962 skills · sorted by relevance
Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when shipping agent features, validating prompt changes, or gating deployments on quality.
The English summary is being prepared. Showing the original description.
Evaluate agent behavior with versioned cases and explicit verifiers. Use when comparing agent or prompt changes, reproducing failures, or running agent regression tests.
The English summary is being prepared. Showing the original description.
Run or interpret bounded multi-page Unlighthouse audits for local Lighthouse evidence. Use for site-wide performance, accessibility, best-practice, and SEO regression checks when field data or API quotas are insufficient.
The English summary is being prepared. Showing the original description.
Use when the user asks to "track where my emails are actually landing after I send", "read my seed-list inbox vs spam vs promotions results", "trend my Gmail Postmaster / Microsoft SNDS reputation", or "did placement drop after my last send"; produces a per-provider inbox/spam/promotions placement read, a domain/IP reputation trend from Postmaster + SNDS, a send-over-send delta with named regressions, and a reusable SEND-S placement snapshot on your own exported telemetry. Not for the pre-send SPF/DKIM/DMARC auth pre-flight — use deliverability-qa; not for computing the EQS or running the vetoes — use email-quality-auditor. 邮件收件箱落点监测/收件箱vs垃圾邮件/Postmaster声誉趋势
The English summary is being prepared. Showing the original description.
Machine learning in Python with scikit-learn. Use for classification, regression, clustering, model evaluation, and ML pipelines.
The English summary is being prepared. Showing the original description.
コミット/PR の「全部置換した」「-N%削減」等の完了主張を grep で反証できる残骸や best/typical/worst 試算で検証し、抽出・集約リファクタでは並列度(Promise.all)/fast-path/遅延評価の性能特性退行と、Map/Set 集約キーの cross-kind 衝突による検出漏れも監査する
The English summary is being prepared. Showing the original description.
Ensure code changes keep logs/metrics/traces useful for debugging failures and regressions.
The English summary is being prepared. Showing the original description.
Verifies bug fixes are correct and complete by tracing callers, checking imports/exports, validating path resolution, and confirming no regressions. Does the code work? Use when reviewing code changes for functional correctness.
The English summary is being prepared. Showing the original description.
Covers Flutter testing across all three layers: unit tests (business logic, ViewModels, repositories), widget tests (UI rendering, interactions, golden regression), and integration/E2E tests (full app flows, native OS interactions). Use this skill when writing any Flutter test, setting up mocking with mocktail or mockito, implementing golden file tests, debugging async failures (pumpAndSettle timeouts, Timer leaks, FakeAsync deadlocks), fixing cross-platform golden pixel diffs in CI/CD, testing state management (Riverpod/BLoC/Provider), handling permission dialogs or native system UI with Patrol, or troubleshooting MediaQuery/Theme missing errors in widget tests.
The English summary is being prepared. Showing the original description.
Orchestrate any tdmcp test-coverage work: run the coverage harness, inspect coverage gaps, plan focused Vitest/msw or bridge tests, delegate coverage writers, verify coverage deltas, and re-run gates. Use whenever the user asks to raise coverage, add broad regression coverage, create a test harness, improve tests, re-run a coverage wave, or fix a coverage gate.
The English summary is being prepared. Showing the original description.
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
The English summary is being prepared. Showing the original description.
Review FriendlyBet quality, regression risk, test plans, release readiness, version bump discipline, scoring/locking correctness, provider fallback behavior, and dirty-worktree safety. Use before shipping app code, scoring changes, migrations, sports integrations, copy updates, PWA cache changes, or any risky user-facing flow.
The English summary is being prepared. Showing the original description.
Expert en QA exploratoire v4 (tests systématiques, chasse aux bugs, preuves, rapports, régression)
The English summary is being prepared. Showing the original description.
Expert en tests d'agents IA (tests unitaires, intégration, régression, guardrails, red teaming agents)
The English summary is being prepared. Showing the original description.
Write focused tdmcp tests for one assigned coverage gap. Use for Vitest/msw unit tests, integration tests, bridge tests, CLI/config/resource tests, and regression tests that should raise coverage without weakening behavior.
The English summary is being prepared. Showing the original description.
Pixel-based motion and UI change analysis from frame sequences or screenshots using computer vision and visual comparison. Use when `.transition` or visual effects are not observable via MotionEyes logs, when you only have screenshots/video, when you need regression diffs across builds, or when you need to summarize on-screen changes without instrumentation. Do not use when MotionEyes traces are available and you need precise timing/values; use `motioneyes-animation-debug` instead.
The English summary is being prepared. Showing the original description.
Systematically finds and fixes bugs using proven debugging techniques. Traces from symptoms to root cause, implements fixes, and prevents regression.
The English summary is being prepared. Showing the original description.
Use when you need to run real accessibility tests — Playwright keyboard interactions, axe-core scanning, visual regression, and WCAG 2.2 compliance checks. The measurement layer that feeds evidence into a11y-critic reviews.
The English summary is being prepared. Showing the original description.
5-level verification pyramid: static→unit→Playwright E2E (homepage-first, 6bp)→AI visual→post-deploy. 8-check quality gate. Multi-agent testing (functional/security/a11y/performance). Playwright v1.59+ AI agents (Planner/Generator/Healer). WCAG 2.2 AA via axe-core v4.11. Percy+Chromatic visual regression. ADA Title II 2027/2028 deadlines.
The English summary is being prepared. Showing the original description.
Audits security and supply-chain risk between two git refs with Codex cross-validation. 预发布安全审计（含 Codex 交叉验证）。Use when performing pre-release security audits, supply-chain reviews, or comparing two git refs for security regressions. Triggers on “预发布审计”, “security audit”, “release audit”, “安全预审”.
The English summary is being prepared. Showing the original description.
Use after the Lean model changed and before touching backend code — regenerates Kotlin from Lean, lists changed generated symbols, the hand-written files and contract tests that reference them, and golden regressions, so the blast radius is known before implementation.
The English summary is being prepared. Showing the original description.
Use when you need the current position in the Lean spec-driven pipeline, or any deterministic check of a Cradle project — status, golden regression, Lean layer walls, regeneration impact, unslop lint, ddd cleanup. Runs the scripts under scripts/ and reports their output verbatim.
The English summary is being prepared. Showing the original description.
Use after changing prompts, skills, the compiler, or editorial policies — or when the user asks to measure edit quality, run regression evals, check agreement with approved edits, or says '評価して', '一致率を測って', 'eval を回して'. Compares agent output against human-approved golden projects.
The English summary is being prepared. Showing the original description.
Disciplined diagnosis workflow for hard, intermittent, or multi-component bugs and performance regressions: inspect logs and existing evidence, build a feedback loop, test falsifiable hypotheses, instrument gaps, and verify the outcome. Use when the root cause is unclear, reproduction is unreliable, several causes or components are plausible, or performance has regressed. Do NOT use for obvious single-cause errors, straightforward configuration or syntax fixes, planned feature work, or broad architecture review. Diagnosis-only requests stop after reporting the root cause and evidence; apply a fix only when the user requested one.
The English summary is being prepared. Showing the original description.