“regression”的搜索结果

Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.

中文简介正在准备中。当前显示原文说明。

Use this skill to monitor and verify a deployed URL after releases — checks HTTP endpoints, SSE streams, static assets, console errors, and performance regressions after deploys, merges, or dependency upgrades. Smoke / canary / post-deploy verification.

中文简介正在准备中。当前显示原文说明。

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.

中文简介正在准备中。当前显示原文说明。

Remediation only — repair web accessibility (a11y) violations against WCAG 2.2 with a baseline, edit, and verify loop. Takes a target (URL, files, directory) or a findings worklist from `accessibility-scan`/`accessibility-inspect`/`accessibility-audit`, applies mechanical fixes as given, leaves TODOs for visual or contextual judgment, and verifies by re-running the baseline check. It only fixes. To find issues use `accessibility-scan` (one page, automated), `accessibility-inspect` (one page, manual), or `accessibility-audit` (whole site, WCAG-EM); to check for regressions use `accessibility-diff`. Use it for 'fix the a11y issues in X', 'make this accessible', 'add missing alt text and labels', 'apply these accessibility fixes', 'remediate these violations'.

中文简介正在准备中。当前显示原文说明。

Regression check — diff a live page's web accessibility (a11y) violations against a baseline. By default it compares your uncommitted changes (stash-based); pass `--branch [<name>]` to compare against a branch. Reports the new WCAG violations introduced, the ones fixed, and the count of pre-existing ones. Use it for 'did my change break accessibility', 'what a11y issues did this PR add', or as a CI gate. For a full scan of one page use `accessibility-scan`; for a whole site use `accessibility-audit`.

中文简介正在准备中。当前显示原文说明。

Coordinates code quality: ln-511 metrics, ln-512 cleanup, inline agent review (Codex + Gemini), ln-513 regression, ln-514 log analysis. Returns quality_verdict + aggregated results.

中文简介正在准备中。当前显示原文说明。

QA a change by driving the running dev app like a real QA engineer - start the server and a real browser session, write a checklist from the agreed requirements and the diff, execute every item with evidence, then go looking for anything that looks off even where the diff did not touch. Reports findings by severity and separates regressions from pre-existing problems. Use after a change is implemented and the gates pass, when the user asks to "QA this", "test it in the app", or "check it actually works".

中文简介正在准备中。当前显示原文说明。

Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.

中文简介正在准备中。当前显示原文说明。

Optimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times need improvement. Use when profiling reveals bottlenecks that need fixing.

中文简介正在准备中。当前显示原文说明。

Verifies build output integrity after code changes. Runs builds, validates artifact structure, checks for regressions in bundle size, asset references, and static export completeness. The last line of defense before a bad deploy ships.

中文简介正在准备中。当前显示原文说明。

Write meaningful Replica tests. Use when adding regression coverage, testing new behavior, or changing existing automated tests.

中文简介正在准备中。当前显示原文说明。

Trigger when: (1) the user mentions "manim", "scene", "video", "EN/KO render", "GEODE_HERO_LANG", "1080p60", or (2) editing files under `scripts/visualizations/` ending in `.py`, or (3) the user asks to render, re-render, or extend any of the four validated scenes (`geode_hero.py`, `autoresearch_filewalk.py`, `autoresearch_compare.py`, `critical_floor.py`). GEODE Manim Scene authoring standard. Locks the patterns the four validated scenes already share — Anthropic-style palette, Helvetica Neue + Pretendard font pairing with weight=NORMAL, EN/KO multilingual lang via `GEODE_HERO_LANG` env, `_dashed_arrow_with_head` stage-coupled tinting, `verify_hero_layout.py` ratchet — so the next scene does not re-discover the kerning / padding / transition regressions catalogued in [[viz-frame-audit]].

中文简介正在准备中。当前显示原文说明。

Performs subgroup and heterogeneous treatment effect (HTE) analyses for clinical trials. Covers Mantel-Haenszel pooling, Breslow-Day, interaction tests in regression, RERI for additive interaction, modern data-adaptive HTE methods (STEPP, SIDES, causal forests, X/R-learners), Bayesian shrinkage (Dixon-Simon, MAP, EXNEX), graphical multiplicity (Bretz-Maurer), and credibility frameworks (Sun BMJ, EMA 2019). Use when analyzing treatment effects across patient subgroups for regulatory submissions or precision-medicine claims.

中文简介正在准备中。当前显示原文说明。

Performs time-to-event analysis for clinical trials including Cox proportional hazards regression with PH diagnostics, restricted mean survival time (RMST) under non-PH, competing risks via Fine-Gray vs cause-specific Cox, weighted log-rank and MaxCombo for non-proportional hazards, recurrent events (Andersen-Gill, PWP, WLW), and interval-censored data. Use when analyzing time-to-event endpoints (OS, PFS, DOR, TTR, TTNT) in oncology or other clinical trials.

中文简介正在准备中。当前显示原文说明。

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

中文简介正在准备中。当前显示原文说明。

Use when autonomously improving a measurable scalar metric through bounded, git-tracked iterations: modify one scoped change, verify, keep or revert. Triggers on /mk:loop, 'optimize coverage/bundle size/lint count', 'iterate until the metric improves'. NOT for subjective cleanup (see mk:cook), known-root-cause bugs (see mk:fix), behavioral grading (see mk:evaluate), or shipping (see mk:ship).

中文简介正在准备中。当前显示原文说明。

Reflect subskill for simmer. Records iteration results in trajectory table, tracks best candidate, handles regression rollback, and passes ASI forward to the next round. Supports both single-file and workspace modes. Do not invoke directly — called by simmer orchestrator after each judge round.

中文简介正在准备中。当前显示原文说明。

Review code changes for correctness defects, regressions, security risks, data-integrity problems, concurrency hazards, and missing meaningful tests. Use for pull requests, branches, commits, patches, or working-tree reviews; do not use for implementation unless the user separately requests fixes.

中文简介正在准备中。当前显示原文说明。

Design, implement, and evaluate risk-based software tests across unit, integration, contract, end-to-end, and regression layers. Use when adding tests, reproducing bugs, improving coverage, diagnosing flaky tests, or defining a test strategy; do not use to change production behavior unless the user also requests implementation.

中文简介正在准备中。当前显示原文说明。

Optimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times need improvement. Use when profiling reveals bottlenecks that need fixing.

中文简介正在准备中。当前显示原文说明。

Analyze web performance URLs with the PerfGraph CLI and interpret its deterministic reports, causal chains, and prioritized remediation data. Use when the request names perfgraph, or asks to measure or diagnose loading speed, Core Web Vitals, Lighthouse performance, bottlenecks, or web performance regressions.

中文简介正在准备中。当前显示原文说明。

Use when the user reports a hard bug, unexpected failure, or performance regression that needs root-cause analysis.

中文简介正在准备中。当前显示原文说明。

Isolate the root cause of ML performance drops, inconsistent evaluations, prediction errors, and training-serving mismatches across data, labels, splits, pipelines, models, metrics, and runtime behavior. Use when investigating a reproducible failure or regression, not routine model selection or general performance validation.

中文简介正在准备中。当前显示原文说明。

Review local git changes before opening a PR or merging. First review all local tracked and untracked files; if none exist, review the current branch against a requested base branch or the Git Town parent branch. Use zero to three review subagents only when risk, diff size, language specificity, or uncertainty justifies the token cost, then report high-confidence bugs, regressions, risky assumptions, and missing tests. Use when the user asks for code review, local review, branch sanity check, pre-PR review, or review of work-in-progress changes.

中文简介正在准备中。当前显示原文说明。