「rag」の検索結果

Expert chaos engineer specializing in controlled failure injection, resilience testing, and building antifragile systems. Masters chaos experiments, game day planning, and continuous resilience improvement with focus on learning from failure.

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。

Add a professional footer to README files with engagement prompts, community channels, and call-to-action for subscriptions. Use when you need to enhance your README with a footer that encourages interaction and builds community.

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。

Extracts a company's tone of voice from its own content and turns it into rules a writer or an AI can follow. Phase 1 analyses 15 to 20 pages for sentence, paragraph, word and structure patterns with frequency counts; after the user reviews it, Phase 2 writes the guidelines: tone attributes with before and after examples, a We are / We are not table, tone by context, vocabulary to use and avoid, and open questions. Triggers: "tone of voice", "brand voice", "voice guidelines", "writing style guide", "extract voice from our website", "TOV". Not for visual identity (use /brand-kit) or messaging (use /messaging).

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。

Check a text fragment for potential secrets (API keys, tokens, passwords) BEFORE sending to chat / committing / publishing. Second protection layer on top of the pre-commit hook — manual gate, user explicitly calls on potentially sensitive text.

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 repository documentation: detect drift between code and docs, report coverage by category. Run manually or on triggered drift critical.

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 query a local Markdown knowledge base ("vault"). TWO functions — (1) CONVERT raw files (PDF, Word/docx, PowerPoint/pptx, Excel/xlsx, csv/tsv, images, html, md/txt, json/yaml/code, audio/video) into clean Markdown with retrieval-friendly frontmatter; local-first (pandoc / python-pptx / openpyxl / pymupdf4llm / whisper), with cloud OCR (MinerU) only as a fallback. (2) ANSWER questions over the resulting vault with retrieval discipline — self-monitor coverage, flag missing/lossy content, and propose Maps-of-Content (MOCs). Triggers: "build/sync my local knowledge base", "convert these files to markdown for AI", "整理我的资料库", "把文件转成 md 给 AI 读", "本地知识库", "读我的本地 vault 回答", "这个主题我的资料里怎么说". Not for: one-off web research, or files that are already in a single doc you can read directly.

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-coverage formatted Excel report generation with Dutch market compatibility

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。

Assess MotherDuck costs, plan fit, and ROI using current pricing and the workload’s compute and storage needs.

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。

Load files, object storage, dataframes, or external databases into MotherDuck using an appropriate bulk ingestion path.

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-agent adversarial code review. Spawns three reviewer subagents (Auditor, Adversary, Pragmatist) on a single model, runs a cross-examination round, then deterministically synthesizes a single ranked report. Use this for non-trivial PRs, security-sensitive changes, refactors that touch many files, or any change where one perspective has obvious blind spots. Trigger phrases include "adverse review", "adversarial review", "multi-perspective review", "review my changes from multiple angles", "panel review". NOT suitable for trivial diffs (typos, dependency bumps, formatting).

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。

Perform a thorough, Incan-project-aware code review. Use when the user asks for a review, code critique, PR review, or says /review. Checks Rust anti-patterns, compiler pipeline completeness, error handling, test coverage, style conventions, and RFC compliance specific to the Incan compiler codebase.

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 touched tests and test-adjacent code for style, Result-returning patterns, panic helpers, unwrap/expect use, and obvious coverage gaps. Use when a broad review needs a dedicated test pass or when the user asks for test-review specifically.

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 PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".

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。

Implement the separately maintained Documents React client for AuthCrunch encrypted storage, recovery keys, chunk upload/download, recipient sharing, and safe session handling. Does not implement manager/profile APIs or provision the backend.

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。

Maintain the opt-in encrypted Documents API, immutable account ownership, SQLite ciphertext storage, chunk transactions, recipient key envelopes, configuration parser, and TLS/browser cryptographic tests. The separately maintained React application has its own integration 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。

Maintain required external authorization decisions, gatekeeper and validator hooks, the HTTP JSON plugin, reusable parsers, and protected-request E2E coverage. Excludes credential authentication and claims enrichment.

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。

Maintain authorization ACL rules, typed custom claim fields, their reusable parser, policy integration, and signed-token or authenticated-user E2E 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。

Edit gameplay clips (Valorant, CS2, Fortnite, any shooter) into a music-synced highlight montage, frag movie, velocity edit or TikTok/Reels/Shorts "edit" with beat sync, slow motion, speed ramps, kill zooms, transitions, lyric words, cover image; also copy the editing of a reference video ("com a mesma edição desse vídeo"), or fix a rendered edit that stutters ("travado", "quedas de fps"), has choppy slow motion or kills off the beat. Portuguese - "edita um vídeo", "faz um montage", "highlight", "edit pro TikTok", "faz uma capa". Not for plain trimming, joining or converting clips (use ffmpeg).

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。

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated 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。

Use when the user wants to check dataset quality, diagnose eval issues, or before running evolve. Checks size, difficulty distribution, dead examples, coverage, and splits. Auto-corrects issues found.

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 an AEO-first topical map optimized for AI search citation — entity clusters, query fan-out coverage, information gain scoring, and multi-platform distribution. Produces entity map, content node architecture, schema blueprint, and 90-day publishing calendar. Use when "topical map", "content architecture", "site structure", "topic clusters", "pillar content plan", "AEO map", "AI search architecture", "entity map", "what content should we build", or any request to plan a site's topical structure for AI search visibility.

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。

Pull performance data for published content across every surface — LinkedIn, Dev.to, Google Search Console, GA4, and AI citation tracking (Perplexity, Anthropic, OpenAI). Grades each piece as winner, average, or underperformer and surfaces whether an AI search engine has cited it.

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。

Testing patterns for PHPUnit tests. Use when writing tests, debugging test failures, setting up test coverage, or implementing test patterns for ATmosphere features.

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。

Go-to-market engineering for the Yupcha portfolio (OmniVoice-Studio, the Clay-alternative in this repo, ResuBird). A closed set of executable verbs — research, audit, draft, measure, prepare, publish, escalate — each with a typed contract, required sources, and a risk tier. Use when: (1) researching ICP/competitors/channels/prior art, (2) auditing our own properties for what's actually broken (dead pricing pages, 404ing clone URLs, unfilled demos, licence detection, watermark coverage), (3) drafting docs/comparison pages/release notes/launch copy, (4) measuring real numbers against GOAL.md, (5) preparing a Show HN or a listing up to the send button, (6) any question about whether a GTM action is allowed. Triggers: 'gtm', 'go to market', 'launch', 'show hn', 'growth', 'marketing', 'positioning', 'icp', 'competitors', 'outreach', 'cold email', 'audit our', 'is it ok to', 'can we post', 'promote'.

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。