“tool”的搜索结果

Refactor apps so backend owns runtime truth and UI only projects snapshots. Use when tools have split authority. NOT for cosmetic UI work or new features before drift is removed.

中文简介正在准备中。当前显示原文说明。

Audits an Articles of Agreement contract — the daemon-witnessed agreement every official Port Daddy agent signs covering registration, transcript reporting, tool-use gating, file claims, parley conduct, budget limits, and operator control — against the enforcement-beats-hope bar: a clause counts as safe only when it resolves to a concrete, daemon-observable mechanism with a defined denial shape, never a promise the agent might honor. Use when drafting a new agent's Articles, reviewing a compliance-level (C0-C6) claim, deciding whether a clause is genuinely enforced or merely documented, or auditing whether an agent's claimed identity can be trusted. NOT for securing the inbound event-to-spawn path (fleet-event-spawn-trust), designing the relay's transport PKI and signing keys (pd-relay-zero-trust), or tracking an agent's identity and reputation across its whole lifetime after it signs (agent-identity-continuity-reputation).

中文简介正在准备中。当前显示原文说明。

Design decisions for when and what sounds to use in web apps, mobile apps, and desktop native apps — plus how to create them with AI. Covers UI sound vocabulary (confirms, alerts, transitions, errors), platform conventions (iOS, macOS, Material), creating sounds with AI tools (ElevenLabs, AudioCraft, Stable Audio), Web Audio API for procedural sounds, haptic-audio pairing, and the psychology of satisfying vs. annoying UI sounds. Activate on 'app sounds', 'UI sounds', 'notification sound', 'sound design app', 'earcons', 'sonic branding', 'interaction sounds', 'feedback sounds', 'app audio', 'satisfying sounds'. NOT for professional audio engineering (use sound-engineer), Windows 3.1 retro sounds specifically (use win31-audio-design), music composition (use sound-engineer).

中文简介正在准备中。当前显示原文说明。

Plan, evaluate, and adopt agent infrastructure for a named workload. Use for agent runtime/framework selection, agent evaluation or observability plans, memory and tool boundaries, infrastructure cost controls, and organizational adoption. Covers workload-first comparison, risk and recovery planning, held-out evaluation, cost accounting, and staged rollout. Not a vendor ranking or a production certification. NOT for implementing a specific agent behavior (agentic-patterns), building a specific agent (ai-engineer), prompt optimization (prompt-engineer), or conventional ETL workflow design (jury_rig-architect).

中文简介正在准备中。当前显示原文说明。

Cryptographic security for agentic systems — zero-trust agent networking, signed message envelopes (JWS/JWE), capability-based security (ocaps), Merkle tree audit trails, WASM sandboxing, and formal verification. Covers CLI dev tool security, mTLS between agents, permission boundaries (least privilege for AI agents), and supply chain security for skills/plugins. Activate on: "agent security", "zero trust agents", "secure agent communication", "capability-based security", "ocap", "signed messages between agents", "agent audit trail", "sandbox agent execution", "agent permissions", "mTLS agents", "cryptographic verification", "agent supply chain", "OWASP agentic", "prove agent did X", "tamper-proof agent logs". NOT for: application-level SAST scanning (use security-auditor), network firewall rules (use infrastructure), SOC2/HIPAA compliance (organizational), or prompt injection defense (use prompt-engineer).

中文简介正在准备中。当前显示原文说明。

Design RL simulation sandboxes, trajectory datasets, QLoRA/LoRA adaptation plans, eval harnesses, and rollback unhooks for agents learning specific coding behaviors beyond the base model. Use when building or reviewing tool-use training loops, offline trajectories, reward functions, self-improvement harnesses, or Port Daddy agent behavior curricula. NOT for generic ML tutorials, full model training operations, or production deployment without eval gates and safety unhooks.

中文简介正在准备中。当前显示原文说明。

Designs and audits deterministic, authority-filtered partitions of trust-typed context for already admitted bodies or abstract continuation slots. Use when causal context, obligations, disclosure boundaries, vector-space identity, capacity, and omission proofs must survive partitioning. NOT for spawning or admitting agents, choosing worker count, retrieving arbitrary knowledge, writing successor prompts, or granting tools, leases, identity, or effect authority.

中文简介正在准备中。当前显示原文说明。

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

中文简介正在准备中。当前显示原文说明。

Design low-friction UX, interaction patterns, and comeback loops for AI coding assistant apps, agent consoles, background coding agents, and Port Daddy swarm/operator surfaces. Use when creating flows like prompt-to-diff, context attach, plan/apply/review, checkpoint rollback, background-agent dashboards, visual proof, or multi-agent invocation. NOT for generic landing pages, static dashboards, or implementation-only changes without product flow.

