「esp」の検索結果

Diagnose and fix RFDB data disappearing after compaction, where rfdb-server reports a tiny node count (e.g. "15 nodes") on startup despite manifest_index.json showing hundreds of thousands of nodes and segment files existing on disk. Use when: (1) rfdb-server logs "Default database: N nodes" with N orders of magnitude smaller than recent analysis output, (2) /api/stats returns only the most recent commit's nodes, (3) the issue appears AFTER a compaction event (manifest with l1_node_segments populated and node_segments: []), (4) subsequent commits dropped L1 references. Root cause: ManifestStore::create_manifest() initializes l1_node_segments/l1_edge_segments to Vec::new() instead of cloning from current manifest, so any commit AFTER compaction silently orphans all L1 data even though segment .seg files still exist on disk. Compaction injects L1 fields explicitly after create_manifest, but regular commits do not.

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。

RFDB server becomes unresponsive (60s+ timeouts) during enricher addEdges write storms. Use when: (1) RFDB CPU spikes to 60-90% after addEdges calls; (2) subsequent reads time out at 60s; (3) server stays catatonic for 5-15 min after a write storm; (4) Tokio main thread parked (write-lock contention). Root cause: add_edges() calls maybe_auto_flush() which has a memory-pressure path that fires on NODE count — not edge count — and holds the exclusive write lock during disk I/O. Fix: separate maybe_auto_flush_edges() uses byte-limit only.

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 user asks to setup endorctl, install endorctl, run endorctl scan, scan for vulnerabilities, run endor scan or run Endor Labs scan or when any endorctl command fails with 'command not found', 'no such file or directory', authentication errors, 'unauthorized', '403', 'tenant not found', EOF error, or namespace/access errors.

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。

Delegate an approved finite batch of independent engineering or research responsibilities using the operator's existing worker channel. Use for broad repository discovery, multiple search directions, repeated checks and substantial dirty work; keep coupled single tasks with one worker and explicit solo work in the main 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。

MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 31 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.

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 run SQL - especially analytical SQL - on local files (parquet/csv/json), URLs, S3 paths, or remote databases (Postgres, MySQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake) without setting up a server. Provides chDB - embedded ClickHouse SQL in Python with 1000+ functions, Session for stateful multi-step pipelines, parametrized queries, and cross-source joins via `s3()`, `mysql()`, `postgresql()`, `iceberg()`, `deltaLake()`, `remoteSecure()` table functions. TRIGGER when: user wants SQL on parquet/csv/files or across remote analytical sources; uses ClickHouse SQL features (window functions, windowFunnel, geoToH3, JSON path ops, Session, parametrized queries); imports `chdb` or calls `chdb.query()`. SKIP this skill for pandas-style DataFrame method-chaining (use chdb-datastore instead) or ClickHouse server administration.

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。

Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood 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。

YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use before /plan-ceo-review or /plan-eng-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。

Review or polish a product UI for accessibility, brand fidelity, hierarchy, rhythm, responsive behavior, themes, interaction states, and generic AI-template patterns. Use for visual audits, accessibility checks, UX polish, UI critique, or pre-ship design review. Do not use for generic code review, backend review, or API design.

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 product-grounded visual quality constraints during user-visible UI changes. Use for layout, styling, content hierarchy, theming, responsive behavior, or interaction affordances. Stay inactive for logic-only changes that preserve the rendered interface.

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。

Multi-platform review analysis — pulls Yelp/Google/TripAdvisor reviews, identifies recurring complaints, sentiment patterns, response rate, and rating trajectory

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, review, and browser-test interactive website page or module HTML from a confirmed UI Architecture Map and visual direction. Use for HTML First Drafts, restrained motion implementation, full-page or module-first prototypes, rendered design review, responsive and interaction QA, page composition, and implementation handoff. Do not use for design exploration, unconfirmed visual or motion direction, content strategy, Design Systems, Elementor controls, CMS templates, or framework components.

