「bug surface」の検索結果

Use this skill when the user is measuring GPU-kernel-initiated RDMA WRITE latency through doca-gpunetio — building and running the `gpunetio_ib_write_lat` client + server pair under `doca/tools/gpunetio_ib_write_lat/`, checking GPU-NIC pairing, reading the half-iter / full-iter / CUDA-side usec columns, characterizing median / p99 / jitter for a real-time control loop, picking GPUNetIO vs GPI vs CPU-initiated `perftest`, or weighing the latency-vs-batching trade-off. Trigger even without 'GPUNetIO' or 'ib_write_lat': 'GPU kernel RDMA latency benchmark', 'how fast can a CUDA kernel post a WRITE', 'p99 RDMA latency on H100 + ConnectX', 'kernel-launched WR tail latency', or 'compare GPU-init vs CPU-init perftest'. Route elsewhere for bandwidth runs (doca-gpunetio-ib-write-bw), the GPI surface (doca-gpi), library debugging (doca-gpunetio), or DOCA install.

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。

Provides web exploitation techniques for CTF challenges. Use when the target is primarily an HTTP application, API, browser client, template engine, identity flow, or smart-contract frontend/backend surface, including XSS, SQLi, SSTI, SSRF, XXE, JWT, auth bypass, file upload, request smuggling, OAuth/OIDC, SAML, prototype pollution, and similar web bugs. Do not use it for native binary memory corruption, reverse engineering of standalone executables, disk or memory forensics, or pure cryptanalysis unless the web flaw is still the main path to the flag.

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 a deep root-cause investigation on the AWS DevOps Agent. Use when the user describes an incident, alarm, outage, or unexplained behavior — keywords like "5xx", "503", "OOM", "latency spike", "deployment failure", "rollback", "sev1", "investigate", "root cause", "debug", "alarm fired", "service down". Polls and streams progress, then surfaces recommendations.

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。

Generate the dispatcher PCF for a third-party `.ppmplugin` (wrap-runtime) control. Runs `pac pcf init` in the pcf/ subfolder, rewrites ControlManifest.Input.xml from ARCHITECTURE §6, and writes index.ts derived from ARCHITECTURE §4 (message contract), §8 (PCF surface), §9 (error UX) — no placeholders. The bridge dispatches the composite key `<name>/<receiver>` to `NativeModules.<nativeModule>.<method>` via the host-injected `window.PowerApps.NativeExtension.sendAsync` global (never `cordova.exec` — not in the PCF sandbox); also emits a `PowerAppsNativeExtension.d.ts` ambient declaration. Responses are peeled with `extractResponse`. Emits structured JSON debug/error logs. Validated by `npm run build`. **Local only** — does not deploy. Needs only `pac` CLI. Run after the native module exists. Uses npm (not pnpm).

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。

Surfaces PAC CLI upload errors and Dataverse async operation errors, pattern-matches against a known failure catalog, and optionally auto-fixes identified issues. Use when asked to: "diagnose deployment", "debug deployment", "deployment failed", "show deployment errors", "fix deployment issues", "show upload logs", "why did my deploy fail", or "troubleshoot upload".

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 building or debugging Geometry Nodes, headless or live: procedural modeling, scattering objects on a surface, arrays along a curve, repeat or for-each loops, simulation zones, 5.2 physics (cloth, colliders, forces, effectors), closures, bundles, matrices, node-group assets with gizmos. Also when a GN script links nothing, shows red links, ignores modifier inputs, loses instances in a bounding box, or a simulation resets or jumps.

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 QA testing on a page, feature, or full site at one of three depth tiers (smoke, standard, full). Use this skill whenever the user asks to QA a page or site, run a smoke test after a deploy, verify a page before launch, or run a regression sweep. Triggers on QA, QA sweep, smoke test, regression test, post-deploy check, pre-launch check, verify the deploy, test this page, does the page render, broken link, 404, image not loading. Also triggers proactively after a deploy or a new page launch where verification matters. Covers accessibility, performance, and SEO at the surface-signal level only: deep audits belong to `accessibility-audit`, `performance-optimization`, and `seo-technical`, and code-level debugging to `code-review-web`.

