テスト設計、脆弱性診断、品質保証（1.3万 件）
概要と使いどころ
End-to-end Coval audio-quality testing workflow. Launches one run per audio-robustness scenario against the same voice agent + test set + metrics, polls for completion, and produces the multi-run report URL grouped by Persona. Use when a user wants to follow the Testing Across Audio Qualities cookbook (https://docs.coval.dev/guides/testing-across-audio-qualities) without doing each step by hand.
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。
End-to-end Coval adversarial / red-team testing workflow. Builds one adversarial test set (12 core attack vectors plus legitimate controls, each with an expected-behavior checklist), creates a persistent "Adversarial User" persona and a Composite Evaluation metric that scores each scenario against its own expected behaviors, launches a multi-iteration run against the agent (voice or chat), polls for completion, builds a per-scenario pass/fail scorecard, and creates a saved report grouped by Test Case. Use when a user wants to follow the Adversarial & Red-Team Testing cookbook (https://docs.coval.dev/guides/adversarial-red-team-testing) without doing each step by hand. Triggers: "adversarial test set", "red team my agent", "jailbreak / prompt-injection testing", "test my agent against bad actors".
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。
End-to-end Coval accent testing workflow. Creates one persona per accent (each using a distinct accent voice and mirroring your Standard Customer behavior), launches one run per accent against the same voice agent + test set + metrics, polls for completion, builds a per-persona comparison table from the results, and creates the saved multi-run report (grouped by Persona) via the public API. Use when a user wants to follow the Testing Across Accents cookbook (https://docs.coval.dev/guides/testing-across-accents) without doing each step by hand.
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。
Execute a bounded Coval evaluation on explicit test cases, then audit conversation, recording and metric evidence. Use when the user requests a run; does not automatically rerun, tune an agent or schedule evaluations.
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 a Coval accent testing report from runs across different speaker accents. Use when a user provides a Coval report URL, report export, run IDs, screenshots, or metric summary and wants evidence-backed next steps such as prompt changes, STT/confirmation adjustments, accent-robust routing, or expanded accent coverage.
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。
Validate one Coval judge against independent human labels, with grouped development/test separation, class-specific errors and uncertainty. Use for trust claims or calibration; without real labels, prepare review rather than inventing ground truth.
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 the pytest test suite with coverage. Accepts optional filter flags. Use after making changes to verify nothing broke.
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。
Full website SEO audit with parallel subagent delegation. Crawls up to 500 pages, detects business type, delegates to up to 15 specialists (8 always + 7 conditional), generates health score. Use when user says audit, full SEO check, analyze my site, or website health 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。
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
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。
Trial protocol for teaching AI Matrx an expert's knowledge until the platform breaks, fixing it. Use when asked to run an expertise trial, distil a person/creator/recent video into a Masterwork, or test the capture product. NOT for a known-missing feature (use build-sub-feature).
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。
Splits one big Claude task or automation into a set of focused AI Matrx agents that work on the person's own AI Matrx tables, then builds and test-runs each one. Use when the person says "split my task into agents", "turn my automation into AI Matrx agents", "make agents for my work", or after their data has moved into AI Matrx.
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。
Super-Admin-only lock-down pattern. Use before touching admin.admins, admin.admin_audit_log, is_super_admin() / requireSuperAdmin() / selectIsSuperAdmin, app/api/admin/admins/**, app/(admin)/administration/users/admins/**, the admin RPCs (admin_promote, admin_update, admin_revoke, admin_list, admin_list_audit, admin_find_user_by_email), createAdminClient(), a new RLS policy, SECURITY DEFINER RPC, or admin-gated route, or when locking a sensitive table to Super Admin.
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。
Next.js route metadata, per-route favicons, OpenGraph, and Twitter cards. Use when adding a route or layout, adding a favicon or social share image, auditing missing metadata, naming tab titles, or touching createRouteMetadata, createDynamicRouteMetadata, generateFaviconMetadata, or titlePrefix.
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。
Audit-and-fix method for one user setting area across every repo. Use when a setting seems ignored, duplicated or confusing, on 'audit the X settings' or 'why doesn't my X setting apply', or as a lane of the settings sweep. NOT for adding a new setting (use build-sub-feature).
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。
Real tests around a big code change: written first, proven to fail on a planted break, run by a fresh agent in the live product before and after. Use when told to use safety-net, or before a change wide enough that one agent cannot see every way it breaks. NOT for one test (forcing-function-tests).
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 the full on-track check on a conversation, project, or keyword the owner names: find the sessions, extract exactly what he typed, dispatch independent judges who go to the live product as him and report what was missed, plan the remedy, and return one page — what he will see, what is missing, the plan. Use when told to check whether work is on track, to audit a project that has drifted, on 'run the on-track check on X', or when a long campaign is about to freeze, hand off, or claim done.
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。
Working playbook preloaded into the browser-tester helper; the coach updates its Lessons after each round. Use only when acting as browser-tester or coaching it. NOT for general UI work (use matrx-frontend's browser-testing doc).
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。
A live demo or admin page shipped with every feature whose results the user would otherwise not see. Use when adding a backend endpoint or feature with no UI to see it, when output only shows in logs, the DB, or an agent run, or when the user asks 'how do I test this'.
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。
The interview primitive for putting open decisions to an owner. Use on 'grill me', 'stress-test this', or 'what do you need from me before you build this', and whenever a plan, scope, spec, vision, or question ledger needs owner rulings. NOT for steps only a human can perform (use a guided session).
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。
Doctrine for auditing an ENTIRE feature and building it to its ideal state. Use on 'deep dive on X', 'audit the X feature', 'figure out everything X does', 'take over X and finish it', 'bring X up to best practices', or when a whole feature needs overhauling, unifying, or finishing, not patching. NOT for one small addition (use build-sub-feature).
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。
The agent.review_queue register for work Arman must see or test in the UI. Use at the end of any task that produced something reviewable, at the start of a task to check prior feedback, and when reviewing, claiming, routing, or repairing a queue row.
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。
Doctrine for adding a capability INTO a live, existing feature to a world-class bar. Use on 'add X to Y', 'extend Y to support X', a new option, button, setting, endpoint, or tool for Y, or a sub-feature spec to implement. NOT for whole-feature audits or overhauls (use feature-deep-dive).
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。
The re-measure and standing report of the canonical data model's live DB conformance. Use when asked 'where are we at' on DB drift or conformance, to update the drift numbers, when a drift-audit brief is re-issued, or on /drift-audit. NOT the per-table fix recipe (use matrx-frontend's db-canonicalize-table).
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。
The bar every automated test or guard must clear: green only when the real system works. Use when writing, fixing, or reviewing a test, mock, stub, fixture, snapshot, or self-test; adding a regression test for a bug; or about to call work done because tests pass.
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。