「diff」の検索結果

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff".

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。

RL 强化学习训练与推理（rollout）路径的算子差异性扫描。当用户提供训练启动脚本路径，要求对比 Megatron 训练路径与 vLLM 推理路径的算子差异（尤其是融合算子 vs 单算子不一致）时使用此 skill。典型触发词包括"训推算子扫描"、"训推差异性"、"算子差异报告"、"融合算子对比"、"train vs infer op diff"。注意：本 skill 通过运行完整 RL 训练脚本（集成 profiling）来采集真实运行时算子（非静态源码扫描，非独立分离运行）。当训练、推理使用不同脚本时禁止触发。

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。

Find the angle that makes something sell. Use this skill whenever the user mentions positioning, angles, differentiation, unique selling proposition, 'how do I stand out', 'what makes us different', value proposition, messaging framework, or 'find the hook'. Also trigger when copy isn't converting (often a positioning problem), when marketing feels generic, when launching a product, creating a lead magnet, writing a landing page, or entering a crowded market. Even if the user is about to write copy without established positioning, run this first — the angle informs everything downstream. Generates 3-5 positioning angles with competitive web research and validation.

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。

Research and analyze competitors to find positioning gaps and strategic opportunities. Use this skill whenever the user mentions competitors, competitive analysis, competitor teardown, market landscape, 'who else does this', 'how are we different', or competitor research. Also trigger when the user is entering a new market, when positioning feels weak or generic, when preparing for a launch, when any downstream skill needs competitors.md but it doesn't exist, or when the user asks about differentiation or market gaps. Even if the user just names a competitor casually ('what does X do?'), this skill likely applies. Three modes: Quick Scan, Deep Teardown, Gap Finder.

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。

Instructions to make or update an app's UI so that it adapts to different Android devices including phones, tablets, foldables, laptops, desktop, TV, Auto and XR. It includes how to handle different window sizes, pointing devices (such as mouse) and text entry devices (such as keyboard) using the Compose MediaQuery API. It also covers multi-pane layouts using Navigation3 Scenes, adaptive UI components (such as buttons) with varying target sizes, and adaptive layouts (including navigation areas - nav rails and nav bars) using the Compose Grid and FlexBox APIs.

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 whenever the user mentions Betaflight, FPV drone firmware, flight-controller config, PID/filter/rates tuning, or blackbox log analysis — or shares a Betaflight artifact: a CLI diff/dump (lines like 'diff all', 'set ', 'feature ', 'resource ') or a .bbl/.bfl blackbox log, even when not named as such — or runs a chirp tuning session via Sweep Studio / FPVLogForge (a chirp log ID to analyse, 'analyse log', 'résultat chirp', iterative Bode/step/Ms tuning). Covers flight symptoms (oscillations, wobble, propwash, jello, hot motors, drift), motor/ESC and RX/ELRS/CRSF setup, builds from 3" to 10" (cinewhoop, tinywhoop, longrange, X-class), version migrations (4.4 → 4.5 → 4.6), and configuring a new drone from scratch (setup wizard). Trigger even when phrased casually ("mon drone wobble", "PID help", "config FC") — under-triggering is worse than over-triggering.

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。

Fetch and display diffs for various scopes (PR, commit, branch, staged, working tree). Used by other skills that need to analyze changes.

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。

Execute git commits using the Conventional Commits specification. Use this skill whenever the user says "commit", "git commit", "/commit", "stage and commit", "make a commit", "save my changes", or asks to commit specific files or all changes. Also triggers on phrases like "push my changes" (commit first), "commit everything", "commit with message X", or whenever git diff/status suggests uncommitted work the user wants to save. Handles auto-staging, diff analysis, message generation, breaking change detection, batch splitting of unrelated changes, safe pushes, and pre-commit hook failures gracefully. Always use this skill rather than ad-hoc git commit commands.

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 any context (blog URL, pasted article, PR diff, meeting notes, release notes, raw prompt) into a narrated explainer mp4 with slides, subtitles, and optionally a talking-head avatar. Uses a free local stack (Pillow + edge-tts + ffmpeg) with optional SadTalker for the avatar. Use when the user says "動画化", "explainer video", "解説動画作って", "ブログを動画に", "記事を動画化", "PRを動画で説明", "議事録を動画化", "context to video", or wants an mp4 from arbitrary text/source. Output is mp4 + srt under the user's chosen project workspace.

Build a new-topic PPTX by reusing an existing reference deck's template (layouts / footers / fonts / palette) while replacing all content from primary sources. Use when "use this product deck's look for a different product deck", "use this deck as template for new topic", "参照デックの体裁で別内容を作る", "既存 PPTX を流用して別テーマで作り直す". Not for deck translation, from-scratch generation, or outline-only planning.

"Apply framing theory to analyze how selection, emphasis, and exclusion shape interpretation of issues. Use this skill when the user needs to deconstruct media or organizational frames, evaluate how different frames affect audience perception and decision-making, or design strategic communication frames — even if they say 'how is this issue being portrayed', 'why do people see this differently', or 'how should we frame this message'.".

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 Difference-in-Differences (DID) to estimate causal treatment effects by comparing changes in outcomes between treatment and control groups. Use this skill when the user evaluates policy interventions, natural experiments, or regulatory changes, needs to test parallel trends, or when they ask 'did this policy work', 'how do I identify causal effects without randomization', or 'what is the treatment effect'.".

