to compare models or versions, sees inconsistent agent output, or is about to put an agent in front of customers.

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。

Build AI-focused SRE incident response practices for LLM outages, degraded quality, runaway cost events, and safety regressions.

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。

Automatically performs git bisect to identify the first bad commit that introduced a bug or failure. Use when debugging regressions, tracking down when a test started failing, or identifying which commit broke functionality. Handles flaky tests with retry logic and provides comprehensive reports with bisect logs and confidence levels.

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。

Compare runtime behavior between original and migrated repositories to detect behavioral differences, regressions, and semantic changes. Use when validating code migrations, refactorings, language ports, framework upgrades, or any transformation that should preserve behavior. Automatically compares test results, execution traces, API responses, and observable outputs between two repository versions. Provides actionable guidance for fixing deviations and ensuring behavioral equivalence.

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。

Instrument code to support efficient git bisect by producing deterministic pass/fail signals and concise runtime summaries for each tested commit. Use when debugging regressions with git bisect, automating bisect workflows, creating bisect test scripts, handling flaky tests during bisection, or needing clear exit codes and logging for automated bisect runs. Helps identify the exact commit that introduced a bug through automated testing.

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。

Automatically repair buggy code and generate comprehensive tests for Python, Java, and C++ programs. Use when users need to fix logic errors or runtime errors in functions, modules, or repositories. Accepts specifications via natural language descriptions, existing test cases, or input/output examples. Generates corrected code, creates or updates tests to verify correctness and prevent regressions, and produces a detailed report explaining the bug, fix, and testing strategy. Triggers on requests like "fix this bug", "repair this code", "debug this function", or "this code is broken".

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。

Upgrade the Svelte submodule to the latest (or specified) version, regenerate fixtures, identify test failures, and fix all regressions until tests pass 100%.

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。

Design reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate graders, baselines, regression gates, and failure analysis. Use when defining agent quality, comparing prompts or models, validating a release, measuring tool-use reliability, investigating regressions, or deciding whether an agent is ready for production.

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。

Think and work like an expert Database Systems Researcher. Use when a task calls for Database Systems Researcher judgment. Reasons from storage hierarchy, concurrency semantics, query-optimization theory, and declared workload models through TPC-C/H, YCSB, and JOB benchmarks, Jepsen/Elle correctness checkers, and perf/blktrace/fio profiling while treating cardinality-estimation plan regressions, tail-latency spikes under skew, unfair fsync-disabled speedups, and benchmark-trick wins as first-class failure modes.

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 changing REPL clear/reset/resume/surface behavior (onClearTerminal, transcriptSeq remount, Ink Static paths, Ctrl+O/Ctrl+E transitions). Enforces single-owner reset transaction and prevents black-screen/flicker/duplicate-row regressions.

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。

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

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 code changes for bugs, regressions, convention violations, and high-value cleanup opportunities. Use for diffs, commit ranges, hosted PR/MR URLs, branches, paths, staged changes, or working-tree changes.

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。

Test application performance with k6 load/stress/soak/spike scripts and k6 scenarios, Lighthouse CI for Web Vitals, and performance budgets as CI gates. Covers load profiles, custom metrics, bottleneck identification, and Core Web Vitals (LCP, INP, CLS). Use when: "performance test," "load test," "stress test," "soak test," "spike test," "k6," "k6 scenarios," "Lighthouse," "Web Vitals," "Core Web Vitals," "performance budget." Not for: scheduled production probes — use synthetic-monitoring; pixel-diff regressions — use visual-testing; designing tests from prod telemetry — use observability-driven-testing. Related: ci-cd-integration, qa-metrics, release-readiness.

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 for 'why does X work this way', 'why we picked Y', '为什么这么设计', design rationale, regressions, or where a magic number came from. Fans out one investigator per evidence category — in this repo that starts with the local decision record (ADRs, docs/design, the daemon issue store, the changelog, wisp) plus git history, and adds MCP-backed categories when the session has them — then returns a cited read with the gaps named. Use `how` for what the code does at runtime.

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。

Braintrust is a hosted platform for evaluating and tracing LLM applications: it runs a task over a dataset, scores the outputs, stores each run as an experiment and logs production traces. Use when a user asks to write or run a Braintrust eval, score LLM outputs with autoevals, compare prompt or model versions as experiments, run evals in CI and fail on regressions, trace OpenAI or Anthropic calls with Braintrust, manage evaluation datasets, or use the bt CLI.

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。

Run AI agent and LLM evaluations in CI/CD pipelines — automated quality gates that fail the build when AI output quality drops. Use when someone asks to "test my AI agent", "add evals to CI", "catch prompt regressions", "compare models", "evaluate LLM output quality", "set up AI quality gates", or "benchmark my agent before deploying". Covers eval frameworks (Cobalt, Promptfoo, Braintrust), LLM-as-judge scoring, threshold-based assertions, and GitHub Actions integration.

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 pull request for correctness, regressions, and missing tests. Use when a mid-level developer needs structured review guidance.

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。

Runs a long swarm of hundreds to thousands of cheap headless coding workers that drive a large failing-test backlog to green. Failures are clustered by signature, each worker fixes one cluster in its own git worktree, a serial no-regression merge gate lands the fixes, the loop resumes across restarts for hours, and it federates across sibling sessions over git branches when one container's CPU is not enough. Use for "fix these thousands of failing tests with a Haiku swarm", "drive the test suite to green with hundreds of agents", "build this compiler or interpreter against a conformance suite", "launch, relaunch or check in on the swarm loop", "the swarm is stuck, idle or rejecting everything", "parallel agents fixing tests keep hitting merge conflicts and regressions", "add sibling containers to the swarm", or "compare models on the tail the swarm could not fix". Ships the harness, a per-project TOML config, a fake-worker selftest, check-in signals and the 2026-10-12 haiku-cc failure catalogue.

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 an AWF (Agentic Workflow Firewall) failure from an error, workflow run URL, or symptom. Covers auth (api-proxy, enterprise/BYOK Copilot, OIDC, mcpg), ARC/DinD and self-hosted runners, alternative runtimes (gVisor/Kata/chroot), Squid/DNS/egress denials, CI and gh-aw safe-output failures, and suspected security regressions. Routes to the canonical diagnosis registry in docs/diagnostics.

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。

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

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。

SEO drift monitoring: capture baselines of SEO-critical elements, detect changes, and track regressions over time. Git for SEO — baseline, diff, and track changes to your on-page SEO. Use when user says "SEO drift", "baseline", "track changes", "did anything break", "SEO regression", "compare SEO", "before and after", "monitor SEO changes", or "deployment check".

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。

Analyzes a repository and any existing test suite, grades existing tests for weakness, classifies mocks, emits a phased roadmap for building a test suite that catches real regressions, then executes those phases one at a time. Use when planning or building a test suite, assessing whether existing tests are worth anything, adding tests to a legacy codebase, or when the user mentions test coverage, test strategy, or weak tests. Not for reviewing a branch for bugs, and not for fixing the bugs it logs.

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。