「verify」の検索結果

Audit whether an enforced-coordination MCP has actually shrunk its ~19 legacy etiquette verbs into the 5 enforced tools — work/act/ask/recall/status — each carrying one denial shape and one transcript event, migrated through a real retirement path (intake-metadata, alias, or doc-history — never a parallel runtime), with zero legacy-verb calls once a body reaches compliance mode C4+. Use when reviewing a broker-collapse migration plan, gating a body's move from advisory (C0-C3) to enforced (C4+) coordination, or verifying IT-018 Broker Collapse compliance. NOT for the inbound trigger→spawn boundary that decides whether an event may spawn an agent at all (use fleet-event-spawn-trust), the capability-token cryptographic mechanism behind a denial (use agentic-zero-trust-security), designing how a swarm of agents invokes and shards work (use swarm-invocation-designer), or auditing an individual PR's mergeability (use agent-pr-authoring).

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。

Produces a narrow-interval quality signal for a WinDAGs skill that a third party can verify without inspecting model weights or method internals. The mechanism is attribution-kNN over a tamper-evident outcome log (task→skills→accept/reject store), combined with a conformal-prediction calibration certificate that provides a formal coverage guarantee. Thompson/Beta sampling is explicitly rejected as a category error: it produces a selection signal for stationary i.i.d. rewards, not an attestation signal for context-dependent LLM output quality. The resulting bundle — outcome-log Merkle root + conformal threshold + optional TEE guardrail signature — constitutes a "narrow-interval trust" credential: verifiable, bounded, and internals-opaque.

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。

Verify every visual-evidence artifact (screenshot/GIF/recording) attached to a PR carries a provenance manifest binding it to real daemon-backed truth — daemon port, run id, transcript head hash, agent node id, commit, and an honest real/fixture/mock source label — and that operator-control-panel PRs cover the required set of proof states. Use when gating a PR's proof artifacts before merge, auditing whether a "LIVE" visual claim is backed by a real daemon run versus a reused or fixture-backed mock, or defining the required state-coverage set for a control-panel change. NOT for the capture technique itself — headless Playwright, `screencapture -x -l`, non-interruptive capture (use port-daddy-agent-skill's visual-evidence doctrine), designing the receipt body schema an artifact attaches to (use agent-work-receipt-designer), or the broader dogfood/Potemkin product-quality bar (use multi-agent-authoring-product-bar).

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。

Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real application on the host.

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 you need to visually interact with a GUI — test buttons, fill forms, verify visual layouts, fuzz web pages, automate user flows, take screenshots, or perform end-to-end QA on any application. Works on cloud VMs, Docker containers, local machines, and sandboxes. Install: pip install cua.

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。

Drive Chrome via the claude-in-chrome MCP to exercise plan.md::Verify steps for a shipped feature. Loads deferred MCP tool schemas, asserts console/network cleanliness, records a GIF for the PR. Used by the browser-verifier agent.

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。