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。

Answer a hard question by fanning it out to a PANEL of models running in parallel — each answering independently with web search and bash, none seeing the others' work — then having Opus 4.8 judge every response into a structured analysis (consensus, contradictions, partial coverage, unique insights, blind spots) and write a final answer grounded in it. The panel is two independent Opus 4.8 runs (slug opus4.8-4.8), Opus 4.8 + GPT-5.5 via codex (opus4.8-gpt5.5), Opus 4.8 + Gemini 3.1 Pro via agy (opus4.8-gemini3.1pro), or all three (opus4.8-gpt5.5-gemini3.1pro). Opus always judges and writes the final answer — the pipeline can't be reversed. Runs on local CLI subscriptions (no metered API), and saves a timestamped provenance .md per run. Use this whenever the user asks to "run it through Fusion", says /fusion, wants a multi-model / panel / ensemble answer, wants a question cross-checked across models, or wants a higher-confidence answer with consensus and blind spots surfaced — even if they don't say "fusion". General-purpose: any topic (research, law, strategy, technical, personal). Best for high-stakes research, design calls, and debugging where being confidently wrong is expensive.

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。

Analyzes an existing codebase using strategic Domain-Driven Design to discover bounded contexts, surface ubiquitous language and semantic collisions, find places where code boundaries diverge from domain boundaries, and produce an evidence-backed domain and context map. Use when the goal is DDD-specific: bounded context discovery, ubiquitous language analysis, domain model discovery, or mapping contested ownership and responsibility. The entire repository is a valid scope; no module or directory must be named first. Does not assess architectural coupling, cohesion, or technical debt — use architectural-analysis. Does not design service communication, integration patterns, or deployment topology — use architectural-analysis or plan-a-feature. Does not refactor code, diagnose bugs, or review code quality — use refactor, investigate, or code-review.

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。

Before removing code that looks redundant, wasteful, or "wrong" based on log observations or code review instinct, grep the test suite for tests whose names describe the exact behavior you're about to remove. A test whose title literally describes the "weird" thing (e.g. "calls play() even when player reports playing", "retries even when first call succeeded", "skips cache even when fresh") is a load-bearing workaround, and the production log you're reacting to is probably the workaround working as designed — not a bug. Use when: (1) Tempted to remove a function call that "looks redundant" based on a production log, (2) About to "simplify" a conditional that seems to always take the same branch, (3) Reviewing code and thinking "why would anyone write this?", (4) A log line shows a state that seems impossible or contradictory (e.g. playing=true but positionMs=0 for seconds), (5) CI surfaces a failing test whose name describes exactly what your fix removed.

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。

Apply Andrej Karpathy-inspired coding-agent guidelines in Codex. Use when writing, reviewing, debugging, or refactoring code to surface assumptions, avoid overengineering, keep edits surgical, and define verifiable success criteria.

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。

Build and debug SceneKit scenes where one 3D object (a product, badge, coin, wheel) performs on a transparent stage inside a SwiftUI app - studio lighting, real shadows, baked keyframe choreography, hand-rolled physics, gestures and haptics, multi-scene sequencing. Use when working with SCNView or SceneView in SwiftUI, UIViewRepresentable 3D scenes, product or hero-object animation, roll or spin entrances, a first-frame hitch when a scene appears, shadows missing or wrong, metal rendering black, choreographed 3D motion that must stay interruptible, a continuous vapor stream (vent air, steam, mist) drawn as a shader-driven sheet, a liquid-metal or jelly blob (noise-deformed surface with mirror reflections and tap ripples), chrome or gold that looks cartoon-flat instead of real, HDRI image-based lighting, free trackball rotation of an actor, deterministic screenshot testing of shader-driven scenes, cutting an actor in two with a finger swipe (runtime mesh slicing with sealed cross-sections and a falling piece), a die-struck relief object (badge, coin, medallion) built from a heightfield with multiple finishes on one mesh, an actor crumbling into debris that falls and rests on the floor, reproducing a real object's motion from photos or video, or keyframed motion that stutters at its own keyframes. Not for RealityKit, ARKit, visionOS, or full game worlds.