中文简介正在准备中。当前显示原文说明。

Improve Coval trace quality after basic ingestion works. Use when traces are sparse, missing useful STT/LLM/TTS/tool spans, missing attributes needed for Coval built-in metrics, or when a customer wants maximum debugging and observability value from agent traces.

中文简介正在准备中。当前显示原文说明。

Delegate a read-only Coval evaluation, simulation, monitoring, product-how-to, or troubleshooting subtask to Sofia through the official Coval MCP consult_sofia tool. Use when the user needs Coval-specific FDE judgment, analysis of organization data, metric or test-set recommendations, or a diagnosis grounded in Coval runs and conversations.

中文简介正在准备中。当前显示原文说明。

Recommend, create, preview, and attach Coval trace-based metrics from OpenTelemetry spans. Use when a user has Coval traces and wants custom trace metrics, trace-aware LLM judge metrics with include_traces, latency, token usage, provider failures, tool behavior, vertical-specific workflow signals, or production monitoring based on trace attributes.

中文简介正在准备中。当前显示原文说明。

Analyze a Coval audio-quality testing report from runs across different voice, speaking-style, volume, interruption, and background-noise scenarios. 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, tool handling fixes, STT/TTS adjustments, trace setup, or expanded audio-scenario coverage.

中文简介正在准备中。当前显示原文说明。

Bing Webmaster Tools + IndexNow extension. Microsoft Copilot citations are fed by the Bing index; this skill makes Bing visibility, link data, and IndexNow URL submission first-class.

中文简介正在准备中。当前显示原文说明。

Recipe for creating or changing a floating window. Use when adding a window, deleting, killing or retiring a window or overlay ('kill this panel', 'remove the X window', consolidating X into Y and deleting X), editing a window component, declaring restore or ephemeral behavior, wiring a ?panels= link or the Tools grid, or a window fails to restore after reload. NOT for drag/resize/tray internals (use window-panels) or for opening an overlay (use overlay-system).

中文简介正在准备中。当前显示原文说明。

Dense UI posture — maximum information density with clear hierarchy. Use when building or reworking admin dashboards, data tables and grids, ops or monitoring views, settings-heavy panels, debug inspectors, state or log viewers, and multi-pane tool UIs someone drives all day.

中文简介正在准备中。当前显示原文说明。

Operating guide for the durable Autonomous Work Loop task fleet. Use when adding work to, coordinating, or working an Autonomous Work Loop campaign, or when calling the work_loop MCP tool.

中文简介正在准备中。当前显示原文说明。

RichDocument action toolkit for markdown and interactive content outside live chat. Use when adding an action or content source, wiring a remote action surface, putting actions on a MarkdownStream/BasicMarkdownContent preview, or touching features/rich-document/**, <RichDocument>, <RichDocumentActionSurface>, registerAction, ContentSourceAdapter, or enableContextMenu. NOT for the live chat message bar (use overlay-system).

中文简介正在准备中。当前显示原文说明。

One-route pattern: public marketing landing plus signed-in workspace. Use when creating or fixing a landing page or a feature's front door, guests see an error, 'make /X work signed out', signed-in users land on a pitch, or ModuleLanding / AuthedWorkspaceCTA. NOT for (public) share viewers or free tools.

中文简介正在准备中。当前显示原文说明。

Redux Toolkit selector rules against re-renders, recalculation warnings, and render loops. Use when writing useSelector/useAppSelector or createSelector, deriving state in a connected component, or seeing 'Selector returned a different result when called with the same parameters'.

中文简介正在准备中。当前显示原文说明。

Pre-ship safety proof for replacing a live implementation with a canonical one. Use when repointing nodes, tools, or services to a new contract, superseding a schema, retiring a legacy or parallel system, or any 'new way replaces the old way' change. NOT for greenfield or unconsumed additive work.

中文简介正在准备中。当前显示原文说明。

Migrating custom icon buttons to TapButtons. Use when replacing a raw <button>, IconButton, or className-styled icon; migrating header, toolbar, or footer icons; lazy-splitting a button's highlight decoration; or on 'tap targets', 'efficiency update', 'lazy split', or making a small component production-ready.

中文简介正在准备中。当前显示原文说明。

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).

中文简介正在准备中。当前显示原文说明。

Rules for every string rendered inside the app, plus the sweep that removes in-app prose. Use when writing or changing a label, hint, description, tooltip, empty state or KPI tile in a .tsx file, or when running Pattern Patrol P14 or asked to find or fix long UI text.

中文简介正在准备中。当前显示原文说明。