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。

Builds and audits a concept-ontology for a regelrecht corpus to decide and verify reference types — cross-law source-binding vs intra-law source-binding vs open-norm leaf vs external-fact leaf — and to catch concept conflation across laws. Core principle: a value's reference type is fixed by WHO derives it, and a binding is sound only when producer and consumer denote the SAME concept; the lexical surface (the word in the text) is not the concept. Detects false friends (one term, different concepts — e.g. a register-based vs a factual "naar de omstandigheden"-based residence/ingezetene concept), orphan plain-params (a value a regulation actually derives, modeled as a brute input), negation/complement re-entry (¬X modeled as an independent leaf next to X), and duplication (one concept re-entered as several independent leafs, losing the single-source-of-truth invariant). Produces a law-level glossary and a stelsel-level concept map with sound same-concept binding edges and flagged lexical-match-but-concept-mismatch edges. Use when deciding whether a value should be cross-law/intra-law/leaf, when the same term means different things across laws, or when a binding might silently conflate concepts.

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。

Works through the surviving mutants that cargo-mutants reports for packages/engine — classify each one as a real test gap, a mutant not worth killing, or dead code, then fix it and verify with `just mutants-diff`. Use when picking up the weekly "Mutatietesten" issue, when asked to improve engine test coverage, or when a pull request fails the Mutation Testing (diff) gate.

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 pull requests, branch diffs, and uncommitted changes in this Flutter repository with a bug-finding mindset. Use when asked to review changes, review a PR, audit a diff, check standards, check compliance, or look for regressions, missing tests, release risks, or architecture mismatches.

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。

Clones a VIDEO ad end to end for a different product or offer, on the Novoads API. The deliverable is a finished rendered MP4 — the WHOLE ad, not its opening, and not a template. Reads the source's style, pacing, camera work, dialogue and tone, adapts it into a Seedance 2.0 prompt, prices it, renders it, files the source beside the clones and diffs each clip's transcript against the approved script. Use for "clone this video ad", "recreate this video for my brand", "make this ad but for my product" when the source is a video, "clone my competitors' VIDEO ads", or a video ad handed over with a product photo. **Among cloners the source's medium decides, not the wording**: "clone this ad" plus a video lands here; a still, or nothing attached, is clone-image-ad, and animating a still as-is is image-to-motion. This pack has no hook-only skill: for the opening alone, clone the whole ad and cut. If it does not move, wrong 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。

Generate and edit images with diffusion models: prompting, seeds, CFG, img2img, inpainting, conditioning, and API integration. Use when adding AI image generation to apps or workflows.

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。

Structured differential diagnosis — generating, prioritizing, and ruling out diagnostic hypotheses.

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。

Compare files, text, and data effectively with diff strategies, semantic comparison, and review workflows.

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。

N-round adversarial review pipeline for empirical research output — the chain from data to LaTeX tables to a manuscript that cites them. A Claude drafter proposes minimal diffs, a deterministic mechanical battery gates every diff from a clean state with a regression gate, a Codex reviewer files check-backed critiques, and a blind judge panel decides residual disputes. Manual-invoke ONLY: trigger when the user explicitly runs /adversarial-empirical-review or names 'adversarial-empirical-review' / 'adversarial empirical review'. Do NOT auto-trigger on generic 'review my results', 'check my tables', or manuscript-editing requests. For prose-style refinement use style-emulation instead; this skill AUDITS WHETHER THE TABLES ARE CORRECT — that each number in the tables is what the analysis code computes, reproduces from the data, and is internally consistent. It is an empirical + code review: the manuscript is read only to resolve table numbering, and prose is not examined.

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 this skill whenever the user asks to run Stata commands, estimate econometric models, work with .dta files, run a .do file, generate Stata output, or do any statistical analysis where Stata is involved. Also trigger when the user mentions Stata variables, Stata syntax, or econometric tasks where Stata is the natural tool, including regressions, IV estimation, diff-in-diff, RDD, panel data, clustering, summary statistics, and margins. Stata runs through pystata on StataNow 19.5 BE; configure once with stata_setup, then drive everything with stata.run() and exchange data directly with pandas. Prefer this skill over subprocess calls or .do-file shelling for Stata work, including cases where the user does not say pystata.

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。

Compare ENCODE experiments across different biosamples, tissues, or cell lines to identify tissue-specific regulatory patterns. Use when the user wants cross-tissue comparison, cell-type comparison, tissue-specific elements, differential chromatin, biosample matching, disease vs normal comparison, developmental time course, constitutive vs variable regulation, or multi-tissue data availability mapping. Handles batch effect detection, biosample hierarchy, and comparison 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。

Rapid UI prototyping — generates 3 visually distinct HTML/CSS components from a text prompt and serves them in a live browser gallery. Use when user runs /prototype, asks to "prototype a UI", "mock up a component", "generate HTML mockups", "create UI variations", "design exploration", "quick UI concept", or wants to see multiple visual approaches to a component. Also trigger when user says "show me different ways to build...", "explore different designs for...", or wants rapid visual exploration of a UI idea — even without saying "prototype" explicitly.

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。

Builds Flux manifests locally, diffs YAML files, patches FluxInstance upgrades, creates authentication secrets, traces GitOps delivery pipelines, and bootstraps clusters with the Flux Operator. Use this skill whenever the user mentions flux-operator, FluxInstance, FluxReport, ResourceSet, ResourceSetInputProvider, Flux CD operator management, or asks about GitOps CLI tooling for Kubernetes with Flux. Also trigger when users ask about building Flux manifests, diffing YAML, patching Flux instances, creating Flux secrets, tracing GitOps delivery pipelines, or bootstrapping clusters with Flux. Even if the user just says "flux operator" or "flux-operator cli" without details, this skill has the authoritative reference.

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。