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。

Independent review loop run before delivery in code work. An independent reviewer (Codex, or fresh Codex-style subagents) reads the whole PR against the approved outcome; the lead fixes in-scope functional findings and re-reviews until none remain. Its differentiator is independence and exhaustiveness — a reviewer that fails differently from the authors, run to clean — distinct from the recursive-refinement ladder. Invoked by the team lead from the unified pre-ship gate (code-mode and /swarm:refine) after the ship steps.

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。

Maps the `hunkdiff/extension` authoring surface for Hunk, the terminal diff viewer — hiding or reordering reviewed files, docked panes, alternate file views, commands and key bindings, dialogs, workspace writes, themes, syntax languages, VCS backends, lifecycle events. Use when writing, debugging, or installing a Hunk extension, or when a request asks Hunk itself to behave differently. Not for reviewing a diff in a live session — that is hunk-review.

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。

Browserless turns Chrome, Firefox, and WebKit into a remote browser service you can self-host or consume as a managed platform. It gives automation stacks a stable WebSocket and REST surface for screenshots, PDFs, scraping, persistent sessions, and debugging without hand-managing browser fleets.

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 measurement surface for ALL Pulp DSP and audio-pipeline work — read it BEFORE writing or gating DSP, not only when something already sounds wrong. Covers the C++ harness (signal generators, metrics, assertions, RenderScenario, contracts), the offline Audio Doctor (magnitude/frequency response, THD/THD+N, phase/group delay), and their Python sibling the Audio Quality Lab (tools/audio/quality-lab — null residual + alignment, LTAS log-spectral distance, spectral flux/centroid, HNR, Theil-Sen drift slope, Kaiser-sinc resampling, license-guarded corpus, regression-net ratchet). TRIGGER on AUTHORING work — "build/design an oscillator/filter/synth/effect", "add a DSP module", "what should the acceptance gate be", "how do I measure aliasing / anti-aliasing / alias floor", "null against a reference", "is this DSP correct", "choose a tolerance", "golden/regression corpus for audio", "measure drift or jitter", "A/B two renders" — AND on DEBUGGING work — "is there sound / no audio / I hear nothing", "does this filter/compressor/synth/delay produce the right signal", "prove the DSP / prove the contract", "measure the frequency response", "what's the THD / is it distorting", "what's the group delay / phase response / measured latency", "magnitude response curve", "render a test tone and assert", "audio regression", "64-frame works but 128 is silent", "sample-rate change pitch-shifted it", "describe what's in this buffer", "audio doctor", "compare before/after a DSP refactor". Reach for this BEFORE hand-rolling any FFT, null test, alias measurement, pitch tracker, or golden-render script — most of it already exists in one of the two lanes. Test/tool layer over HeadlessHost — deterministic, no audio device, no speakers. Off the realtime thread entirely.

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。

Bridge Codex to web-based AI model products by packaging local task context, scrub-checking it, sending it through an approved browser surface to ChatGPT Pro, Claude, Grok, Gemini, or another web model, waiting for the answer, and returning the model response to the user or Codex. Also guide DevSpace-like MCP Connector Mode when the user wants ChatGPT Pro or another MCP-capable web host to access approved local workspaces without relying on Codex browser automation. Use when the user asks for GPT Pro, ChatGPT Pro, Claude web, Grok, Gemini web, web model bridge, external model consult, ask another model, second opinion, use a web AI model, browserless agent access to GPT Pro, MCP connector, DevSpace-like workflow, or send local repo context to a browser-based model for planning, review, debugging, architecture discussion, or implementation guidance.