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。

重采样：把已有多轮对话数据的每条 assistant 回答丢弃，用 verifier 模型/vLLM 服务逐轮重生成，产出可直接进训练的预分词样本（每行含 input_ids/loss_mask）。依赖支持 return_token_ids 的 OpenAI 兼容 chat 服务（服务需由用户提前就绪，本技能不负责拉起服务）。触发：用某模型对某个数据集做重采样/重生成（如“对这个数据集用这个模型做重采样”）、把对话回答用模型重写、生成预分词样本/on-policy/MTP 训练数据。

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。

ACTIVATE THIS SKILL FOR ANY SHELL COMMAND OR FILE READ. Check curl, wget, rm, sudo, apt, dpkg, chmod, dd, format, powershell, bash, sh. Check pipe patterns like | sh or | bash. Check shell wrappers like bash -c, xargs, find -exec. Check cloud CLI (aws, gcloud, kubectl, terraform). Check when user says sysadmin told me, Stack Overflow says, is this safe, can I run. Block reading of .env, .ssh, .aws, and credential files. This skill blocks dangerous commands and warns on risky ones. ALWAYS apply the safety protocol from this document before responding about any command.

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。

Programmatic React video best practices for Remotion. Use this skill whenever the user is writing, debugging, or rendering Remotion code — compositions, useCurrentFrame animations, interpolate, spring, Sequence timing, <Img>/<Video>/<Audio> from @remotion/media, staticFile, calculateMetadata, the Studio preview, `npx remotion render`, captions, subtitles, voiceover, audio visualization, ffmpeg, transitions, light leaks, transparent video, Lottie, 3D scenes, Mapbox flyovers. Triggers especially on HtmlInCanvas / "html in canvas" requests, CRT terminal effects, glitch effects, video shaders, WebGL video, and any request to scaffold a new programmatic React video. Owns `remotion render` and everything about Remotion code. Do NOT trigger for finished MP4 ad assembly from existing slides (that is `/video-content`) or for the inspiration-to-MP4 reference-video pipeline (that is `/cmo-video`).

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。

Cluster keywords by search intent and map each cluster to an existing or proposed page, with cannibalization detection from Search Console. Use this skill when the user has a keyword list (saved set, brand/keyword-plan.md, GSC export, or seed topic) and needs page targets, content briefs, or a site map for SEO pages — especially before seo-content or seo-machine page generation. Triggers: "cluster keywords", "keyword mapping", "map keywords to pages", "keyword cannibalization", "which page should target".

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 setting up a secure email inbox for any AI agent — configuring inbound email via Resend, webhooks, tunneling for local development, and implementing security measures to prevent prompt injection attacks. Also use when someone mentions 'agent email', 'bot inbox', 'receive emails for agent', 'agent webhook', 'email security for AI', 'prompt injection via email', 'inbound email for bot', or wants their AI agent to receive and respond to emails securely.

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。

Write copy that converts. Use when writing landing pages, emails, sales copy, headlines, CTAs, social posts, cold emails, or any persuasive text. Triggers on 'copy', 'copywriting', 'sales copy', 'landing page copy', 'cold email', 'headlines', 'write me a page', 'make this convert', 'rewrite this copy', or any request involving persuasive writing. Three modes: Generate (write from scratch), Edit (improve existing copy with Seven Sweeps), Cold Email (outbound sequences). If someone has text that needs to sell harder, this is the skill.

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。

Turn a local talking-head / 口播 video into metadata, transcript, and an AI-composed card-based video where the agent composes cards by cloning styled templates and filling them (designing bespoke only when content needs it), then renders to MP4. Ships with the Interflow AI club sign-off ("Interflow AI 出品"). Use when the user asks for interflow-video-cut, 口播成片, talking-head repurposing, video takeaways, transcript cleanup, or turning a spoken video into a captioned card video.

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。

Unified Al Brooks Price Action trading assistant — auto-detects your need and responds accordingly

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。

Work with the @upstash/vector TypeScript/JavaScript SDK, a serverless vector database for embeddings, similarity search, semantic search, and RAG (retrieval-augmented generation). Use when upserting, querying, fetching, ranging, or deleting vectors, upserting raw text against an index with a built-in embedding model, choosing dense, sparse, or hybrid indexes, filtering by metadata, organizing data with namespaces, running resumable queries, or connecting Upstash Vector to an AI or LLM application. Also use when the user asks for a vector store, vector search, nearest-neighbor or kNN search, embeddings storage, semantic cache, recommendations or similarity features, or a hosted vector index that needs no infrastructure.

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。

Write modern, version-aware C# for .NET repositories. Use when choosing language features across C# versions, especially C# 13 and C# 14, while staying compatible with the repo's target framework and `LangVersion`.

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 the open-source free `NetArchTest.Rules` library for architecture rules in .NET unit tests. Use when a repo wants lightweight, fluent architecture assertions for namespaces, dependencies, or layering.

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。

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

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。