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。

Build and extend pd-console — Port Daddy's GPU-native macOS operator console (GPUI 0.2.x, Zed's Rust UI). Covers the render-agnostic Block/Pane(Surface) contract, the two-thread reqwest↔smol refresh pipeline, Taffy flexbox layout, uniform_list virtual scroll, focus + keyboard nav, the OKLCH theme and ICS maritime flag badges, GPUI's missing text-input, and the real feature-gated cargo/CI gate. Use when adding panes, visual polish, or debugging GPUI rendering/layout/focus in core/pd-console. NOT for the TypeScript daemon, generic Rust toolchain/borrow-checker help (use rust-with-claude-code), or non-pd GPUI apps with a different theme/architecture.

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 playbook for creating a new NV oOS Pro toolkit under addons/pro/includes/tools/<toolkit> — folder layout, service layer, tool class conventions (canonical envelope, two-gate sanitisation, capability flags), ALL seven registration surfaces (central registry, admin Tools section, settings status map, both WP-CLI commands, schedule presets, workflow presets, SA Toolkit Manager), fixture/oracle testing with a standalone smoke harness, and the phpcs gotcha checklist. Use when asked to build a new Pro toolkit, add a toolkit to the plugin, scaffold toolkit tools, register toolkit presets/toggles, or debug why a new toolkit's tools or presets don't appear. First case study: food-beverage (F&B Management, 21 tools, 2026-10-08, 20/20 Check-totals oracle verified). Complements mcp-ai-wpoos-toolkit-audit (hardening existing toolkits) and mcp-ai-wpoos-test-suite (repair).

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。

Connect and manage Elementor MCP servers as "MCP Apps" on NV oOS assistants — official Elementor MCP (application passwords, permission inheritance, enable/revoke flows), third-party Elementor MCP plugins, the Pro MCP Apps metabox/slash-command/REST surfaces, the Remote Sites "MCP Server" connection type with assistant connection_ref references, auth-type mapping (basic vs header vs oauth), the host allowlist (Security Center setting, constant, filter), tool discovery/bridging into chat, and troubleshooting (allowlist 403s, restricted hosts, protocol fallback, negative discovery cache, same-site in-process bridge, missing connection_ref). Use when connecting an assistant to Elementor MCP, creating a Remote Sites MCP Server connection, using /mcp-app, fixing Test Connection or Discover Tools failures, allowlisting an Elementor host, or debugging bridged elementor_* tools missing from chat.

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。

Scope the real change surface before editing. Use when planning a feature, bugfix, refactor, or review and you need a concrete map of likely touch points, dependencies, tests, and nearby risks.

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。

Investigate AI observability evaluations of both types — `hog` (deterministic code-based) and `llm_judge` (LLM-prompt-based). Find existing evaluations, inspect their configuration, run them against specific generations, query individual pass/fail results, and generate AI-powered summaries of patterns across many runs. Use when the user asks to debug why an evaluation is failing, surface common failure modes, compare results across filters, dry-run a Hog evaluator, prototype a new LLM-judge prompt, or manage the evaluation lifecycle (create, update, enable/disable, delete).

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。

Append structured execution traces across operational, cognitive, and contextual surfaces with minimal overhead. Load when inspecting agent runs, logging tool calls and observations, enabling post-run debugging, or pairing with structured-planning step IDs. Also triggers on "trace this run", "log execution", "agent observability", "run log", or when fault-localize needs evidence. Default-on during multi-step plans. Traces live at .agent-loom/traces/ — git-ignored by default.

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。

[31] ANALYZE. Universal deep thinking methodology for any situation requiring quality reasoning. Use when solving problems, debugging, making decisions, analyzing code, planning, reviewing, or anytime you need thorough thinking instead of surface-level responses. Triggers on "think deeply", "analyze thoroughly", "reason carefully", "deep thinking", "understand completely", or any task requiring careful thought.

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。